1.0

README

@@ -0,0 +1 @@
+TH 基础的yolov5检测模型，不可使用其它版本的yolov5,这个版本应该是yolov5-5.0

data/GlobalWheat2020.yaml

@@ -0,0 +1,55 @@
+# Global Wheat 2020 dataset http://www.global-wheat.com/
+# Train command: python train.py --data GlobalWheat2020.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/GlobalWheat2020
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: # 3422 images
+  - ../datasets/GlobalWheat2020/images/arvalis_1
+  - ../datasets/GlobalWheat2020/images/arvalis_2
+  - ../datasets/GlobalWheat2020/images/arvalis_3
+  - ../datasets/GlobalWheat2020/images/ethz_1
+  - ../datasets/GlobalWheat2020/images/rres_1
+  - ../datasets/GlobalWheat2020/images/inrae_1
+  - ../datasets/GlobalWheat2020/images/usask_1
+
+val: # 748 images (WARNING: train set contains ethz_1)
+  - ../datasets/GlobalWheat2020/images/ethz_1
+
+test: # 1276 images
+  - ../datasets/GlobalWheat2020/images/utokyo_1
+  - ../datasets/GlobalWheat2020/images/utokyo_2
+  - ../datasets/GlobalWheat2020/images/nau_1
+  - ../datasets/GlobalWheat2020/images/uq_1
+
+# number of classes
+nc: 1
+
+# class names
+names: [ 'wheat_head' ]
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+download: |
+  from utils.general import download, Path
+
+  # Download
+  dir = Path('../datasets/GlobalWheat2020')  # dataset directory
+  urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
+          'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
+  download(urls, dir=dir)
+
+  # Make Directories
+  for p in 'annotations', 'images', 'labels':
+      (dir / p).mkdir(parents=True, exist_ok=True)
+
+  # Move
+  for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
+           'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
+      (dir / p).rename(dir / 'images' / p)  # move to /images
+      f = (dir / p).with_suffix('.json')  # json file
+      if f.exists():
+          f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations

data/VisDrone.yaml

@@ -0,0 +1,61 @@
+# VisDrone2019-DET dataset https://github.com/VisDrone/VisDrone-Dataset
+# Train command: python train.py --data VisDrone.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /VisDrone
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../VisDrone/VisDrone2019-DET-train/images  # 6471 images
+val: ../VisDrone/VisDrone2019-DET-val/images  # 548 images
+test: ../VisDrone/VisDrone2019-DET-test-dev/images  # 1610 images
+
+# number of classes
+nc: 10
+
+# class names
+names: [ 'pedestrian', 'people', 'bicycle', 'car', 'van', 'truck', 'tricycle', 'awning-tricycle', 'bus', 'motor' ]
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+download: |
+  from utils.general import download, os, Path
+
+  def visdrone2yolo(dir):
+      from PIL import Image
+      from tqdm import tqdm
+
+      def convert_box(size, box):
+          # Convert VisDrone box to YOLO xywh box
+          dw = 1. / size[0]
+          dh = 1. / size[1]
+          return (box[0] + box[2] / 2) * dw, (box[1] + box[3] / 2) * dh, box[2] * dw, box[3] * dh
+
+      (dir / 'labels').mkdir(parents=True, exist_ok=True)  # make labels directory
+      pbar = tqdm((dir / 'annotations').glob('*.txt'), desc=f'Converting {dir}')
+      for f in pbar:
+          img_size = Image.open((dir / 'images' / f.name).with_suffix('.jpg')).size
+          lines = []
+          with open(f, 'r') as file:  # read annotation.txt
+              for row in [x.split(',') for x in file.read().strip().splitlines()]:
+                  if row[4] == '0':  # VisDrone 'ignored regions' class 0
+                      continue
+                  cls = int(row[5]) - 1
+                  box = convert_box(img_size, tuple(map(int, row[:4])))
+                  lines.append(f"{cls} {' '.join(f'{x:.6f}' for x in box)}\n")
+                  with open(str(f).replace(os.sep + 'annotations' + os.sep, os.sep + 'labels' + os.sep), 'w') as fl:
+                      fl.writelines(lines)  # write label.txt
+
+
+  # Download
+  dir = Path('../VisDrone')  # dataset directory
+  urls = ['https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-train.zip',
+          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-val.zip',
+          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-dev.zip',
+          'https://github.com/ultralytics/yolov5/releases/download/v1.0/VisDrone2019-DET-test-challenge.zip']
+  download(urls, dir=dir)
+
+  # Convert
+  for d in 'VisDrone2019-DET-train', 'VisDrone2019-DET-val', 'VisDrone2019-DET-test-dev':
+      visdrone2yolo(dir / d)  # convert VisDrone annotations to YOLO labels

data/argoverse_hd.yaml

@@ -0,0 +1,21 @@
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
+# Train command: python train.py --data argoverse_hd.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /argoverse
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_argoverse_hd.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../argoverse/Argoverse-1.1/images/train/  # 39384 images
+val: ../argoverse/Argoverse-1.1/images/val/  # 15062 iamges
+test: ../argoverse/Argoverse-1.1/images/test/  # Submit to: https://eval.ai/web/challenges/challenge-page/800/overview
+
+# number of classes
+nc: 8
+
+# class names
+names: [ 'person',  'bicycle',  'car',  'motorcycle',  'bus',  'truck',  'traffic_light',  'stop_sign' ]

data/coco.yaml

@@ -0,0 +1,35 @@
+# COCO 2017 dataset http://cocodataset.org
+# Train command: python train.py --data coco.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /coco
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_coco.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../coco/train2017.txt  # 118287 images
+val: ../coco/val2017.txt  # 5000 images
+test: ../coco/test-dev2017.txt  # 20288 of 40670 images, submit to https://competitions.codalab.org/competitions/20794
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]
+
+# Print classes
+# with open('data/coco.yaml') as f:
+#   d = yaml.safe_load(f)  # dict
+#   for i, x in enumerate(d['names']):
+#     print(i, x)

data/coco128.yaml

@@ -0,0 +1,28 @@
+# COCO 2017 dataset http://cocodataset.org - first 128 training images
+# Train command: python train.py --data coco128.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /coco128
+#     /yolov5
+
+
+# download command/URL (optional)
+download: https://github.com/ultralytics/yolov5/releases/download/v1.0/coco128.zip
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../coco128/images/train2017/  # 128 images
+val: ../coco128/images/train2017/  # 128 images
+
+# number of classes
+nc: 80
+
+# class names
+names: [ 'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train', 'truck', 'boat', 'traffic light',
+         'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep', 'cow',
+         'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+         'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard', 'surfboard',
+         'tennis racket', 'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
+         'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+         'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote', 'keyboard', 'cell phone',
+         'microwave', 'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors', 'teddy bear',
+         'hair drier', 'toothbrush' ]

data/exitPP.yaml

@@ -0,0 +1,47 @@
+# Global Wheat 2020 dataset http://www.global-wheat.com/
+# Train command: python train.py --data GlobalWheat2020.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/GlobalWheat2020
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: # 3422 images
+  - ../../data/exitPP/train/images/
+
+val: # 748 images (WARNING: train set contains ethz_1)
+  - ../../data/exitPP/val/images/
+
+test: # 1276 images
+  - ../../data/exitPP/val/images/
+
+
+# number of classes
+nc: 5
+
+# class names
+names: [ 'ex','dEx','qV','wF','oth']
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+# download: |
+#   from utils.general import download, Path
+
+#   # Download
+#   dir = Path('../datasets/GlobalWheat2020')  # dataset directory
+#   urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
+#           'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
+#   download(urls, dir=dir)
+
+#   # Make Directories
+#   for p in 'annotations', 'images', 'labels':
+#       (dir / p).mkdir(parents=True, exist_ok=True)
+
+#   # Move
+#   for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
+#            'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
+#       (dir / p).rename(dir / 'images' / p)  # move to /images
+#       f = (dir / p).with_suffix('.json')  # json file
+#       if f.exists():
+#           f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations

data/exitPPS.yaml

@@ -0,0 +1,47 @@
+# Global Wheat 2020 dataset http://www.global-wheat.com/
+# Train command: python train.py --data GlobalWheat2020.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/GlobalWheat2020
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: # 3422 images
+  - ../../data/exitPPS/train/images/
+
+val: # 748 images (WARNING: train set contains ethz_1)
+  - ../../data/exitPPS/val/images/
+
+test: # 1276 images
+  - ../../data/exitPPS/val/images/
+
+
+# number of classes
+nc: 9
+
+# class names
+names: [ 'ex','dEx','qV','wF','oth','bdg','rsh','fam','st']
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+# download: |
+#   from utils.general import download, Path
+
+#   # Download
+#   dir = Path('../datasets/GlobalWheat2020')  # dataset directory
+#   urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
+#           'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
+#   download(urls, dir=dir)
+
+#   # Make Directories
+#   for p in 'annotations', 'images', 'labels':
+#       (dir / p).mkdir(parents=True, exist_ok=True)
+
+#   # Move
+#   for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
+#            'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
+#       (dir / p).rename(dir / 'images' / p)  # move to /images
+#       f = (dir / p).with_suffix('.json')  # json file
+#       if f.exists():
+#           f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations

data/exitPlus.yaml

@@ -0,0 +1,47 @@
+# Global Wheat 2020 dataset http://www.global-wheat.com/
+# Train command: python train.py --data GlobalWheat2020.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/GlobalWheat2020
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: # 3422 images
+  - ../../data/exitPlus/train/images/
+
+val: # 748 images (WARNING: train set contains ethz_1)
+  - ../../data/exitPlus/val/images/
+
+test: # 1276 images
+  - ../../data/exitPlus/val/images/
+
+
+# number of classes
+nc: 4
+
+# class names
+names: [ 'exit','dirtyExit','quaticVegetation','waterFloater']
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+# download: |
+#   from utils.general import download, Path
+
+#   # Download
+#   dir = Path('../datasets/GlobalWheat2020')  # dataset directory
+#   urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
+#           'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
+#   download(urls, dir=dir)
+
+#   # Make Directories
+#   for p in 'annotations', 'images', 'labels':
+#       (dir / p).mkdir(parents=True, exist_ok=True)
+
+#   # Move
+#   for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
+#            'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
+#       (dir / p).rename(dir / 'images' / p)  # move to /images
+#       f = (dir / p).with_suffix('.json')  # json file
+#       if f.exists():
+#           f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations

data/exitStone.yaml

@@ -0,0 +1,44 @@
+# Global Wheat 2020 dataset http://www.global-wheat.com/
+# Train command: python train.py --data GlobalWheat2020.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/GlobalWheat2020
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: # 3422 images
+     data/train.txt 
+val: # 748 images (WARNING: train set contains ethz_1)
+    data/val.txt
+test: # 1276 images
+    data/val.txt
+
+# number of classes
+nc: 9
+
+# class names
+names: [ 'ex','dEx','qV','wF','oth','bdg','rsh','fam','st']
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+# download: |
+#   from utils.general import download, Path
+
+#   # Download
+#   dir = Path('../datasets/GlobalWheat2020')  # dataset directory
+#   urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
+#           'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
+#   download(urls, dir=dir)
+
+#   # Make Directories
+#   for p in 'annotations', 'images', 'labels':
+#       (dir / p).mkdir(parents=True, exist_ok=True)
+
+#   # Move
+#   for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
+#            'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
+#       (dir / p).rename(dir / 'images' / p)  # move to /images
+#       f = (dir / p).with_suffix('.json')  # json file
+#       if f.exists():
+#           f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations

data/hyp.finetune.yaml

@@ -0,0 +1,38 @@
+# Hyperparameters for VOC finetuning
+# python train.py --batch 64 --weights yolov5m.pt --data voc.yaml --img 512 --epochs 50
+# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
+
+
+# Hyperparameter Evolution Results
+# Generations: 306
+#                   P         R     mAP.5 mAP.5:.95       box       obj       cls
+# Metrics:        0.6     0.936     0.896     0.684    0.0115   0.00805   0.00146
+
+lr0: 0.0032
+lrf: 0.12
+momentum: 0.843
+weight_decay: 0.00036
+warmup_epochs: 2.0
+warmup_momentum: 0.5
+warmup_bias_lr: 0.05
+box: 0.0296
+cls: 0.243
+cls_pw: 0.631
+obj: 0.301
+obj_pw: 0.911
+iou_t: 0.2
+anchor_t: 2.91
+# anchors: 3.63
+fl_gamma: 0.0
+hsv_h: 0.0138
+hsv_s: 0.664
+hsv_v: 0.464
+degrees: 0.373
+translate: 0.245
+scale: 0.898
+shear: 0.602
+perspective: 0.0
+flipud: 0.00856
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.243

data/hyp.finetune_objects365.yaml

@@ -0,0 +1,28 @@
+lr0: 0.00258
+lrf: 0.17
+momentum: 0.779
+weight_decay: 0.00058
+warmup_epochs: 1.33
+warmup_momentum: 0.86
+warmup_bias_lr: 0.0711
+box: 0.0539
+cls: 0.299
+cls_pw: 0.825
+obj: 0.632
+obj_pw: 1.0
+iou_t: 0.2
+anchor_t: 3.44
+anchors: 3.2
+fl_gamma: 0.0
+hsv_h: 0.0188
+hsv_s: 0.704
+hsv_v: 0.36
+degrees: 0.0
+translate: 0.0902
+scale: 0.491
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.0

data/hyp.scratch.yaml

@@ -0,0 +1,33 @@
+# Hyperparameters for COCO training from scratch
+# python train.py --batch 40 --cfg yolov5m.yaml --weights '' --data coco.yaml --img 640 --epochs 300
+# See tutorials for hyperparameter evolution https://github.com/ultralytics/yolov5#tutorials
+
+
+lr0: 0.01  # initial learning rate (SGD=1E-2, Adam=1E-3)
+lrf: 0.2  # final OneCycleLR learning rate (lr0 * lrf)
+momentum: 0.937  # SGD momentum/Adam beta1
+weight_decay: 0.0005  # optimizer weight decay 5e-4
+warmup_epochs: 3.0  # warmup epochs (fractions ok)
+warmup_momentum: 0.8  # warmup initial momentum
+warmup_bias_lr: 0.1  # warmup initial bias lr
+box: 0.05  # box loss gain
+cls: 0.5  # cls loss gain
+cls_pw: 1.0  # cls BCELoss positive_weight
+obj: 1.0  # obj loss gain (scale with pixels)
+obj_pw: 1.0  # obj BCELoss positive_weight
+iou_t: 0.20  # IoU training threshold
+anchor_t: 4.0  # anchor-multiple threshold
+# anchors: 3  # anchors per output layer (0 to ignore)
+fl_gamma: 0.0  # focal loss gamma (efficientDet default gamma=1.5)
+hsv_h: 0.015  # image HSV-Hue augmentation (fraction)
+hsv_s: 0.7  # image HSV-Saturation augmentation (fraction)
+hsv_v: 0.4  # image HSV-Value augmentation (fraction)
+degrees: 0.0  # image rotation (+/- deg)
+translate: 0.1  # image translation (+/- fraction)
+scale: 0.5  # image scale (+/- gain)
+shear: 0.0  # image shear (+/- deg)
+perspective: 0.0  # image perspective (+/- fraction), range 0-0.001
+flipud: 0.0  # image flip up-down (probability)
+fliplr: 0.5  # image flip left-right (probability)
+mosaic: 1.0  # image mosaic (probability)
+mixup: 0.0  # image mixup (probability)

data/objects365.yaml

@@ -0,0 +1,102 @@
+# Objects365 dataset https://www.objects365.org/
+# Train command: python train.py --data objects365.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/objects365
+#     /yolov5
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../datasets/objects365/images/train  # 1742289 images
+val: ../datasets/objects365/images/val # 5570 images
+
+# number of classes
+nc: 365
+
+# class names
+names: [ 'Person', 'Sneakers', 'Chair', 'Other Shoes', 'Hat', 'Car', 'Lamp', 'Glasses', 'Bottle', 'Desk', 'Cup',
+         'Street Lights', 'Cabinet/shelf', 'Handbag/Satchel', 'Bracelet', 'Plate', 'Picture/Frame', 'Helmet', 'Book',
+         'Gloves', 'Storage box', 'Boat', 'Leather Shoes', 'Flower', 'Bench', 'Potted Plant', 'Bowl/Basin', 'Flag',
+         'Pillow', 'Boots', 'Vase', 'Microphone', 'Necklace', 'Ring', 'SUV', 'Wine Glass', 'Belt', 'Monitor/TV',
+         'Backpack', 'Umbrella', 'Traffic Light', 'Speaker', 'Watch', 'Tie', 'Trash bin Can', 'Slippers', 'Bicycle',
+         'Stool', 'Barrel/bucket', 'Van', 'Couch', 'Sandals', 'Basket', 'Drum', 'Pen/Pencil', 'Bus', 'Wild Bird',
+         'High Heels', 'Motorcycle', 'Guitar', 'Carpet', 'Cell Phone', 'Bread', 'Camera', 'Canned', 'Truck',
+         'Traffic cone', 'Cymbal', 'Lifesaver', 'Towel', 'Stuffed Toy', 'Candle', 'Sailboat', 'Laptop', 'Awning',
+         'Bed', 'Faucet', 'Tent', 'Horse', 'Mirror', 'Power outlet', 'Sink', 'Apple', 'Air Conditioner', 'Knife',
+         'Hockey Stick', 'Paddle', 'Pickup Truck', 'Fork', 'Traffic Sign', 'Balloon', 'Tripod', 'Dog', 'Spoon', 'Clock',
+         'Pot', 'Cow', 'Cake', 'Dinning Table', 'Sheep', 'Hanger', 'Blackboard/Whiteboard', 'Napkin', 'Other Fish',
+         'Orange/Tangerine', 'Toiletry', 'Keyboard', 'Tomato', 'Lantern', 'Machinery Vehicle', 'Fan',
+         'Green Vegetables', 'Banana', 'Baseball Glove', 'Airplane', 'Mouse', 'Train', 'Pumpkin', 'Soccer', 'Skiboard',
+         'Luggage', 'Nightstand', 'Tea pot', 'Telephone', 'Trolley', 'Head Phone', 'Sports Car', 'Stop Sign',
+         'Dessert', 'Scooter', 'Stroller', 'Crane', 'Remote', 'Refrigerator', 'Oven', 'Lemon', 'Duck', 'Baseball Bat',
+         'Surveillance Camera', 'Cat', 'Jug', 'Broccoli', 'Piano', 'Pizza', 'Elephant', 'Skateboard', 'Surfboard',
+         'Gun', 'Skating and Skiing shoes', 'Gas stove', 'Donut', 'Bow Tie', 'Carrot', 'Toilet', 'Kite', 'Strawberry',
+         'Other Balls', 'Shovel', 'Pepper', 'Computer Box', 'Toilet Paper', 'Cleaning Products', 'Chopsticks',
+         'Microwave', 'Pigeon', 'Baseball', 'Cutting/chopping Board', 'Coffee Table', 'Side Table', 'Scissors',
+         'Marker', 'Pie', 'Ladder', 'Snowboard', 'Cookies', 'Radiator', 'Fire Hydrant', 'Basketball', 'Zebra', 'Grape',
+         'Giraffe', 'Potato', 'Sausage', 'Tricycle', 'Violin', 'Egg', 'Fire Extinguisher', 'Candy', 'Fire Truck',
+         'Billiards', 'Converter', 'Bathtub', 'Wheelchair', 'Golf Club', 'Briefcase', 'Cucumber', 'Cigar/Cigarette',
+         'Paint Brush', 'Pear', 'Heavy Truck', 'Hamburger', 'Extractor', 'Extension Cord', 'Tong', 'Tennis Racket',
+         'Folder', 'American Football', 'earphone', 'Mask', 'Kettle', 'Tennis', 'Ship', 'Swing', 'Coffee Machine',
+         'Slide', 'Carriage', 'Onion', 'Green beans', 'Projector', 'Frisbee', 'Washing Machine/Drying Machine',
+         'Chicken', 'Printer', 'Watermelon', 'Saxophone', 'Tissue', 'Toothbrush', 'Ice cream', 'Hot-air balloon',
+         'Cello', 'French Fries', 'Scale', 'Trophy', 'Cabbage', 'Hot dog', 'Blender', 'Peach', 'Rice', 'Wallet/Purse',
+         'Volleyball', 'Deer', 'Goose', 'Tape', 'Tablet', 'Cosmetics', 'Trumpet', 'Pineapple', 'Golf Ball',
+         'Ambulance', 'Parking meter', 'Mango', 'Key', 'Hurdle', 'Fishing Rod', 'Medal', 'Flute', 'Brush', 'Penguin',
+         'Megaphone', 'Corn', 'Lettuce', 'Garlic', 'Swan', 'Helicopter', 'Green Onion', 'Sandwich', 'Nuts',
+         'Speed Limit Sign', 'Induction Cooker', 'Broom', 'Trombone', 'Plum', 'Rickshaw', 'Goldfish', 'Kiwi fruit',
+         'Router/modem', 'Poker Card', 'Toaster', 'Shrimp', 'Sushi', 'Cheese', 'Notepaper', 'Cherry', 'Pliers', 'CD',
+         'Pasta', 'Hammer', 'Cue', 'Avocado', 'Hamimelon', 'Flask', 'Mushroom', 'Screwdriver', 'Soap', 'Recorder',
+         'Bear', 'Eggplant', 'Board Eraser', 'Coconut', 'Tape Measure/Ruler', 'Pig', 'Showerhead', 'Globe', 'Chips',
+         'Steak', 'Crosswalk Sign', 'Stapler', 'Camel', 'Formula 1', 'Pomegranate', 'Dishwasher', 'Crab',
+         'Hoverboard', 'Meat ball', 'Rice Cooker', 'Tuba', 'Calculator', 'Papaya', 'Antelope', 'Parrot', 'Seal',
+         'Butterfly', 'Dumbbell', 'Donkey', 'Lion', 'Urinal', 'Dolphin', 'Electric Drill', 'Hair Dryer', 'Egg tart',
+         'Jellyfish', 'Treadmill', 'Lighter', 'Grapefruit', 'Game board', 'Mop', 'Radish', 'Baozi', 'Target', 'French',
+         'Spring Rolls', 'Monkey', 'Rabbit', 'Pencil Case', 'Yak', 'Red Cabbage', 'Binoculars', 'Asparagus', 'Barbell',
+         'Scallop', 'Noddles', 'Comb', 'Dumpling', 'Oyster', 'Table Tennis paddle', 'Cosmetics Brush/Eyeliner Pencil',
+         'Chainsaw', 'Eraser', 'Lobster', 'Durian', 'Okra', 'Lipstick', 'Cosmetics Mirror', 'Curling', 'Table Tennis' ]
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+download: |
+  from pycocotools.coco import COCO
+  from tqdm import tqdm
+
+  from utils.general import download, Path
+
+  # Make Directories
+  dir = Path('../datasets/objects365')  # dataset directory
+  for p in 'images', 'labels':
+      (dir / p).mkdir(parents=True, exist_ok=True)
+      for q in 'train', 'val':
+          (dir / p / q).mkdir(parents=True, exist_ok=True)
+
+  # Download
+  url = "https://dorc.ks3-cn-beijing.ksyun.com/data-set/2020Objects365%E6%95%B0%E6%8D%AE%E9%9B%86/train/"
+  download([url + 'zhiyuan_objv2_train.tar.gz'], dir=dir, delete=False)  # annotations json
+  download([url + f for f in [f'patch{i}.tar.gz' for i in range(51)]], dir=dir / 'images' / 'train',
+           curl=True, delete=False, threads=8)
+
+  # Move
+  train = dir / 'images' / 'train'
+  for f in tqdm(train.rglob('*.jpg'), desc=f'Moving images'):
+      f.rename(train / f.name)  # move to /images/train
+
+  # Labels
+  coco = COCO(dir / 'zhiyuan_objv2_train.json')
+  names = [x["name"] for x in coco.loadCats(coco.getCatIds())]
+  for cid, cat in enumerate(names):
+      catIds = coco.getCatIds(catNms=[cat])
+      imgIds = coco.getImgIds(catIds=catIds)
+      for im in tqdm(coco.loadImgs(imgIds), desc=f'Class {cid + 1}/{len(names)} {cat}'):
+          width, height = im["width"], im["height"]
+          path = Path(im["file_name"])  # image filename
+          try:
+              with open(dir / 'labels' / 'train' / path.with_suffix('.txt').name, 'a') as file:
+                  annIds = coco.getAnnIds(imgIds=im["id"], catIds=catIds, iscrowd=None)
+                  for a in coco.loadAnns(annIds):
+                      x, y, w, h = a['bbox']  # bounding box in xywh (xy top-left corner)
+                      x, y = x + w / 2, y + h / 2  # xy to center
+                      file.write(f"{cid} {x / width:.5f} {y / height:.5f} {w / width:.5f} {h / height:.5f}\n")
+
+          except Exception as e:
+              print(e)

data/outlet.yaml

@@ -0,0 +1,47 @@
+# Global Wheat 2020 dataset http://www.global-wheat.com/
+# Train command: python train.py --data GlobalWheat2020.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /datasets/GlobalWheat2020
+#     /yolov5
+
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: # 3422 images
+  - ../../data/THexit/train/images/
+
+val: # 748 images (WARNING: train set contains ethz_1)
+  - ../../data/THexit/val/images/
+
+test: # 1276 images
+  - ../../data/THexit/val/images/
+
+
+# number of classes
+nc: 2
+
+# class names
+names: [ 'outlet','no' ]
+
+
+# download command/URL (optional) --------------------------------------------------------------------------------------
+# download: |
+#   from utils.general import download, Path
+
+#   # Download
+#   dir = Path('../datasets/GlobalWheat2020')  # dataset directory
+#   urls = ['https://zenodo.org/record/4298502/files/global-wheat-codalab-official.zip',
+#           'https://github.com/ultralytics/yolov5/releases/download/v1.0/GlobalWheat2020_labels.zip']
+#   download(urls, dir=dir)
+
+#   # Make Directories
+#   for p in 'annotations', 'images', 'labels':
+#       (dir / p).mkdir(parents=True, exist_ok=True)
+
+#   # Move
+#   for p in 'arvalis_1', 'arvalis_2', 'arvalis_3', 'ethz_1', 'rres_1', 'inrae_1', 'usask_1', \
+#            'utokyo_1', 'utokyo_2', 'nau_1', 'uq_1':
+#       (dir / p).rename(dir / 'images' / p)  # move to /images
+#       f = (dir / p).with_suffix('.json')  # json file
+#       if f.exists():
+#           f.rename((dir / 'annotations' / p).with_suffix('.json'))  # move to /annotations

data/scripts/get_argoverse_hd.sh

@@ -0,0 +1,61 @@
+#!/bin/bash
+# Argoverse-HD dataset (ring-front-center camera) http://www.cs.cmu.edu/~mengtial/proj/streaming/
+# Download command: bash data/scripts/get_argoverse_hd.sh
+# Train command: python train.py --data argoverse_hd.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /argoverse
+#     /yolov5
+
+# Download/unzip images
+d='../argoverse/' # unzip directory
+mkdir $d
+url=https://argoverse-hd.s3.us-east-2.amazonaws.com/
+f=Argoverse-HD-Full.zip
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f &# download, unzip, remove in background
+wait                                              # finish background tasks
+
+cd ../argoverse/Argoverse-1.1/
+ln -s tracking images
+
+cd ../Argoverse-HD/annotations/
+
+python3 - "$@" <<END
+import json
+from pathlib import Path
+
+annotation_files = ["train.json", "val.json"]
+print("Converting annotations to YOLOv5 format...")
+
+for val in annotation_files:
+    a = json.load(open(val, "rb"))
+
+    label_dict = {}
+    for annot in a['annotations']:
+        img_id = annot['image_id']
+        img_name = a['images'][img_id]['name']
+        img_label_name = img_name[:-3] + "txt"
+
+        cls = annot['category_id']  # instance class id
+        x_center, y_center, width, height = annot['bbox']
+        x_center = (x_center + width / 2) / 1920.  # offset and scale
+        y_center = (y_center + height / 2) / 1200.  # offset and scale
+        width /= 1920.  # scale
+        height /= 1200.  # scale
+
+        img_dir = "./labels/" + a['seq_dirs'][a['images'][annot['image_id']]['sid']]
+
+        Path(img_dir).mkdir(parents=True, exist_ok=True)
+        if img_dir + "/" + img_label_name not in label_dict:
+            label_dict[img_dir + "/" + img_label_name] = []
+
+        label_dict[img_dir + "/" + img_label_name].append(f"{cls} {x_center} {y_center} {width} {height}\n")
+
+    for filename in label_dict:
+        with open(filename, "w") as file:
+            for string in label_dict[filename]:
+                file.write(string)
+
+END
+
+mv ./labels ../../Argoverse-1.1/

data/scripts/get_coco.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# COCO 2017 dataset http://cocodataset.org
+# Download command: bash data/scripts/get_coco.sh
+# Train command: python train.py --data coco.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /coco
+#     /yolov5
+
+# Download/unzip labels
+d='../' # unzip directory
+url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
+f='coco2017labels.zip' # or 'coco2017labels-segments.zip', 68 MB
+echo 'Downloading' $url$f ' ...'
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
+
+# Download/unzip images
+d='../coco/images' # unzip directory
+url=http://images.cocodataset.org/zips/
+f1='train2017.zip' # 19G, 118k images
+f2='val2017.zip'   # 1G, 5k images
+f3='test2017.zip'  # 7G, 41k images (optional)
+for f in $f1 $f2; do
+  echo 'Downloading' $url$f '...'
+  curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
+done
+wait # finish background tasks

data/scripts/get_coco128.sh

@@ -0,0 +1,17 @@
+#!/bin/bash
+# COCO128 dataset https://www.kaggle.com/ultralytics/coco128
+# Download command: bash data/scripts/get_coco128.sh
+# Train command: python train.py --data coco128.yaml
+# Default dataset location is next to /yolov5:
+#   /parent_folder
+#     /coco128
+#     /yolov5
+
+# Download/unzip images and labels
+d='../' # unzip directory
+url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
+f='coco128.zip' # or 'coco2017labels-segments.zip', 68 MB
+echo 'Downloading' $url$f ' ...'
+curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
+
+wait # finish background tasks

data/scripts/get_voc.sh

@@ -0,0 +1,116 @@
+#!/bin/bash
+# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC/
+# Download command: bash data/scripts/get_voc.sh
+# Train command: python train.py --data voc.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /VOC
+#     /yolov5
+
+start=$(date +%s)
+mkdir -p ../tmp
+cd ../tmp/
+
+# Download/unzip images and labels
+d='.' # unzip directory
+url=https://github.com/ultralytics/yolov5/releases/download/v1.0/
+f1=VOCtrainval_06-Nov-2007.zip # 446MB, 5012 images
+f2=VOCtest_06-Nov-2007.zip     # 438MB, 4953 images
+f3=VOCtrainval_11-May-2012.zip # 1.95GB, 17126 images
+for f in $f3 $f2 $f1; do
+  echo 'Downloading' $url$f '...' 
+  curl -L $url$f -o $f && unzip -q $f -d $d && rm $f & # download, unzip, remove in background
+done
+wait # finish background tasks
+
+end=$(date +%s)
+runtime=$((end - start))
+echo "Completed in" $runtime "seconds"
+
+echo "Splitting dataset..."
+python3 - "$@" <<END
+import os
+import xml.etree.ElementTree as ET
+from os import getcwd
+
+sets = [('2012', 'train'), ('2012', 'val'), ('2007', 'train'), ('2007', 'val'), ('2007', 'test')]
+
+classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog",
+           "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
+
+
+def convert_box(size, box):
+    dw = 1. / (size[0])
+    dh = 1. / (size[1])
+    x, y, w, h = (box[0] + box[1]) / 2.0 - 1, (box[2] + box[3]) / 2.0 - 1, box[1] - box[0], box[3] - box[2]
+    return x * dw, y * dh, w * dw, h * dh
+
+
+def convert_annotation(year, image_id):
+    in_file = open('VOCdevkit/VOC%s/Annotations/%s.xml' % (year, image_id))
+    out_file = open('VOCdevkit/VOC%s/labels/%s.txt' % (year, image_id), 'w')
+    tree = ET.parse(in_file)
+    root = tree.getroot()
+    size = root.find('size')
+    w = int(size.find('width').text)
+    h = int(size.find('height').text)
+
+    for obj in root.iter('object'):
+        difficult = obj.find('difficult').text
+        cls = obj.find('name').text
+        if cls not in classes or int(difficult) == 1:
+            continue
+        cls_id = classes.index(cls)
+        xmlbox = obj.find('bndbox')
+        b = (float(xmlbox.find('xmin').text), float(xmlbox.find('xmax').text), float(xmlbox.find('ymin').text),
+             float(xmlbox.find('ymax').text))
+        bb = convert_box((w, h), b)
+        out_file.write(str(cls_id) + " " + " ".join([str(a) for a in bb]) + '\n')
+
+
+cwd = getcwd()
+for year, image_set in sets:
+    if not os.path.exists('VOCdevkit/VOC%s/labels/' % year):
+        os.makedirs('VOCdevkit/VOC%s/labels/' % year)
+    image_ids = open('VOCdevkit/VOC%s/ImageSets/Main/%s.txt' % (year, image_set)).read().strip().split()
+    list_file = open('%s_%s.txt' % (year, image_set), 'w')
+    for image_id in image_ids:
+        list_file.write('%s/VOCdevkit/VOC%s/JPEGImages/%s.jpg\n' % (cwd, year, image_id))
+        convert_annotation(year, image_id)
+    list_file.close()
+END
+
+cat 2007_train.txt 2007_val.txt 2012_train.txt 2012_val.txt >train.txt
+cat 2007_train.txt 2007_val.txt 2007_test.txt 2012_train.txt 2012_val.txt >train.all.txt
+
+mkdir ../VOC ../VOC/images ../VOC/images/train ../VOC/images/val
+mkdir ../VOC/labels ../VOC/labels/train ../VOC/labels/val
+
+python3 - "$@" <<END
+import os
+
+print(os.path.exists('../tmp/train.txt'))
+with open('../tmp/train.txt', 'r') as f:
+    for line in f.readlines():
+        line = "/".join(line.split('/')[-5:]).strip()
+        if os.path.exists("../" + line):
+            os.system("cp ../" + line + " ../VOC/images/train")
+
+        line = line.replace('JPEGImages', 'labels').replace('jpg', 'txt')
+        if os.path.exists("../" + line):
+            os.system("cp ../" + line + " ../VOC/labels/train")
+
+print(os.path.exists('../tmp/2007_test.txt'))
+with open('../tmp/2007_test.txt', 'r') as f:
+    for line in f.readlines():
+        line = "/".join(line.split('/')[-5:]).strip()
+        if os.path.exists("../" + line):
+            os.system("cp ../" + line + " ../VOC/images/val")
+
+        line = line.replace('JPEGImages', 'labels').replace('jpg', 'txt')
+        if os.path.exists("../" + line):
+            os.system("cp ../" + line + " ../VOC/labels/val")
+END
+
+rm -rf ../tmp # remove temporary directory
+echo "VOC download done."

data/val.txt

@@ -0,0 +1,263 @@
+/home/thsw/WJ/data/exitPPS/images/00000626.jpg
+/home/thsw/WJ/data/exitPPS/images/00000480.jpg
+/home/thsw/WJ/data/exitPPS/images/30.jpg
+/home/thsw/WJ/data/exitPPS/images/00000882.jpg
+/home/thsw/WJ/data/exitPPS/images/00000749.jpg
+/home/thsw/WJ/data/exitPPS/images/79.jpg
+/home/thsw/WJ/data/exitPPS/images/00000085.jpg
+/home/thsw/WJ/data/exitPPS/images/00000754.jpg
+/home/thsw/WJ/data/exitPPS/images/00000837.jpg
+/home/thsw/WJ/data/exitPPS/images/00001005.jpg
+/home/thsw/WJ/data/exitPPS/images/00000744.jpg
+/home/thsw/WJ/data/exitPPS/images/00000147.jpg
+/home/thsw/WJ/data/exitPPS/images/00000170.jpg
+/home/thsw/WJ/data/exitPPS/images/00000264.jpg
+/home/thsw/WJ/data/exitPPS/images/00000747.jpg
+/home/thsw/WJ/data/exitPPS/images/00000379.jpg
+/home/thsw/WJ/data/exitPPS/images/00000451.jpg
+/home/thsw/WJ/data/exitPPS/images/00001140.jpg
+/home/thsw/WJ/data/exitPPS/images/00000488.jpg
+/home/thsw/WJ/data/exitPPS/images/00001167.jpg
+/home/thsw/WJ/data/exitPPS/images/00000231.jpg
+/home/thsw/WJ/data/exitPPS/images/00000528.jpg
+/home/thsw/WJ/data/exitPPS/images/00000743.jpg
+/home/thsw/WJ/data/exitPPS/images/00000535.jpg
+/home/thsw/WJ/data/exitPPS/images/00000718.jpg
+/home/thsw/WJ/data/exitPPS/images/63.jpg
+/home/thsw/WJ/data/exitPPS/images/00000157.jpg
+/home/thsw/WJ/data/exitPPS/images/16.jpg
+/home/thsw/WJ/data/exitPPS/images/00000629.jpg
+/home/thsw/WJ/data/exitPPS/images/00000905.jpg
+/home/thsw/WJ/data/exitPPS/images/00001065.jpg
+/home/thsw/WJ/data/exitPPS/images/18.jpg
+/home/thsw/WJ/data/exitPPS/images/00001014.jpg
+/home/thsw/WJ/data/exitPPS/images/00000025.jpg
+/home/thsw/WJ/data/exitPPS/images/00000700.jpg
+/home/thsw/WJ/data/exitPPS/images/00000822.jpg
+/home/thsw/WJ/data/exitPPS/images/00000674.jpg
+/home/thsw/WJ/data/exitPPS/images/00000361.jpg
+/home/thsw/WJ/data/exitPPS/images/00000220.jpg
+/home/thsw/WJ/data/exitPPS/images/00000549.jpg
+/home/thsw/WJ/data/exitPPS/images/00000909.jpg
+/home/thsw/WJ/data/exitPPS/images/00000438.jpg
+/home/thsw/WJ/data/exitPPS/images/00000097.jpg
+/home/thsw/WJ/data/exitPPS/images/00000250.jpg
+/home/thsw/WJ/data/exitPPS/images/00001078.jpg
+/home/thsw/WJ/data/exitPPS/images/39.jpg
+/home/thsw/WJ/data/exitPPS/images/00000112.jpg
+/home/thsw/WJ/data/exitPPS/images/00001194.jpg
+/home/thsw/WJ/data/exitPPS/images/00000037.jpg
+/home/thsw/WJ/data/exitPPS/images/00001181.jpg
+/home/thsw/WJ/data/exitPPS/images/15.jpg
+/home/thsw/WJ/data/exitPPS/images/00000015.jpg
+/home/thsw/WJ/data/exitPPS/images/00001097.jpg
+/home/thsw/WJ/data/exitPPS/images/00000079.jpg
+/home/thsw/WJ/data/exitPPS/images/00000892.jpg
+/home/thsw/WJ/data/exitPPS/images/00000374.jpg
+/home/thsw/WJ/data/exitPPS/images/00000984.jpg
+/home/thsw/WJ/data/exitPPS/images/00000785.jpg
+/home/thsw/WJ/data/exitPPS/images/00000440.jpg
+/home/thsw/WJ/data/exitPPS/images/00000107.jpg
+/home/thsw/WJ/data/exitPPS/images/00000918.jpg
+/home/thsw/WJ/data/exitPPS/images/00000920.jpg
+/home/thsw/WJ/data/exitPPS/images/00000054.jpg
+/home/thsw/WJ/data/exitPPS/images/00000228.jpg
+/home/thsw/WJ/data/exitPPS/images/00000824.jpg
+/home/thsw/WJ/data/exitPPS/images/51.jpg
+/home/thsw/WJ/data/exitPPS/images/00000478.jpg
+/home/thsw/WJ/data/exitPPS/images/00000763.jpg
+/home/thsw/WJ/data/exitPPS/images/00000242.jpg
+/home/thsw/WJ/data/exitPPS/images/00000757.jpg
+/home/thsw/WJ/data/exitPPS/images/00000617.jpg
+/home/thsw/WJ/data/exitPPS/images/00001122.jpg
+/home/thsw/WJ/data/exitPPS/images/72.jpg
+/home/thsw/WJ/data/exitPPS/images/00000960.jpg
+/home/thsw/WJ/data/exitPPS/images/00000871.jpg
+/home/thsw/WJ/data/exitPPS/images/00000122.jpg
+/home/thsw/WJ/data/exitPPS/images/00000782.jpg
+/home/thsw/WJ/data/exitPPS/images/00000603.jpg
+/home/thsw/WJ/data/exitPPS/images/00000843.jpg
+/home/thsw/WJ/data/exitPPS/images/00000742.jpg
+/home/thsw/WJ/data/exitPPS/images/00000795.jpg
+/home/thsw/WJ/data/exitPPS/images/00000049.jpg
+/home/thsw/WJ/data/exitPPS/images/00001161.jpg
+/home/thsw/WJ/data/exitPPS/images/00000985.jpg
+/home/thsw/WJ/data/exitPPS/images/00000452.jpg
+/home/thsw/WJ/data/exitPPS/images/00001093.jpg
+/home/thsw/WJ/data/exitPPS/images/00000521.jpg
+/home/thsw/WJ/data/exitPPS/images/00000269.jpg
+/home/thsw/WJ/data/exitPPS/images/00000391.jpg
+/home/thsw/WJ/data/exitPPS/images/5.jpg
+/home/thsw/WJ/data/exitPPS/images/00000935.jpg
+/home/thsw/WJ/data/exitPPS/images/00000006.jpg
+/home/thsw/WJ/data/exitPPS/images/00000132.jpg
+/home/thsw/WJ/data/exitPPS/images/00000434.jpg
+/home/thsw/WJ/data/exitPPS/images/00000302.jpg
+/home/thsw/WJ/data/exitPPS/images/00000354.jpg
+/home/thsw/WJ/data/exitPPS/images/00000551.jpg
+/home/thsw/WJ/data/exitPPS/images/00001143.jpg
+/home/thsw/WJ/data/exitPPS/images/00000355.jpg
+/home/thsw/WJ/data/exitPPS/images/00000968.jpg
+/home/thsw/WJ/data/exitPPS/images/00000411.jpg
+/home/thsw/WJ/data/exitPPS/images/37.jpg
+/home/thsw/WJ/data/exitPPS/images/00000858.jpg
+/home/thsw/WJ/data/exitPPS/images/00000162.jpg
+/home/thsw/WJ/data/exitPPS/images/00000343.jpg
+/home/thsw/WJ/data/exitPPS/images/32.jpg
+/home/thsw/WJ/data/exitPPS/images/00000919.jpg
+/home/thsw/WJ/data/exitPPS/images/00000336.jpg
+/home/thsw/WJ/data/exitPPS/images/00000857.jpg
+/home/thsw/WJ/data/exitPPS/images/00000787.jpg
+/home/thsw/WJ/data/exitPPS/images/00001050.jpg
+/home/thsw/WJ/data/exitPPS/images/00000796.jpg
+/home/thsw/WJ/data/exitPPS/images/00000155.jpg
+/home/thsw/WJ/data/exitPPS/images/00000115.jpg
+/home/thsw/WJ/data/exitPPS/images/00000750.jpg
+/home/thsw/WJ/data/exitPPS/images/00000694.jpg
+/home/thsw/WJ/data/exitPPS/images/00000249.jpg
+/home/thsw/WJ/data/exitPPS/images/00000697.jpg
+/home/thsw/WJ/data/exitPPS/images/00000675.jpg
+/home/thsw/WJ/data/exitPPS/images/00000460.jpg
+/home/thsw/WJ/data/exitPPS/images/00000459.jpg
+/home/thsw/WJ/data/exitPPS/images/00001164.jpg
+/home/thsw/WJ/data/exitPPS/images/00000324.jpg
+/home/thsw/WJ/data/exitPPS/images/00000292.jpg
+/home/thsw/WJ/data/exitPPS/images/00001125.jpg
+/home/thsw/WJ/data/exitPPS/images/00001004.jpg
+/home/thsw/WJ/data/exitPPS/images/00000772.jpg
+/home/thsw/WJ/data/exitPPS/images/00001104.jpg
+/home/thsw/WJ/data/exitPPS/images/00000518.jpg
+/home/thsw/WJ/data/exitPPS/images/00000377.jpg
+/home/thsw/WJ/data/exitPPS/images/00000262.jpg
+/home/thsw/WJ/data/exitPPS/images/00000522.jpg
+/home/thsw/WJ/data/exitPPS/images/00000316.jpg
+/home/thsw/WJ/data/exitPPS/images/00000550.jpg
+/home/thsw/WJ/data/exitPPS/images/00000143.jpg
+/home/thsw/WJ/data/exitPPS/images/00000876.jpg
+/home/thsw/WJ/data/exitPPS/images/00000225.jpg
+/home/thsw/WJ/data/exitPPS/images/00000712.jpg
+/home/thsw/WJ/data/exitPPS/images/00000561.jpg
+/home/thsw/WJ/data/exitPPS/images/00000650.jpg
+/home/thsw/WJ/data/exitPPS/images/2.jpg
+/home/thsw/WJ/data/exitPPS/images/00000828.jpg
+/home/thsw/WJ/data/exitPPS/images/00000863.jpg
+/home/thsw/WJ/data/exitPPS/images/00000356.jpg
+/home/thsw/WJ/data/exitPPS/images/74.jpg
+/home/thsw/WJ/data/exitPPS/images/00000619.jpg
+/home/thsw/WJ/data/exitPPS/images/00000152.jpg
+/home/thsw/WJ/data/exitPPS/images/00000600.jpg
+/home/thsw/WJ/data/exitPPS/images/00001062.jpg
+/home/thsw/WJ/data/exitPPS/images/75.jpg
+/home/thsw/WJ/data/exitPPS/images/00000720.jpg
+/home/thsw/WJ/data/exitPPS/images/00000903.jpg
+/home/thsw/WJ/data/exitPPS/images/00000375.jpg
+/home/thsw/WJ/data/exitPPS/images/00000400.jpg
+/home/thsw/WJ/data/exitPPS/images/00000010.jpg
+/home/thsw/WJ/data/exitPPS/images/00001128.jpg
+/home/thsw/WJ/data/exitPPS/images/00000094.jpg
+/home/thsw/WJ/data/exitPPS/images/00000586.jpg
+/home/thsw/WJ/data/exitPPS/images/00000078.jpg
+/home/thsw/WJ/data/exitPPS/images/00000313.jpg
+/home/thsw/WJ/data/exitPPS/images/00000270.jpg
+/home/thsw/WJ/data/exitPPS/images/00000719.jpg
+/home/thsw/WJ/data/exitPPS/images/00000332.jpg
+/home/thsw/WJ/data/exitPPS/images/00000031.jpg
+/home/thsw/WJ/data/exitPPS/images/00000676.jpg
+/home/thsw/WJ/data/exitPPS/images/00001114.jpg
+/home/thsw/WJ/data/exitPPS/images/00000707.jpg
+/home/thsw/WJ/data/exitPPS/images/00000976.jpg
+/home/thsw/WJ/data/exitPPS/images/00000055.jpg
+/home/thsw/WJ/data/exitPPS/images/102.jpg
+/home/thsw/WJ/data/exitPPS/images/00000738.jpg
+/home/thsw/WJ/data/exitPPS/images/00000666.jpg
+/home/thsw/WJ/data/exitPPS/images/00000422.jpg
+/home/thsw/WJ/data/exitPPS/images/00000116.jpg
+/home/thsw/WJ/data/exitPPS/images/00001153.jpg
+/home/thsw/WJ/data/exitPPS/images/00000353.jpg
+/home/thsw/WJ/data/exitPPS/images/00000430.jpg
+/home/thsw/WJ/data/exitPPS/images/00001012.jpg
+/home/thsw/WJ/data/exitPPS/images/00000021.jpg
+/home/thsw/WJ/data/exitPPS/images/00000065.jpg
+/home/thsw/WJ/data/exitPPS/images/00000166.jpg
+/home/thsw/WJ/data/exitPPS/images/00000544.jpg
+/home/thsw/WJ/data/exitPPS/images/00000593.jpg
+/home/thsw/WJ/data/exitPPS/images/00001134.jpg
+/home/thsw/WJ/data/exitPPS/images/93.jpg
+/home/thsw/WJ/data/exitPPS/images/00000516.jpg
+/home/thsw/WJ/data/exitPPS/images/00000279.jpg
+/home/thsw/WJ/data/exitPPS/images/00000360.jpg
+/home/thsw/WJ/data/exitPPS/images/00001045.jpg
+/home/thsw/WJ/data/exitPPS/images/00000059.jpg
+/home/thsw/WJ/data/exitPPS/images/55.jpg
+/home/thsw/WJ/data/exitPPS/images/00000877.jpg
+/home/thsw/WJ/data/exitPPS/images/00000267.jpg
+/home/thsw/WJ/data/exitPPS/images/00000042.jpg
+/home/thsw/WJ/data/exitPPS/images/00000627.jpg
+/home/thsw/WJ/data/exitPPS/images/65.jpg
+/home/thsw/WJ/data/exitPPS/images/00000853.jpg
+/home/thsw/WJ/data/exitPPS/images/00000511.jpg
+/home/thsw/WJ/data/exitPPS/images/00000043.jpg
+/home/thsw/WJ/data/exitPPS/images/00000383.jpg
+/home/thsw/WJ/data/exitPPS/images/00000739.jpg
+/home/thsw/WJ/data/exitPPS/images/00000182.jpg
+/home/thsw/WJ/data/exitPPS/images/00001060.jpg
+/home/thsw/WJ/data/exitPPS/images/107.jpg
+/home/thsw/WJ/data/exitPPS/images/00000253.jpg
+/home/thsw/WJ/data/exitPPS/images/00001082.jpg
+/home/thsw/WJ/data/exitPPS/images/00000952.jpg
+/home/thsw/WJ/data/exitPPS/images/00000427.jpg
+/home/thsw/WJ/data/exitPPS/images/00000624.jpg
+/home/thsw/WJ/data/exitPPS/images/00000599.jpg
+/home/thsw/WJ/data/exitPPS/images/00000622.jpg
+/home/thsw/WJ/data/exitPPS/images/00000883.jpg
+/home/thsw/WJ/data/exitPPS/images/00000380.jpg
+/home/thsw/WJ/data/exitPPS/images/00000731.jpg
+/home/thsw/WJ/data/exitPPS/images/00000180.jpg
+/home/thsw/WJ/data/exitPPS/images/00000204.jpg
+/home/thsw/WJ/data/exitPPS/images/00000653.jpg
+/home/thsw/WJ/data/exitPPS/images/00000542.jpg
+/home/thsw/WJ/data/exitPPS/images/00000118.jpg
+/home/thsw/WJ/data/exitPPS/images/00001141.jpg
+/home/thsw/WJ/data/exitPPS/images/00001032.jpg
+/home/thsw/WJ/data/exitPPS/images/00000789.jpg
+/home/thsw/WJ/data/exitPPS/images/00000477.jpg
+/home/thsw/WJ/data/exitPPS/images/00000068.jpg
+/home/thsw/WJ/data/exitPPS/images/00000221.jpg
+/home/thsw/WJ/data/exitPPS/images/00001071.jpg
+/home/thsw/WJ/data/exitPPS/images/00000408.jpg
+/home/thsw/WJ/data/exitPPS/images/00000385.jpg
+/home/thsw/WJ/data/exitPPS/images/00000734.jpg
+/home/thsw/WJ/data/exitPPS/images/00000436.jpg
+/home/thsw/WJ/data/exitPPS/images/78.jpg
+/home/thsw/WJ/data/exitPPS/images/00001142.jpg
+/home/thsw/WJ/data/exitPPS/images/00000886.jpg
+/home/thsw/WJ/data/exitPPS/images/00000523.jpg
+/home/thsw/WJ/data/exitPPS/images/34.jpg
+/home/thsw/WJ/data/exitPPS/images/00000321.jpg
+/home/thsw/WJ/data/exitPPS/images/00000163.jpg
+/home/thsw/WJ/data/exitPPS/images/00000818.jpg
+/home/thsw/WJ/data/exitPPS/images/00000656.jpg
+/home/thsw/WJ/data/exitPPS/images/00000347.jpg
+/home/thsw/WJ/data/exitPPS/images/00000084.jpg
+/home/thsw/WJ/data/exitPPS/images/00000202.jpg
+/home/thsw/WJ/data/exitPPS/images/00000474.jpg
+/home/thsw/WJ/data/exitPPS/images/00000168.jpg
+/home/thsw/WJ/data/exitPPS/images/67.jpg
+/home/thsw/WJ/data/exitPPS/images/00001041.jpg
+/home/thsw/WJ/data/exitPPS/images/00000340.jpg
+/home/thsw/WJ/data/exitPPS/images/00000668.jpg
+/home/thsw/WJ/data/exitPPS/images/00000604.jpg
+/home/thsw/WJ/data/exitPPS/images/00000187.jpg
+/home/thsw/WJ/data/exitPPS/images/00000456.jpg
+/home/thsw/WJ/data/exitPPS/images/00001150.jpg
+/home/thsw/WJ/data/exitPPS/images/00001025.jpg
+/home/thsw/WJ/data/exitPPS/images/00000206.jpg
+/home/thsw/WJ/data/exitPPS/images/00000533.jpg
+/home/thsw/WJ/data/exitPPS/images/00000441.jpg
+/home/thsw/WJ/data/exitPPS/images/00000873.jpg
+/home/thsw/WJ/data/exitPPS/images/00000490.jpg
+/home/thsw/WJ/data/exitPPS/images/00001086.jpg
+/home/thsw/WJ/data/exitPPS/images/00001096.jpg
+/home/thsw/WJ/data/exitPPS/images/00001008.jpg
+/home/thsw/WJ/data/exitPPS/images/00000426.jpg
+/home/thsw/WJ/data/exitPPS/images/00000388.jpg

data/voc.yaml

@@ -0,0 +1,21 @@
+# PASCAL VOC dataset http://host.robots.ox.ac.uk/pascal/VOC/
+# Train command: python train.py --data voc.yaml
+# Default dataset location is next to YOLOv5:
+#   /parent_folder
+#     /VOC
+#     /yolov5
+
+
+# download command/URL (optional)
+download: bash data/scripts/get_voc.sh
+
+# train and val data as 1) directory: path/images/, 2) file: path/images.txt, or 3) list: [path1/images/, path2/images/]
+train: ../VOC/images/train/  # 16551 images
+val: ../VOC/images/val/  # 4952 images
+
+# number of classes
+nc: 20
+
+# class names
+names: [ 'aeroplane', 'bicycle', 'bird', 'boat', 'bottle', 'bus', 'car', 'cat', 'chair', 'cow', 'diningtable', 'dog',
+         'horse', 'motorbike', 'person', 'pottedplant', 'sheep', 'sofa', 'train', 'tvmonitor' ]

detect.py

@@ -0,0 +1,443 @@
+import argparse
+import time
+from pathlib import Path
+import random,string
+import cv2
+import torch
+import torch.backends.cudnn as cudnn
+
+import base64
+import requests
+
+
+from models.experimental import attempt_load
+from utils.datasets import LoadStreams, LoadImages
+from utils.general import check_img_size, check_requirements, check_imshow, non_max_suppression, apply_classifier, \
+    scale_coords, xyxy2xywh, strip_optimizer, set_logging, increment_path
+from utils.plots import plot_one_box,plot_one_box_PIL,draw_painting_joint,get_label_arrays,get_websource,smooth_outline_auto
+from utils.get_offline_url import update_websource_offAndLive,platurlToJsonfile, get_websource_fromTxt
+from utils.torch_utils import select_device, load_classifier, time_synchronized
+import cv2
+import queue
+import os,json,sys
+import numpy as np
+from threading import Thread
+import datetime,_thread
+import subprocess as sp
+import time
+from PIL import Image, ImageDraw, ImageFont
+from segutils.segmodel import SegModel,get_largest_contours
+sys.path.extend(['/home/thsw2/WJ/src/yolov5/segutils'])
+#from segutils.segWaterBuilding import  SegModel,get_largest_contours,illBuildings
+from segutils.core.models.bisenet import BiSeNet_MultiOutput
+from collections import  Counter
+import matplotlib.pyplot as plt
+
+platform_query_url='http://47.96.182.154:9051/api/suanfa/getPlatformInfo'
+offlineFile='mintors/offlines/doneCodes.txt'
+
+def get_cls(array):
+    dcs = Counter(array)
+    keys = list(dcs.keys())
+    values = list(dcs.values())
+    max_index = values.index(max(values))
+    cls = int(keys[max_index])
+    return cls
+ 
+##9月3日之后，需要新增语义分割模型。
+##10月22日， source 改成文件输入
+##12月31日，支持从platform读取离线视频
+# 使用线程锁，防止线程死锁
+mutex = _thread.allocate_lock()
+# 存图片的队列
+frame_queue = queue.Queue()
+
+# 推流的地址，前端通过这个地址拉流，主机的IP，2019是ffmpeg在nginx中设置的端口号
+
+
+#camera_path='rtmp://58.200.131.2:1935/livetv/cctv1'
+camera_path='/data/WJ/data/THexit/vedio/XiYuDaiHe4.MP4'
+###lables colors  (BGR)#####
+rainbows=[
+           (0,0,255),(0,255,0),(255,0,0),(255,0,255),(255,255,0),(255,127,0),(255,0,127),
+           (127,255,0),(0,255,127),(0,127,255),(127,0,255),(255,127,255),(255,255,127),
+           (127,255,255),(0,255,255),(255,127,255),(127,255,255),
+           (0,127,0),(0,0,127),(0,255,255)
+         ]
+
+def detect(save_img=False):
+    rtmpUrl = "rtmp://127.0.0.1:1935/live/test"
+    OutVideoW,OutVideoH,OutVideoFps=int(opt.OutVideoW),int(opt.OutVideoH),int(opt.OutVideoFps)
+    command=['ffmpeg',
+                '-y',
+                #'-re',' ', 
+                '-f', 'rawvideo',
+                '-vcodec','rawvideo',
+                '-pix_fmt', 'bgr24',
+                '-s', "{}x{}".format(OutVideoW,OutVideoH),# 图片分辨率
+                #'-vcodec','libx264',
+                #'-b','2500k',
+                '-r', str(OutVideoFps),# 视频帧率
+                '-i', '-',
+                '-c:v', 'libx264',
+                '-pix_fmt', 'yuv420p',
+                #'-preset', 'ultrafast',
+                '-f', 'flv',
+                rtmpUrl]
+                
+
+
+    source, weights, view_img, save_txt, imgsz = opt.source, opt.weights, opt.view_img, opt.save_txt, opt.img_size
+    #save_img = not opt.nosave and not source.endswith('.txt')  # save inference images
+    save_img = not opt.nosave 
+    webcam = source.isnumeric() or source.endswith('.txt') or source.lower().startswith(
+        ('rtsp://', 'rtmp://', 'http://', 'https://'))
+    sourceTxt=source
+    if source.endswith('.txt'):
+        #source_list,port_list,streamName_list = get_websource(source)
+        source_infos = get_websource_fromTxt(source)
+    else:
+        #source_list,port_list,streamName_list = [source],[1935],['demo']
+        source_infos = [{'url':source,'port':1935,'name':'demo'  }]
+    # Directories
+    save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
+    (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+    # Initialize
+    set_logging()
+    device = select_device(opt.device)
+    half = device.type != 'cpu'  # half precision only supported on CUDA
+    # Load model
+    model = attempt_load(weights, map_location=device)  # load FP32 model
+    stride = int(model.stride.max())  # model stride
+    imgsz = check_img_size(imgsz, s=stride)  # check img_size
+    #print('###'*20,imgsz,stride)
+    
+    ##加载分割模型###
+    seg_nclass = 2
+    weights = 'weights/segmentation/BiSeNet/checkpoint.pth'
+    segmodel = SegModel(nclass=seg_nclass,weights=weights,device=device)
+    
+    '''nclass = [2,2]
+    Segmodel =  BiSeNet_MultiOutput(nclass)
+    weights='weights/segmentation/WaterBuilding.pth'
+    segmodel = SegModel(model=Segmodel,nclass=nclass,weights=weights,device='cuda:0',multiOutput=True)'''
+
+
+    
+    if half:
+        model.half()  # to FP16
+    # Second-stage classifier
+    classify = False
+    if classify:
+        modelc = load_classifier(name='resnet101', n=2)  # initialize
+        modelc.load_state_dict(torch.load('weights/resnet101.pt', map_location=device)['model']).to(device).eval()
+    if webcam:
+        # create file pointer
+        fp_out=open('mintors/%s.txt'%(time.strftime("Start-%Y-%m-%d-%H-%M-%S", time.localtime())) ,'w')
+    # Set Dataloader
+    vid_path, vid_writer = None, None
+    stream_id = 0
+    platurlToJsonfile(platform_query_url)    
+    while True:
+        #for isource in range(len(source_list)):
+        for isource in range(len(source_infos)):    
+            #source , port ,streamName = source_list[isource],port_list[isource],streamName_list[isource]
+            source , port ,streamName = source_infos[isource]['url'],source_infos[isource]['port'],source_infos[isource]['name']
+            print('########## detect.py line129 souce informations:',isource, source , port ,streamName,webcam  )
+            Push_Flag = False       
+            #for wang in ['test']:            
+            try:
+                if webcam:
+                    #view_img = check_imshow()
+                    cudnn.benchmark = True  # set True to speed up constant image size inference
+                    print('#########Using web cam#################')
+                    dataset = LoadStreams(source, img_size=imgsz, stride=stride)
+                        
+                    # Get names and colors,fp_log,fp_out都是日志文件
+                    fp_log=open('mintors/detection/stream_%s_%d-%s.txt'%(streamName,stream_id,time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())) ,'w')           
+                    fp_out.write(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())+ '  rtmp stream-%s-%d  starts  \n'%(streamName,stream_id)    )
+                    fp_out.flush()
+                    problem_image = [[],[],[],[],[]];
+                else:
+                    dataset = LoadImages(source, img_size=imgsz, stride=stride)
+
+   
+                ####
+                iimage_cnt = 0
+                names = model.module.names if hasattr(model, 'module') else model.names   
+                EngLish_label = True
+                if os.path.exists(opt.labelnames):
+                    with open(opt.labelnames,'r') as fp:
+                        namesjson=json.load(fp)
+                        names_fromfile=namesjson['labelnames']                         
+                    if len(names_fromfile) == len(names):
+                        names = names_fromfile
+                        EngLish_label = False
+                    else:
+                        print('******Warning 文件:%s读取的类别数目与模型中的数目不一致，使用模型的类别********'%(opt.labelnames))    
+
+                colors = rainbows
+                label_arraylist = get_label_arrays(names,colors,outfontsize=40)
+
+                # Run inference
+                if device.type != 'cpu':
+                    model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
+                t00 = time.time();
+
+
+                if webcam:
+                  while True:
+                      if len(command) > 0:
+                          rtmpUrl = "rtmp://127.0.0.1:%s/live/test"%(port)
+                          command[-1] = rtmpUrl
+                          # 管道配置，其中用到管道
+                          print(command)
+                          ppipe = sp.Popen(command, stdin=sp.PIPE)
+                          Push_Flag = True
+                          break
+                time00=time.time()
+
+                for path, img, im0s, vid_cap in dataset:
+                    t0= time_synchronized()
+                    img = torch.from_numpy(img).to(device)
+                    img = img.half() if half else img.float()  # uint8 to fp16/32
+                    img /= 255.0  # 0 - 255 to 0.0 - 1.0
+                    timeseg0 = time.time()  
+                    if segmodel:                    
+                        if webcam:
+                            seg_pred,segstr = segmodel.eval(im0s[0] )
+                            #seg_pred = segmodel.eval(im0s[0],outsize=None,smooth_kernel=20)
+                        else:
+                            seg_pred,segstr = segmodel.eval(im0s )
+                            #seg_pred = segmodel.eval(im0s[0],outsize=None,smooth_kernel=20)
+                      
+
+                    timeseg1 = time.time() 
+                    if img.ndimension() == 3:
+                        img = img.unsqueeze(0)
+            
+                    # Inference
+                    t1 = time_synchronized()
+                    
+                    pred = model(img, augment=opt.augment)[0]
+                    #print('###','line197:',img.shape,opt.augment,opt.conf_thres, opt.iou_thres, opt.classes, opt.agnostic_nms)
+                    # Apply NMS
+                    pred = non_max_suppression(pred, opt.conf_thres, opt.iou_thres, classes=opt.classes, agnostic=opt.agnostic_nms)
+                    t2 = time_synchronized()
+                    # Apply Classifier
+                    if classify:
+                        pred = apply_classifier(pred, modelc, img, im0s)
+ 
+                    # Process detections
+                    for i, det in enumerate(pred):  # detections per image      
+                        if webcam:  # batch_size >= 1
+                            p, s, im0, frame = path[i], '%g: ' % i, im0s[i].copy(), dataset.count
+                            im0_bak = im0.copy()
+                        else:
+                            p, s, im0, frame = path, '', im0s, getattr(dataset, 'frame', 0)   
+                        
+                        iimage_cnt += 1
+                        p = Path(p)  # to Path
+                        save_path = str(save_dir / p.name)  # img.jpg
+                     
+                        txt_path = str(save_dir / 'labels' / p.stem) + ('' if dataset.mode == 'image' else f'_{frame}')  # img.txt
+                        s += '%gx%g ' % img.shape[2:]  # print string
+                        gn = torch.tensor(im0.shape)[[1, 0, 1, 0]]  # normalization gain whwh
+
+                        
+                        if segmodel: 
+                            contours, hierarchy = cv2.findContours(seg_pred,cv2.RETR_TREE,cv2.CHAIN_APPROX_SIMPLE)                            
+                            water = seg_pred.copy();
+                            if len(contours)>0:
+                                max_id = get_largest_contours(contours)                
+                                water[:,:]=0                                                      
+                                cv2.fillPoly(water, [contours[max_id][:,0,:]], 1) 
+                                
+                                cv2.drawContours(im0,contours,max_id,(0,255,255),3)
+                                
+                            else:
+                                water[:,:] = 0
+                            #im0,water = illBuildings(seg_pred,im0)   
+
+                        if len(det):
+                            # Rescale boxes from img_size to im0 size
+                            det[:, :4] = scale_coords(img.shape[2:], det[:, :4], im0.shape).round()
+                            #check weather the box is inside of water area
+                            if segmodel: 
+                                det_c = det.clone(); det_c=det_c.cpu().numpy()                                      
+                                #area_factors = np.array([np.sum(water[int(x[1]):int(x[3]), int(x[0]):int(x[2])] )/((x[2]-x[0])*(x[3]-x[1])) for x in det]  )
+                                area_factors = np.array([np.sum(water[int(x[1]):int(x[3]), int(x[0]):int(x[2])] )/((x[2]-x[0])*(x[3]-x[1])) for x in det_c]  )                  
+                                #det = det[area_factors>0.1]                                           
+                                det = det[area_factors>0.03]
+                        ###联通要求，临时屏蔽掉水生植被
+                        '''if len(det):
+                            clss = det[:,5] 
+                            det = det[clss!=2]'''
+
+                        if len(det)>0: 
+                            # Print results
+                            for c in det[:, -1].unique():
+                                n = (det[:, -1] == c).sum()  # detections per class
+                                s += f"{n} {names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                            
+                            # Write results
+                            for *xyxy, conf, cls in reversed(det):
+                                if save_txt:  # Write to file
+                                    xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                                    line = (cls, *xywh, conf) if opt.save_conf else (cls, *xywh)  # label format
+                                    with open(txt_path + '.txt', 'a') as f:
+                                        f.write(('%g ' * len(line)).rstrip() % line + '\n')
+            
+                                if save_img or view_img:  # Add bbox to image
+                                    label = f'{names[int(cls)]} {conf:.2f}'
+                                    if EngLish_label:
+                                        plot_one_box(xyxy, im0, label=label, color=colors[int(cls)%20], line_thickness=3)
+                                    else:
+                                        #im0=plot_one_box_PIL(xyxy, im0, label=label, color=colors[int(cls)%20], line_thickness=3)   
+                                        im0 = draw_painting_joint(xyxy,im0,label_arraylist[int(cls)],score=conf,color=rainbows[int(cls)%20],line_thickness=None)             
+                    
+                            ###处理问题图片，每fpsample帧，上报一张图片。以平均得分最大的为最佳图片
+                            if webcam:
+                                problem_image[0].append( det[:,4].mean()); problem_image[1].append(det);
+                                problem_image[2].append(im0);problem_image[3].append(iimage_cnt);problem_image[4].append(im0_bak)
+                       
+                        if webcam & (iimage_cnt % opt.fpsample == 0) & (dataset.mode != 'image') &  (len(problem_image[0])>0):                        
+                            best_index = problem_image[0].index(max(problem_image[0]))  
+                            best_frame = problem_image[3][ best_index]   
+                            img_send = problem_image[2][ best_index]   
+                            img_bak = problem_image[4][ best_index]   
+                            dets = problem_image[1][best_index] 
+                            cls_max = get_cls(dets[:,5].cpu().detach().numpy())
+
+                            time_str = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime()) 
+                            uid=''.join(random.sample(string.ascii_letters + string.digits, 16))
+                            AIUrl='problems/images_tmp/%s_frame-%d-%d_type-%s_%s_s-%s_AI.jpg'%(time_str,best_frame,iimage_cnt,names[cls_max],uid,streamName)
+                            ORIUrl='problems/images_tmp/%s_frame-%d-%d_type-%s_%s_s-%s_OR.jpg'%(time_str,best_frame,iimage_cnt,names[cls_max],uid,streamName)
+                            cv2.imwrite(AIUrl,img_send); cv2.imwrite(ORIUrl,img_bak)
+                            outstr='%s save images to %s \n'%(time_str, AIUrl)
+                            fp_log.write(outstr )                    
+                            problem_image=[[],[],[],[],[]]
+                              
+                        # Print time (inference + NMS)
+                        t3 = time_synchronized()
+         
+                        # Save results (image with detections)
+                        if save_img:
+                            if dataset.mode == 'image':
+                                cv2.imwrite(save_path, im0)
+                            else:  # 'video' or 'stream'
+                                if vid_path != save_path:  # new video
+                                    vid_path = save_path
+                                    if isinstance(vid_writer, cv2.VideoWriter):
+                                        vid_writer.release()  # release previous video writer
+                                    if vid_cap:  # video
+                                        fps = vid_cap.get(cv2.CAP_PROP_FPS)
+                                        w = int(vid_cap.get(cv2.CAP_PROP_FRAME_WIDTH))
+                                        h = int(vid_cap.get(cv2.CAP_PROP_FRAME_HEIGHT))
+                                    else:  # stream
+                                        fps, w, h = 30, im0.shape[1], im0.shape[0]
+                                        save_path += '.mp4'
+                                    vid_writer = cv2.VideoWriter(save_path, cv2.VideoWriter_fourcc(*'mp4v'), fps, (w, h))
+                                im0 = cv2.resize(im0,(OutVideoW,OutVideoH))
+                  
+                                if dataset.mode == 'stream':
+                                    ppipe.stdin.write(im0.tostring())
+                  
+                            t4 = time_synchronized()
+                            #outstr='%s Done.read:%.1f ms, infer:%.1f ms, seginfer:%.1f ms,draw:%.1f ms,  save:%.1f ms   total:%.1f ms \n'%(s,(t1 - t0)*1000, (t2 - t1)*1000,(timeseg1-timeseg0)*1000, (t3 - t2)*1000,(t4-t3)*1000, (t4-t00)*1000)
+                            timestr=time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+                            outstr='%s ,%s,iframe:%d,,read:%.1f ms,copy:%.1f, infer:%.1f ms, detinfer:%.1f ms,draw:%.1f ms,  save:%.1f ms   total:%.1f ms \n'%(s,timestr,iimage_cnt,(t0 - t00)*1000,(timeseg0-t0)*1000, (t1 - timeseg0)*1000,(t2-t1)*1000, (t3 - t2)*1000,(t4-t3)*1000, (t4-t00)*1000)
+                            if webcam:   
+                                if len(det):                              
+                                    fp_log.write(outstr )
+                            else:
+                                print(outstr)
+                                print(segstr)
+                            sys.stdout.flush()
+                            
+                            t00=t4
+                
+            
+                if save_txt or save_img:
+                    s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+                    print(f"Results saved to {save_dir}{s}")
+                
+                print(f'Done. ({time.time() - t0:.3f}s)')
+                if not webcam:
+                    break;
+            
+            except Exception as e:
+                print('#######reading souce:%s ,error    :%s:'%(source,e  ))
+                if Push_Flag and webcam: 
+                    ####source end 推流or视频结束 ###
+                    ppipe.kill()
+                    
+                    fp_out.write(time.strftime("%Y-%m-%d %H:%M:%S", time.localtime()) +'  rtmp stream-%s-%d  ends \n'%(streamName,stream_id)  );fp_out.flush()
+                    stream_id += 1
+                    time_str = time.strftime("%Y-%m-%d-%H-%M-%S", time.localtime())
+                    if 'off' in streamName:##只有离线视频时，才会写结束文件。
+                        EndUrl='problems/images_tmp/%s_frame-9999-9999_type-结束_9999999999999999_s-%s_AI.jpg'%(time_str,streamName)
+                        img_end=np.zeros((100,100),dtype=np.uint8);cv2.imwrite(EndUrl,img_end)
+                        EndUrl='problems/images_tmp/%s_frame-9999-9999_type-结束_9999999999999999_s-%s_OR.jpg'%(time_str,streamName)
+                        cv2.imwrite(EndUrl,img_end)
+                        time_str = time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())
+                        with open( 'mintors/offlines/doneCodes.txt','a+' ) as fp:
+                            fp.write('%s %s\n'%(time_str,streamName  ))
+
+                        #source_infos=update_websource_offAndLive(platform_query_url,sourceTxt,offlineFile)
+                    fp_log.close()
+                if webcam:    
+                    fp_out.write( time.strftime("%Y-%m-%d %H:%M:%S", time.localtime())+'  GPU server sleep 10s \n'   )    ;fp_out.flush()      
+                time.sleep(10)  
+
+                if not webcam:
+                    break;  
+                   
+        ###update source (online or offline)
+        source_infos=update_websource_offAndLive(platform_query_url,sourceTxt,offlineFile)
+        if len(source_infos)==0:
+            print('######NO valid source sleep 10s#####')
+            time.sleep(10)
+    if webcam:               
+        fp_out.close()       
+
+    
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
+    parser.add_argument('--source', type=str, default='data/images', help='source')  # file/folder, 0 for webcam
+    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--conf-thres', type=float, default=0.25, help='object confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.45, help='IOU threshold for NMS')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--view-img', action='store_true', help='display results')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
+    parser.add_argument('--classes', nargs='+', type=int, help='filter by class: --class 0, or --class 0 2 3')
+    parser.add_argument('--agnostic-nms', action='store_true', help='class-agnostic NMS')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--update', action='store_true', help='update all models')
+    parser.add_argument('--project', default='runs/detect', help='save results to project/name')
+    parser.add_argument('--name', default='exp', help='save results to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--labelnames', type=str,default=None, help='labes nams')
+
+    parser.add_argument('--fpsample', type=int, default=240, help='fpsample')
+    parser.add_argument('--OutVideoW', type=int, default=1920, help='out video width size')
+    parser.add_argument('--OutVideoH', type=int, default=1080, help='out video height size')
+    parser.add_argument('--OutVideoFps', type=int, default=30, help='out video fps ')
+
+    opt = parser.parse_args()
+    print(opt)
+    check_requirements(exclude=('pycocotools', 'thop'))
+
+    with torch.no_grad():
+        if opt.update:  # update all models (to fix SourceChangeWarning)
+            for opt.weights in ['yolov5s.pt', 'yolov5m.pt', 'yolov5l.pt', 'yolov5x.pt']:
+                detect()
+                strip_optimizer(opt.weights)
+        else:
+            detect()

detect.sh

@@ -0,0 +1,24 @@
+
+#OutVideoW=3840 OutVideoH=2160 OutVideoFps=30 source=/home/thsw2/WJ/data/video3840
+#OutVideoW=1920 OutVideoH=1080 OutVideoFps=30 source=/home/thsw2/WJ/data/video1920
+#OutVideoW=3840 OutVideoH=2160 
+OutVideoW=1920 OutVideoH=1080
+OutVideoFps=30
+#source='rtmp://demoplay.yunhengzhizao.cn/live/test' #address2
+#source='rtmp://liveplay.yunhengzhizao.cn/live/demo' #address1
+#source='rtmp://liveplay.yunhengzhizao.cn/live/demo_HD5M' #address1_HD5M
+
+source=config/source.txt
+#source='/home/thsw2/WJ/data/THexit/val/images/'
+
+#model=runs/train/exp10/weights/best.pt
+#model=weights/best_5classes.pt  ###before 1228
+#model=weights/best_5classes_1228.pt
+model=weights/1230_last.pt
+labelnames=config/labelnames.json
+fpsample=720 confthres=0.4
+
+#python detect_zhuanbo.py  --weights ${model} --source ${source} --OutVideoW ${OutVideoW} --OutVideoH ${OutVideoH} --OutVideoFps ${OutVideoFps} --labelnames ${labelnames} --fpsample ${fpsample}  --conf-thres ${confthres}
+
+python  detect.py   --weights ${model} --source ${source} --OutVideoW ${OutVideoW} --OutVideoH ${OutVideoH} --OutVideoFps ${OutVideoFps} --labelnames ${labelnames} --fpsample ${fpsample}  --conf-thres ${confthres} &
+python Send_tranfer.py   &

hubconf.py

@@ -0,0 +1,139 @@
+"""YOLOv5 PyTorch Hub models https://pytorch.org/hub/ultralytics_yolov5/
+
+Usage:
+    import torch
+    model = torch.hub.load('ultralytics/yolov5', 'yolov5s')
+"""
+
+from pathlib import Path
+
+import torch
+
+from models.yolo import Model
+from utils.general import check_requirements, set_logging
+from utils.google_utils import attempt_download
+from utils.torch_utils import select_device
+
+dependencies = ['torch', 'yaml']
+check_requirements(Path(__file__).parent / 'requirements.txt', exclude=('pycocotools', 'thop'))
+set_logging()
+
+
+def create(name, pretrained, channels, classes, autoshape):
+    """Creates a specified YOLOv5 model
+
+    Arguments:
+        name (str): name of model, i.e. 'yolov5s'
+        pretrained (bool): load pretrained weights into the model
+        channels (int): number of input channels
+        classes (int): number of model classes
+
+    Returns:
+        pytorch model
+    """
+    try:
+        cfg = list((Path(__file__).parent / 'models').rglob(f'{name}.yaml'))[0]  # model.yaml path
+        model = Model(cfg, channels, classes)
+        if pretrained:
+            fname = f'{name}.pt'  # checkpoint filename
+            attempt_download(fname)  # download if not found locally
+            ckpt = torch.load(fname, map_location=torch.device('cpu'))  # load
+            msd = model.state_dict()  # model state_dict
+            csd = ckpt['model'].float().state_dict()  # checkpoint state_dict as FP32
+            csd = {k: v for k, v in csd.items() if msd[k].shape == v.shape}  # filter
+            model.load_state_dict(csd, strict=False)  # load
+            if len(ckpt['model'].names) == classes:
+                model.names = ckpt['model'].names  # set class names attribute
+            if autoshape:
+                model = model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
+        device = select_device('0' if torch.cuda.is_available() else 'cpu')  # default to GPU if available
+        return model.to(device)
+
+    except Exception as e:
+        help_url = 'https://github.com/ultralytics/yolov5/issues/36'
+        s = 'Cache maybe be out of date, try force_reload=True. See %s for help.' % help_url
+        raise Exception(s) from e
+
+
+def custom(path_or_model='path/to/model.pt', autoshape=True):
+    """YOLOv5-custom model https://github.com/ultralytics/yolov5
+
+    Arguments (3 options):
+        path_or_model (str): 'path/to/model.pt'
+        path_or_model (dict): torch.load('path/to/model.pt')
+        path_or_model (nn.Module): torch.load('path/to/model.pt')['model']
+
+    Returns:
+        pytorch model
+    """
+    model = torch.load(path_or_model) if isinstance(path_or_model, str) else path_or_model  # load checkpoint
+    if isinstance(model, dict):
+        model = model['ema' if model.get('ema') else 'model']  # load model
+
+    hub_model = Model(model.yaml).to(next(model.parameters()).device)  # create
+    hub_model.load_state_dict(model.float().state_dict())  # load state_dict
+    hub_model.names = model.names  # class names
+    if autoshape:
+        hub_model = hub_model.autoshape()  # for file/URI/PIL/cv2/np inputs and NMS
+    device = select_device('0' if torch.cuda.is_available() else 'cpu')  # default to GPU if available
+    return hub_model.to(device)
+
+
+def yolov5s(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-small model https://github.com/ultralytics/yolov5
+    return create('yolov5s', pretrained, channels, classes, autoshape)
+
+
+def yolov5m(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-medium model https://github.com/ultralytics/yolov5
+    return create('yolov5m', pretrained, channels, classes, autoshape)
+
+
+def yolov5l(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-large model https://github.com/ultralytics/yolov5
+    return create('yolov5l', pretrained, channels, classes, autoshape)
+
+
+def yolov5x(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
+    return create('yolov5x', pretrained, channels, classes, autoshape)
+
+
+def yolov5s6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-small model https://github.com/ultralytics/yolov5
+    return create('yolov5s6', pretrained, channels, classes, autoshape)
+
+
+def yolov5m6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-medium model https://github.com/ultralytics/yolov5
+    return create('yolov5m6', pretrained, channels, classes, autoshape)
+
+
+def yolov5l6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-large model https://github.com/ultralytics/yolov5
+    return create('yolov5l6', pretrained, channels, classes, autoshape)
+
+
+def yolov5x6(pretrained=True, channels=3, classes=80, autoshape=True):
+    # YOLOv5-xlarge model https://github.com/ultralytics/yolov5
+    return create('yolov5x6', pretrained, channels, classes, autoshape)
+
+
+if __name__ == '__main__':
+    model = create(name='yolov5s', pretrained=True, channels=3, classes=80, autoshape=True)  # pretrained example
+    # model = custom(path_or_model='path/to/model.pt')  # custom example
+
+    # Verify inference
+    import cv2
+    import numpy as np
+    from PIL import Image
+
+    imgs = ['data/images/zidane.jpg',  # filename
+            'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg',  # URI
+            cv2.imread('data/images/bus.jpg')[:, :, ::-1],  # OpenCV
+            Image.open('data/images/bus.jpg'),  # PIL
+            np.zeros((320, 640, 3))]  # numpy
+
+    results = model(imgs)  # batched inference
+    results.print()
+    results.save()

models/common.py

@@ -0,0 +1,386 @@
+# YOLOv5 common modules
+
+import math
+from copy import copy
+from pathlib import Path
+
+import numpy as np
+import pandas as pd
+import requests
+import torch
+import torch.nn as nn
+from PIL import Image
+from torch.cuda import amp
+
+from utils.datasets import letterbox
+from utils.general import non_max_suppression, make_divisible, scale_coords, increment_path, xyxy2xywh
+from utils.plots import color_list, plot_one_box
+from utils.torch_utils import time_synchronized
+
+
+def autopad(k, p=None):  # kernel, padding
+    # Pad to 'same'
+    if p is None:
+        p = k // 2 if isinstance(k, int) else [x // 2 for x in k]  # auto-pad
+    return p
+
+
+def DWConv(c1, c2, k=1, s=1, act=True):
+    # Depthwise convolution
+    return Conv(c1, c2, k, s, g=math.gcd(c1, c2), act=act)
+
+
+class Conv(nn.Module):
+    # Standard convolution
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Conv, self).__init__()
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g, bias=False)
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.SiLU() if act is True else (act if isinstance(act, nn.Module) else nn.Identity())
+
+    def forward(self, x):
+        return self.act(self.bn(self.conv(x)))
+
+    def fuseforward(self, x):
+        return self.act(self.conv(x))
+
+
+class TransformerLayer(nn.Module):
+    # Transformer layer https://arxiv.org/abs/2010.11929 (LayerNorm layers removed for better performance)
+    def __init__(self, c, num_heads):
+        super().__init__()
+        self.q = nn.Linear(c, c, bias=False)
+        self.k = nn.Linear(c, c, bias=False)
+        self.v = nn.Linear(c, c, bias=False)
+        self.ma = nn.MultiheadAttention(embed_dim=c, num_heads=num_heads)
+        self.fc1 = nn.Linear(c, c, bias=False)
+        self.fc2 = nn.Linear(c, c, bias=False)
+
+    def forward(self, x):
+        x = self.ma(self.q(x), self.k(x), self.v(x))[0] + x
+        x = self.fc2(self.fc1(x)) + x
+        return x
+
+
+class TransformerBlock(nn.Module):
+    # Vision Transformer https://arxiv.org/abs/2010.11929
+    def __init__(self, c1, c2, num_heads, num_layers):
+        super().__init__()
+        self.conv = None
+        if c1 != c2:
+            self.conv = Conv(c1, c2)
+        self.linear = nn.Linear(c2, c2)  # learnable position embedding
+        self.tr = nn.Sequential(*[TransformerLayer(c2, num_heads) for _ in range(num_layers)])
+        self.c2 = c2
+
+    def forward(self, x):
+        if self.conv is not None:
+            x = self.conv(x)
+        b, _, w, h = x.shape
+        p = x.flatten(2)
+        p = p.unsqueeze(0)
+        p = p.transpose(0, 3)
+        p = p.squeeze(3)
+        e = self.linear(p)
+        x = p + e
+
+        x = self.tr(x)
+        x = x.unsqueeze(3)
+        x = x.transpose(0, 3)
+        x = x.reshape(b, self.c2, w, h)
+        return x
+
+
+class Bottleneck(nn.Module):
+    # Standard bottleneck
+    def __init__(self, c1, c2, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, shortcut, groups, expansion
+        super(Bottleneck, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_, c2, 3, 1, g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class BottleneckCSP(nn.Module):
+    # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(BottleneckCSP, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = nn.Conv2d(c1, c_, 1, 1, bias=False)
+        self.cv3 = nn.Conv2d(c_, c_, 1, 1, bias=False)
+        self.cv4 = Conv(2 * c_, c2, 1, 1)
+        self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+
+    def forward(self, x):
+        y1 = self.cv3(self.m(self.cv1(x)))
+        y2 = self.cv2(x)
+        return self.cv4(self.act(self.bn(torch.cat((y1, y2), dim=1))))
+
+
+class C3(nn.Module):
+    # CSP Bottleneck with 3 convolutions
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):  # ch_in, ch_out, number, shortcut, groups, expansion
+        super(C3, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c1, c_, 1, 1)
+        self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
+        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+        # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
+
+    def forward(self, x):
+        return self.cv3(torch.cat((self.m(self.cv1(x)), self.cv2(x)), dim=1))
+
+
+class C3TR(C3):
+    # C3 module with TransformerBlock()
+    def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
+        super().__init__(c1, c2, n, shortcut, g, e)
+        c_ = int(c2 * e)
+        self.m = TransformerBlock(c_, c_, 4, n)
+
+
+class SPP(nn.Module):
+    # Spatial pyramid pooling layer used in YOLOv3-SPP
+    def __init__(self, c1, c2, k=(5, 9, 13)):
+        super(SPP, self).__init__()
+        c_ = c1 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, 1, 1)
+        self.cv2 = Conv(c_ * (len(k) + 1), c2, 1, 1)
+        self.m = nn.ModuleList([nn.MaxPool2d(kernel_size=x, stride=1, padding=x // 2) for x in k])
+
+    def forward(self, x):
+        x = self.cv1(x)
+        return self.cv2(torch.cat([x] + [m(x) for m in self.m], 1))
+
+
+class Focus(nn.Module):
+    # Focus wh information into c-space
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Focus, self).__init__()
+        self.conv = Conv(c1 * 4, c2, k, s, p, g, act)
+        # self.contract = Contract(gain=2)
+
+    def forward(self, x):  # x(b,c,w,h) -> y(b,4c,w/2,h/2)
+        return self.conv(torch.cat([x[..., ::2, ::2], x[..., 1::2, ::2], x[..., ::2, 1::2], x[..., 1::2, 1::2]], 1))
+        # return self.conv(self.contract(x))
+
+
+class Contract(nn.Module):
+    # Contract width-height into channels, i.e. x(1,64,80,80) to x(1,256,40,40)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        N, C, H, W = x.size()  # assert (H / s == 0) and (W / s == 0), 'Indivisible gain'
+        s = self.gain
+        x = x.view(N, C, H // s, s, W // s, s)  # x(1,64,40,2,40,2)
+        x = x.permute(0, 3, 5, 1, 2, 4).contiguous()  # x(1,2,2,64,40,40)
+        return x.view(N, C * s * s, H // s, W // s)  # x(1,256,40,40)
+
+
+class Expand(nn.Module):
+    # Expand channels into width-height, i.e. x(1,64,80,80) to x(1,16,160,160)
+    def __init__(self, gain=2):
+        super().__init__()
+        self.gain = gain
+
+    def forward(self, x):
+        N, C, H, W = x.size()  # assert C / s ** 2 == 0, 'Indivisible gain'
+        s = self.gain
+        x = x.view(N, s, s, C // s ** 2, H, W)  # x(1,2,2,16,80,80)
+        x = x.permute(0, 3, 4, 1, 5, 2).contiguous()  # x(1,16,80,2,80,2)
+        return x.view(N, C // s ** 2, H * s, W * s)  # x(1,16,160,160)
+
+
+class Concat(nn.Module):
+    # Concatenate a list of tensors along dimension
+    def __init__(self, dimension=1):
+        super(Concat, self).__init__()
+        self.d = dimension
+
+    def forward(self, x):
+        return torch.cat(x, self.d)
+
+
+class NMS(nn.Module):
+    # Non-Maximum Suppression (NMS) module
+    conf = 0.25  # confidence threshold
+    iou = 0.45  # IoU threshold
+    classes = None  # (optional list) filter by class
+
+    def __init__(self):
+        super(NMS, self).__init__()
+
+    def forward(self, x):
+        return non_max_suppression(x[0], conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)
+
+
+class autoShape(nn.Module):
+    # input-robust model wrapper for passing cv2/np/PIL/torch inputs. Includes preprocessing, inference and NMS
+    conf = 0.25  # NMS confidence threshold
+    iou = 0.45  # NMS IoU threshold
+    classes = None  # (optional list) filter by class
+
+    def __init__(self, model):
+        super(autoShape, self).__init__()
+        self.model = model.eval()
+
+    def autoshape(self):
+        print('autoShape already enabled, skipping... ')  # model already converted to model.autoshape()
+        return self
+
+    @torch.no_grad()
+    def forward(self, imgs, size=640, augment=False, profile=False):
+        # Inference from various sources. For height=640, width=1280, RGB images example inputs are:
+        #   filename:   imgs = 'data/images/zidane.jpg'
+        #   URI:             = 'https://github.com/ultralytics/yolov5/releases/download/v1.0/zidane.jpg'
+        #   OpenCV:          = cv2.imread('image.jpg')[:,:,::-1]  # HWC BGR to RGB x(640,1280,3)
+        #   PIL:             = Image.open('image.jpg')  # HWC x(640,1280,3)
+        #   numpy:           = np.zeros((640,1280,3))  # HWC
+        #   torch:           = torch.zeros(16,3,320,640)  # BCHW (scaled to size=640, 0-1 values)
+        #   multiple:        = [Image.open('image1.jpg'), Image.open('image2.jpg'), ...]  # list of images
+
+        t = [time_synchronized()]
+        p = next(self.model.parameters())  # for device and type
+        if isinstance(imgs, torch.Tensor):  # torch
+            with amp.autocast(enabled=p.device.type != 'cpu'):
+                return self.model(imgs.to(p.device).type_as(p), augment, profile)  # inference
+
+        # Pre-process
+        n, imgs = (len(imgs), imgs) if isinstance(imgs, list) else (1, [imgs])  # number of images, list of images
+        shape0, shape1, files = [], [], []  # image and inference shapes, filenames
+        for i, im in enumerate(imgs):
+            f = f'image{i}'  # filename
+            if isinstance(im, str):  # filename or uri
+                im, f = np.asarray(Image.open(requests.get(im, stream=True).raw if im.startswith('http') else im)), im
+            elif isinstance(im, Image.Image):  # PIL Image
+                im, f = np.asarray(im), getattr(im, 'filename', f) or f
+            files.append(Path(f).with_suffix('.jpg').name)
+            if im.shape[0] < 5:  # image in CHW
+                im = im.transpose((1, 2, 0))  # reverse dataloader .transpose(2, 0, 1)
+            im = im[:, :, :3] if im.ndim == 3 else np.tile(im[:, :, None], 3)  # enforce 3ch input
+            s = im.shape[:2]  # HWC
+            shape0.append(s)  # image shape
+            g = (size / max(s))  # gain
+            shape1.append([y * g for y in s])
+            imgs[i] = im if im.data.contiguous else np.ascontiguousarray(im)  # update
+        shape1 = [make_divisible(x, int(self.stride.max())) for x in np.stack(shape1, 0).max(0)]  # inference shape
+        x = [letterbox(im, new_shape=shape1, auto=False)[0] for im in imgs]  # pad
+        x = np.stack(x, 0) if n > 1 else x[0][None]  # stack
+        x = np.ascontiguousarray(x.transpose((0, 3, 1, 2)))  # BHWC to BCHW
+        x = torch.from_numpy(x).to(p.device).type_as(p) / 255.  # uint8 to fp16/32
+        t.append(time_synchronized())
+
+        with amp.autocast(enabled=p.device.type != 'cpu'):
+            # Inference
+            y = self.model(x, augment, profile)[0]  # forward
+            t.append(time_synchronized())
+
+            # Post-process
+            y = non_max_suppression(y, conf_thres=self.conf, iou_thres=self.iou, classes=self.classes)  # NMS
+            for i in range(n):
+                scale_coords(shape1, y[i][:, :4], shape0[i])
+
+            t.append(time_synchronized())
+            return Detections(imgs, y, files, t, self.names, x.shape)
+
+
+class Detections:
+    # detections class for YOLOv5 inference results
+    def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
+        super(Detections, self).__init__()
+        d = pred[0].device  # device
+        gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs]  # normalizations
+        self.imgs = imgs  # list of images as numpy arrays
+        self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
+        self.names = names  # class names
+        self.files = files  # image filenames
+        self.xyxy = pred  # xyxy pixels
+        self.xywh = [xyxy2xywh(x) for x in pred]  # xywh pixels
+        self.xyxyn = [x / g for x, g in zip(self.xyxy, gn)]  # xyxy normalized
+        self.xywhn = [x / g for x, g in zip(self.xywh, gn)]  # xywh normalized
+        self.n = len(self.pred)  # number of images (batch size)
+        self.t = tuple((times[i + 1] - times[i]) * 1000 / self.n for i in range(3))  # timestamps (ms)
+        self.s = shape  # inference BCHW shape
+
+    def display(self, pprint=False, show=False, save=False, render=False, save_dir=''):
+        colors = color_list()
+        for i, (img, pred) in enumerate(zip(self.imgs, self.pred)):
+            str = f'image {i + 1}/{len(self.pred)}: {img.shape[0]}x{img.shape[1]} '
+            if pred is not None:
+                for c in pred[:, -1].unique():
+                    n = (pred[:, -1] == c).sum()  # detections per class
+                    str += f"{n} {self.names[int(c)]}{'s' * (n > 1)}, "  # add to string
+                if show or save or render:
+                    for *box, conf, cls in pred:  # xyxy, confidence, class
+                        label = f'{self.names[int(cls)]} {conf:.2f}'
+                        plot_one_box(box, img, label=label, color=colors[int(cls) % 10])
+            img = Image.fromarray(img.astype(np.uint8)) if isinstance(img, np.ndarray) else img  # from np
+            if pprint:
+                print(str.rstrip(', '))
+            if show:
+                img.show(self.files[i])  # show
+            if save:
+                f = self.files[i]
+                img.save(Path(save_dir) / f)  # save
+                print(f"{'Saved' * (i == 0)} {f}", end=',' if i < self.n - 1 else f' to {save_dir}\n')
+            if render:
+                self.imgs[i] = np.asarray(img)
+
+    def print(self):
+        self.display(pprint=True)  # print results
+        print(f'Speed: %.1fms pre-process, %.1fms inference, %.1fms NMS per image at shape {tuple(self.s)}' % self.t)
+
+    def show(self):
+        self.display(show=True)  # show results
+
+    def save(self, save_dir='runs/hub/exp'):
+        save_dir = increment_path(save_dir, exist_ok=save_dir != 'runs/hub/exp')  # increment save_dir
+        Path(save_dir).mkdir(parents=True, exist_ok=True)
+        self.display(save=True, save_dir=save_dir)  # save results
+
+    def render(self):
+        self.display(render=True)  # render results
+        return self.imgs
+
+    def pandas(self):
+        # return detections as pandas DataFrames, i.e. print(results.pandas().xyxy[0])
+        new = copy(self)  # return copy
+        ca = 'xmin', 'ymin', 'xmax', 'ymax', 'confidence', 'class', 'name'  # xyxy columns
+        cb = 'xcenter', 'ycenter', 'width', 'height', 'confidence', 'class', 'name'  # xywh columns
+        for k, c in zip(['xyxy', 'xyxyn', 'xywh', 'xywhn'], [ca, ca, cb, cb]):
+            a = [[x[:5] + [int(x[5]), self.names[int(x[5])]] for x in x.tolist()] for x in getattr(self, k)]  # update
+            setattr(new, k, [pd.DataFrame(x, columns=c) for x in a])
+        return new
+
+    def tolist(self):
+        # return a list of Detections objects, i.e. 'for result in results.tolist():'
+        x = [Detections([self.imgs[i]], [self.pred[i]], self.names, self.s) for i in range(self.n)]
+        for d in x:
+            for k in ['imgs', 'pred', 'xyxy', 'xyxyn', 'xywh', 'xywhn']:
+                setattr(d, k, getattr(d, k)[0])  # pop out of list
+        return x
+
+    def __len__(self):
+        return self.n
+
+
+class Classify(nn.Module):
+    # Classification head, i.e. x(b,c1,20,20) to x(b,c2)
+    def __init__(self, c1, c2, k=1, s=1, p=None, g=1):  # ch_in, ch_out, kernel, stride, padding, groups
+        super(Classify, self).__init__()
+        self.aap = nn.AdaptiveAvgPool2d(1)  # to x(b,c1,1,1)
+        self.conv = nn.Conv2d(c1, c2, k, s, autopad(k, p), groups=g)  # to x(b,c2,1,1)
+        self.flat = nn.Flatten()
+
+    def forward(self, x):
+        z = torch.cat([self.aap(y) for y in (x if isinstance(x, list) else [x])], 1)  # cat if list
+        return self.flat(self.conv(z))  # flatten to x(b,c2)

models/experimental.py

@@ -0,0 +1,134 @@
+# YOLOv5 experimental modules
+
+import numpy as np
+import torch
+import torch.nn as nn
+
+from models.common import Conv, DWConv
+from utils.google_utils import attempt_download
+
+
+class CrossConv(nn.Module):
+    # Cross Convolution Downsample
+    def __init__(self, c1, c2, k=3, s=1, g=1, e=1.0, shortcut=False):
+        # ch_in, ch_out, kernel, stride, groups, expansion, shortcut
+        super(CrossConv, self).__init__()
+        c_ = int(c2 * e)  # hidden channels
+        self.cv1 = Conv(c1, c_, (1, k), (1, s))
+        self.cv2 = Conv(c_, c2, (k, 1), (s, 1), g=g)
+        self.add = shortcut and c1 == c2
+
+    def forward(self, x):
+        return x + self.cv2(self.cv1(x)) if self.add else self.cv2(self.cv1(x))
+
+
+class Sum(nn.Module):
+    # Weighted sum of 2 or more layers https://arxiv.org/abs/1911.09070
+    def __init__(self, n, weight=False):  # n: number of inputs
+        super(Sum, self).__init__()
+        self.weight = weight  # apply weights boolean
+        self.iter = range(n - 1)  # iter object
+        if weight:
+            self.w = nn.Parameter(-torch.arange(1., n) / 2, requires_grad=True)  # layer weights
+
+    def forward(self, x):
+        y = x[0]  # no weight
+        if self.weight:
+            w = torch.sigmoid(self.w) * 2
+            for i in self.iter:
+                y = y + x[i + 1] * w[i]
+        else:
+            for i in self.iter:
+                y = y + x[i + 1]
+        return y
+
+
+class GhostConv(nn.Module):
+    # Ghost Convolution https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=1, s=1, g=1, act=True):  # ch_in, ch_out, kernel, stride, groups
+        super(GhostConv, self).__init__()
+        c_ = c2 // 2  # hidden channels
+        self.cv1 = Conv(c1, c_, k, s, None, g, act)
+        self.cv2 = Conv(c_, c_, 5, 1, None, c_, act)
+
+    def forward(self, x):
+        y = self.cv1(x)
+        return torch.cat([y, self.cv2(y)], 1)
+
+
+class GhostBottleneck(nn.Module):
+    # Ghost Bottleneck https://github.com/huawei-noah/ghostnet
+    def __init__(self, c1, c2, k=3, s=1):  # ch_in, ch_out, kernel, stride
+        super(GhostBottleneck, self).__init__()
+        c_ = c2 // 2
+        self.conv = nn.Sequential(GhostConv(c1, c_, 1, 1),  # pw
+                                  DWConv(c_, c_, k, s, act=False) if s == 2 else nn.Identity(),  # dw
+                                  GhostConv(c_, c2, 1, 1, act=False))  # pw-linear
+        self.shortcut = nn.Sequential(DWConv(c1, c1, k, s, act=False),
+                                      Conv(c1, c2, 1, 1, act=False)) if s == 2 else nn.Identity()
+
+    def forward(self, x):
+        return self.conv(x) + self.shortcut(x)
+
+
+class MixConv2d(nn.Module):
+    # Mixed Depthwise Conv https://arxiv.org/abs/1907.09595
+    def __init__(self, c1, c2, k=(1, 3), s=1, equal_ch=True):
+        super(MixConv2d, self).__init__()
+        groups = len(k)
+        if equal_ch:  # equal c_ per group
+            i = torch.linspace(0, groups - 1E-6, c2).floor()  # c2 indices
+            c_ = [(i == g).sum() for g in range(groups)]  # intermediate channels
+        else:  # equal weight.numel() per group
+            b = [c2] + [0] * groups
+            a = np.eye(groups + 1, groups, k=-1)
+            a -= np.roll(a, 1, axis=1)
+            a *= np.array(k) ** 2
+            a[0] = 1
+            c_ = np.linalg.lstsq(a, b, rcond=None)[0].round()  # solve for equal weight indices, ax = b
+
+        self.m = nn.ModuleList([nn.Conv2d(c1, int(c_[g]), k[g], s, k[g] // 2, bias=False) for g in range(groups)])
+        self.bn = nn.BatchNorm2d(c2)
+        self.act = nn.LeakyReLU(0.1, inplace=True)
+
+    def forward(self, x):
+        return x + self.act(self.bn(torch.cat([m(x) for m in self.m], 1)))
+
+
+class Ensemble(nn.ModuleList):
+    # Ensemble of models
+    def __init__(self):
+        super(Ensemble, self).__init__()
+
+    def forward(self, x, augment=False):
+        y = []
+        for module in self:
+            y.append(module(x, augment)[0])
+        # y = torch.stack(y).max(0)[0]  # max ensemble
+        # y = torch.stack(y).mean(0)  # mean ensemble
+        y = torch.cat(y, 1)  # nms ensemble
+        return y, None  # inference, train output
+
+
+def attempt_load(weights, map_location=None):
+    # Loads an ensemble of models weights=[a,b,c] or a single model weights=[a] or weights=a
+    model = Ensemble()
+    for w in weights if isinstance(weights, list) else [weights]:
+        attempt_download(w)
+        ckpt = torch.load(w, map_location=map_location)  # load
+        model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().fuse().eval())  # FP32 model
+
+    # Compatibility updates
+    for m in model.modules():
+        if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU]:
+            m.inplace = True  # pytorch 1.7.0 compatibility
+        elif type(m) is Conv:
+            m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+
+    if len(model) == 1:
+        return model[-1]  # return model
+    else:
+        print('Ensemble created with %s\n' % weights)
+        for k in ['names', 'stride']:
+            setattr(model, k, getattr(model[-1], k))
+        return model  # return ensemble

models/export.py

@@ -0,0 +1,123 @@
+"""Exports a YOLOv5 *.pt model to ONNX and TorchScript formats
+
+Usage:
+    $ export PYTHONPATH="$PWD" && python models/export.py --weights yolov5s.pt --img 640 --batch 1
+"""
+
+import argparse
+import sys
+import time
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+
+import torch
+import torch.nn as nn
+
+import models
+from models.experimental import attempt_load
+from utils.activations import Hardswish, SiLU
+from utils.general import colorstr, check_img_size, check_requirements, set_logging
+from utils.torch_utils import select_device
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='./yolov5s.pt', help='weights path')
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='image size')  # height, width
+    parser.add_argument('--batch-size', type=int, default=1, help='batch size')
+    parser.add_argument('--grid', action='store_true', help='export Detect() layer grid')
+    parser.add_argument('--device', default='cpu', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--dynamic', action='store_true', help='dynamic ONNX axes')  # ONNX-only
+    parser.add_argument('--simplify', action='store_true', help='simplify ONNX model')  # ONNX-only
+    opt = parser.parse_args()
+    opt.img_size *= 2 if len(opt.img_size) == 1 else 1  # expand
+    print(opt)
+    set_logging()
+    t = time.time()
+
+    # Load PyTorch model
+    device = select_device(opt.device)
+    model = attempt_load(opt.weights, map_location=device)  # load FP32 model
+    labels = model.names
+
+    # Checks
+    gs = int(max(model.stride))  # grid size (max stride)
+    opt.img_size = [check_img_size(x, gs) for x in opt.img_size]  # verify img_size are gs-multiples
+
+    # Input
+    img = torch.zeros(opt.batch_size, 3, *opt.img_size).to(device)  # image size(1,3,320,192) iDetection
+
+    # Update model
+    for k, m in model.named_modules():
+        m._non_persistent_buffers_set = set()  # pytorch 1.6.0 compatibility
+        if isinstance(m, models.common.Conv):  # assign export-friendly activations
+            if isinstance(m.act, nn.Hardswish):
+                m.act = Hardswish()
+            elif isinstance(m.act, nn.SiLU):
+                m.act = SiLU()
+        # elif isinstance(m, models.yolo.Detect):
+        #     m.forward = m.forward_export  # assign forward (optional)
+    model.model[-1].export = not opt.grid  # set Detect() layer grid export
+    y = model(img)  # dry run
+
+    # TorchScript export -----------------------------------------------------------------------------------------------
+    prefix = colorstr('TorchScript:')
+    try:
+        print(f'\n{prefix} starting export with torch {torch.__version__}...')
+        f = opt.weights.replace('.pt', '.torchscript.pt')  # filename
+        ts = torch.jit.trace(model, img, strict=False)
+        ts.save(f)
+        print(f'{prefix} export success, saved as {f}')
+    except Exception as e:
+        print(f'{prefix} export failure: {e}')
+
+    # ONNX export ------------------------------------------------------------------------------------------------------
+    prefix = colorstr('ONNX:')
+    try:
+        import onnx
+
+        print(f'{prefix} starting export with onnx {onnx.__version__}...')
+        f = opt.weights.replace('.pt', '.onnx')  # filename
+        torch.onnx.export(model, img, f, verbose=False, opset_version=12, input_names=['images'],
+                          output_names=['classes', 'boxes'] if y is None else ['output'],
+                          dynamic_axes={'images': {0: 'batch', 2: 'height', 3: 'width'},  # size(1,3,640,640)
+                                        'output': {0: 'batch', 2: 'y', 3: 'x'}} if opt.dynamic else None)
+
+        # Checks
+        model_onnx = onnx.load(f)  # load onnx model
+        onnx.checker.check_model(model_onnx)  # check onnx model
+        # print(onnx.helper.printable_graph(model_onnx.graph))  # print
+
+        # Simplify
+        if opt.simplify:
+            try:
+                check_requirements(['onnx-simplifier'])
+                import onnxsim
+
+                print(f'{prefix} simplifying with onnx-simplifier {onnxsim.__version__}...')
+                model_onnx, check = onnxsim.simplify(model_onnx,
+                                                     dynamic_input_shape=opt.dynamic,
+                                                     input_shapes={'images': list(img.shape)} if opt.dynamic else None)
+                assert check, 'assert check failed'
+                onnx.save(model_onnx, f)
+            except Exception as e:
+                print(f'{prefix} simplifier failure: {e}')
+        print(f'{prefix} export success, saved as {f}')
+    except Exception as e:
+        print(f'{prefix} export failure: {e}')
+
+    # CoreML export ----------------------------------------------------------------------------------------------------
+    prefix = colorstr('CoreML:')
+    try:
+        import coremltools as ct
+
+        print(f'{prefix} starting export with coremltools {onnx.__version__}...')
+        # convert model from torchscript and apply pixel scaling as per detect.py
+        model = ct.convert(ts, inputs=[ct.ImageType(name='image', shape=img.shape, scale=1 / 255.0, bias=[0, 0, 0])])
+        f = opt.weights.replace('.pt', '.mlmodel')  # filename
+        model.save(f)
+        print(f'{prefix} export success, saved as {f}')
+    except Exception as e:
+        print(f'{prefix} export failure: {e}')
+
+    # Finish
+    print(f'\nExport complete ({time.time() - t:.2f}s). Visualize with https://github.com/lutzroeder/netron.')

models/hub/anchors.yaml

@@ -0,0 +1,58 @@
+# Default YOLOv5 anchors for COCO data
+
+
+# P5 -------------------------------------------------------------------------------------------------------------------
+# P5-640:
+anchors_p5_640:
+  - [ 10,13, 16,30, 33,23 ]  # P3/8
+  - [ 30,61, 62,45, 59,119 ]  # P4/16
+  - [ 116,90, 156,198, 373,326 ]  # P5/32
+
+
+# P6 -------------------------------------------------------------------------------------------------------------------
+# P6-640:  thr=0.25: 0.9964 BPR, 5.54 anchors past thr, n=12, img_size=640, metric_all=0.281/0.716-mean/best, past_thr=0.469-mean: 9,11,  21,19,  17,41,  43,32,  39,70,  86,64,  65,131,  134,130,  120,265,  282,180,  247,354,  512,387
+anchors_p6_640:
+  - [ 9,11,  21,19,  17,41 ]  # P3/8
+  - [ 43,32,  39,70,  86,64 ]  # P4/16
+  - [ 65,131,  134,130,  120,265 ]  # P5/32
+  - [ 282,180,  247,354,  512,387 ]  # P6/64
+
+# P6-1280:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1280, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 19,27,  44,40,  38,94,  96,68,  86,152,  180,137,  140,301,  303,264,  238,542,  436,615,  739,380,  925,792
+anchors_p6_1280:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# P6-1920:  thr=0.25: 0.9950 BPR, 5.55 anchors past thr, n=12, img_size=1920, metric_all=0.281/0.714-mean/best, past_thr=0.468-mean: 28,41,  67,59,  57,141,  144,103,  129,227,  270,205,  209,452,  455,396,  358,812,  653,922,  1109,570,  1387,1187
+anchors_p6_1920:
+  - [ 28,41,  67,59,  57,141 ]  # P3/8
+  - [ 144,103,  129,227,  270,205 ]  # P4/16
+  - [ 209,452,  455,396,  358,812 ]  # P5/32
+  - [ 653,922,  1109,570,  1387,1187 ]  # P6/64
+
+
+# P7 -------------------------------------------------------------------------------------------------------------------
+# P7-640:  thr=0.25: 0.9962 BPR, 6.76 anchors past thr, n=15, img_size=640, metric_all=0.275/0.733-mean/best, past_thr=0.466-mean: 11,11,  13,30,  29,20,  30,46,  61,38,  39,92,  78,80,  146,66,  79,163,  149,150,  321,143,  157,303,  257,402,  359,290,  524,372
+anchors_p7_640:
+  - [ 11,11,  13,30,  29,20 ]  # P3/8
+  - [ 30,46,  61,38,  39,92 ]  # P4/16
+  - [ 78,80,  146,66,  79,163 ]  # P5/32
+  - [ 149,150,  321,143,  157,303 ]  # P6/64
+  - [ 257,402,  359,290,  524,372 ]  # P7/128
+
+# P7-1280:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1280, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 19,22,  54,36,  32,77,  70,83,  138,71,  75,173,  165,159,  148,334,  375,151,  334,317,  251,626,  499,474,  750,326,  534,814,  1079,818
+anchors_p7_1280:
+  - [ 19,22,  54,36,  32,77 ]  # P3/8
+  - [ 70,83,  138,71,  75,173 ]  # P4/16
+  - [ 165,159,  148,334,  375,151 ]  # P5/32
+  - [ 334,317,  251,626,  499,474 ]  # P6/64
+  - [ 750,326,  534,814,  1079,818 ]  # P7/128
+
+# P7-1920:  thr=0.25: 0.9968 BPR, 6.71 anchors past thr, n=15, img_size=1920, metric_all=0.273/0.732-mean/best, past_thr=0.463-mean: 29,34,  81,55,  47,115,  105,124,  207,107,  113,259,  247,238,  222,500,  563,227,  501,476,  376,939,  749,711,  1126,489,  801,1222,  1618,1227
+anchors_p7_1920:
+  - [ 29,34,  81,55,  47,115 ]  # P3/8
+  - [ 105,124,  207,107,  113,259 ]  # P4/16
+  - [ 247,238,  222,500,  563,227 ]  # P5/32
+  - [ 501,476,  376,939,  749,711 ]  # P6/64
+  - [ 1126,489,  801,1222,  1618,1227 ]  # P7/128

models/hub/yolov3-spp.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3-SPP head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, SPP, [512, [5, 9, 13]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

models/hub/yolov3-tiny.yaml

@@ -0,0 +1,41 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,14, 23,27, 37,58]  # P4/16
+  - [81,82, 135,169, 344,319]  # P5/32
+
+# YOLOv3-tiny backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [16, 3, 1]],  # 0
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 1-P1/2
+   [-1, 1, Conv, [32, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 3-P2/4
+   [-1, 1, Conv, [64, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 5-P3/8
+   [-1, 1, Conv, [128, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 7-P4/16
+   [-1, 1, Conv, [256, 3, 1]],
+   [-1, 1, nn.MaxPool2d, [2, 2, 0]],  # 9-P5/32
+   [-1, 1, Conv, [512, 3, 1]],
+   [-1, 1, nn.ZeroPad2d, [[0, 1, 0, 1]]],  # 11
+   [-1, 1, nn.MaxPool2d, [2, 1, 0]],  # 12
+  ]
+
+# YOLOv3-tiny head
+head:
+  [[-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [256, 3, 1]],  # 19 (P4/16-medium)
+
+   [[19, 15], 1, Detect, [nc, anchors]],  # Detect(P4, P5)
+  ]

models/hub/yolov3.yaml

@@ -0,0 +1,51 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# darknet53 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Conv, [32, 3, 1]],  # 0
+   [-1, 1, Conv, [64, 3, 2]],  # 1-P1/2
+   [-1, 1, Bottleneck, [64]],
+   [-1, 1, Conv, [128, 3, 2]],  # 3-P2/4
+   [-1, 2, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 5-P3/8
+   [-1, 8, Bottleneck, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 7-P4/16
+   [-1, 8, Bottleneck, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 9-P5/32
+   [-1, 4, Bottleneck, [1024]],  # 10
+  ]
+
+# YOLOv3 head
+head:
+  [[-1, 1, Bottleneck, [1024, False]],
+   [-1, 1, Conv, [512, [1, 1]]],
+   [-1, 1, Conv, [1024, 3, 1]],
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, Conv, [1024, 3, 1]],  # 15 (P5/32-large)
+
+   [-2, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 8], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Bottleneck, [512, False]],
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, Conv, [512, 3, 1]],  # 22 (P4/16-medium)
+
+   [-2, 1, Conv, [128, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Bottleneck, [256, False]],
+   [-1, 2, Bottleneck, [256, False]],  # 27 (P3/8-small)
+
+   [[27, 22, 15], 1, Detect, [nc, anchors]],   # Detect(P3, P4, P5)
+  ]

models/hub/yolov5-fpn.yaml

@@ -0,0 +1,42 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, Bottleneck, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 6, BottleneckCSP, [1024]],  # 9
+  ]
+
+# YOLOv5 FPN head
+head:
+  [[-1, 3, BottleneckCSP, [1024, False]],  # 10 (P5/32-large)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 1, Conv, [512, 1, 1]],
+   [-1, 3, BottleneckCSP, [512, False]],  # 14 (P4/16-medium)
+
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 3, BottleneckCSP, [256, False]],  # 18 (P3/8-small)
+
+   [[18, 14, 10], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5-p2.yaml

@@ -0,0 +1,54 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors: 3
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Focus, [ 64, 3 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 9, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 7-P5/32
+    [ -1, 1, SPP, [ 1024, [ 5, 9, 13 ] ] ],
+    [ -1, 3, C3, [ 1024, False ] ],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [ [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 13
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 17 (P3/8-small)
+
+    [ -1, 1, Conv, [ 128, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 2 ], 1, Concat, [ 1 ] ],  # cat backbone P2
+    [ -1, 1, C3, [ 128, False ] ],  # 21 (P2/4-xsmall)
+
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],
+    [ [ -1, 18 ], 1, Concat, [ 1 ] ],  # cat head P3
+    [ -1, 3, C3, [ 256, False ] ],  # 24 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 14 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 27 (P4/16-medium)
+
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],
+    [ [ -1, 10 ], 1, Concat, [ 1 ] ],  # cat head P5
+    [ -1, 3, C3, [ 1024, False ] ],  # 30 (P5/32-large)
+
+    [ [ 24, 27, 30 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5-p6.yaml

@@ -0,0 +1,56 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors: 3
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Focus, [ 64, 3 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 9, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 768 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 9-P6/64
+    [ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
+    [ -1, 3, C3, [ 1024, False ] ],  # 11
+  ]
+
+# YOLOv5 head
+head:
+  [ [ -1, 1, Conv, [ 768, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 8 ], 1, Concat, [ 1 ] ],  # cat backbone P5
+    [ -1, 3, C3, [ 768, False ] ],  # 15
+
+    [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 19
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 23 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 20 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 26 (P4/16-medium)
+
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],
+    [ [ -1, 16 ], 1, Concat, [ 1 ] ],  # cat head P5
+    [ -1, 3, C3, [ 768, False ] ],  # 29 (P5/32-large)
+
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],
+    [ [ -1, 12 ], 1, Concat, [ 1 ] ],  # cat head P6
+    [ -1, 3, C3, [ 1024, False ] ],  # 32 (P5/64-xlarge)
+
+    [ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5-p7.yaml

@@ -0,0 +1,67 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors: 3
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Focus, [ 64, 3 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 9, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 768 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 9-P6/64
+    [ -1, 3, C3, [ 1024 ] ],
+    [ -1, 1, Conv, [ 1280, 3, 2 ] ],  # 11-P7/128
+    [ -1, 1, SPP, [ 1280, [ 3, 5 ] ] ],
+    [ -1, 3, C3, [ 1280, False ] ],  # 13
+  ]
+
+# YOLOv5 head
+head:
+  [ [ -1, 1, Conv, [ 1024, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 10 ], 1, Concat, [ 1 ] ],  # cat backbone P6
+    [ -1, 3, C3, [ 1024, False ] ],  # 17
+
+    [ -1, 1, Conv, [ 768, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 8 ], 1, Concat, [ 1 ] ],  # cat backbone P5
+    [ -1, 3, C3, [ 768, False ] ],  # 21
+
+    [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 25
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 29 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 26 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 32 (P4/16-medium)
+
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],
+    [ [ -1, 22 ], 1, Concat, [ 1 ] ],  # cat head P5
+    [ -1, 3, C3, [ 768, False ] ],  # 35 (P5/32-large)
+
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],
+    [ [ -1, 18 ], 1, Concat, [ 1 ] ],  # cat head P6
+    [ -1, 3, C3, [ 1024, False ] ],  # 38 (P6/64-xlarge)
+
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],
+    [ [ -1, 14 ], 1, Concat, [ 1 ] ],  # cat head P7
+    [ -1, 3, C3, [ 1280, False ] ],  # 41 (P7/128-xxlarge)
+
+    [ [ 29, 32, 35, 38, 41 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5, P6, P7)
+  ]

models/hub/yolov5-panet.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, BottleneckCSP, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, BottleneckCSP, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, BottleneckCSP, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, BottleneckCSP, [1024, False]],  # 9
+  ]
+
+# YOLOv5 PANet head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, BottleneckCSP, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, BottleneckCSP, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, BottleneckCSP, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5l6.yaml

@@ -0,0 +1,60 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Focus, [ 64, 3 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 9, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 768 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 9-P6/64
+    [ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
+    [ -1, 3, C3, [ 1024, False ] ],  # 11
+  ]
+
+# YOLOv5 head
+head:
+  [ [ -1, 1, Conv, [ 768, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 8 ], 1, Concat, [ 1 ] ],  # cat backbone P5
+    [ -1, 3, C3, [ 768, False ] ],  # 15
+
+    [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 19
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 23 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 20 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 26 (P4/16-medium)
+
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],
+    [ [ -1, 16 ], 1, Concat, [ 1 ] ],  # cat head P5
+    [ -1, 3, C3, [ 768, False ] ],  # 29 (P5/32-large)
+
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],
+    [ [ -1, 12 ], 1, Concat, [ 1 ] ],  # cat head P6
+    [ -1, 3, C3, [ 1024, False ] ],  # 32 (P6/64-xlarge)
+
+    [ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5m6.yaml

@@ -0,0 +1,60 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Focus, [ 64, 3 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 9, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 768 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 9-P6/64
+    [ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
+    [ -1, 3, C3, [ 1024, False ] ],  # 11
+  ]
+
+# YOLOv5 head
+head:
+  [ [ -1, 1, Conv, [ 768, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 8 ], 1, Concat, [ 1 ] ],  # cat backbone P5
+    [ -1, 3, C3, [ 768, False ] ],  # 15
+
+    [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 19
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 23 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 20 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 26 (P4/16-medium)
+
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],
+    [ [ -1, 16 ], 1, Concat, [ 1 ] ],  # cat head P5
+    [ -1, 3, C3, [ 768, False ] ],  # 29 (P5/32-large)
+
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],
+    [ [ -1, 12 ], 1, Concat, [ 1 ] ],  # cat head P6
+    [ -1, 3, C3, [ 1024, False ] ],  # 32 (P6/64-xlarge)
+
+    [ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5s-transformer.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3TR, [1024, False]],  # 9  <-------- C3TR() Transformer module
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/hub/yolov5s6.yaml

@@ -0,0 +1,60 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Focus, [ 64, 3 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 9, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 768 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 9-P6/64
+    [ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
+    [ -1, 3, C3, [ 1024, False ] ],  # 11
+  ]
+
+# YOLOv5 head
+head:
+  [ [ -1, 1, Conv, [ 768, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 8 ], 1, Concat, [ 1 ] ],  # cat backbone P5
+    [ -1, 3, C3, [ 768, False ] ],  # 15
+
+    [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 19
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 23 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 20 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 26 (P4/16-medium)
+
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],
+    [ [ -1, 16 ], 1, Concat, [ 1 ] ],  # cat head P5
+    [ -1, 3, C3, [ 768, False ] ],  # 29 (P5/32-large)
+
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],
+    [ [ -1, 12 ], 1, Concat, [ 1 ] ],  # cat head P6
+    [ -1, 3, C3, [ 1024, False ] ],  # 32 (P6/64-xlarge)
+
+    [ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5, P6)
+  ]

models/hub/yolov5x6.yaml

@@ -0,0 +1,60 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+
+# anchors
+anchors:
+  - [ 19,27,  44,40,  38,94 ]  # P3/8
+  - [ 96,68,  86,152,  180,137 ]  # P4/16
+  - [ 140,301,  303,264,  238,542 ]  # P5/32
+  - [ 436,615,  739,380,  925,792 ]  # P6/64
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [ [ -1, 1, Focus, [ 64, 3 ] ],  # 0-P1/2
+    [ -1, 1, Conv, [ 128, 3, 2 ] ],  # 1-P2/4
+    [ -1, 3, C3, [ 128 ] ],
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],  # 3-P3/8
+    [ -1, 9, C3, [ 256 ] ],
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],  # 5-P4/16
+    [ -1, 9, C3, [ 512 ] ],
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],  # 7-P5/32
+    [ -1, 3, C3, [ 768 ] ],
+    [ -1, 1, Conv, [ 1024, 3, 2 ] ],  # 9-P6/64
+    [ -1, 1, SPP, [ 1024, [ 3, 5, 7 ] ] ],
+    [ -1, 3, C3, [ 1024, False ] ],  # 11
+  ]
+
+# YOLOv5 head
+head:
+  [ [ -1, 1, Conv, [ 768, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 8 ], 1, Concat, [ 1 ] ],  # cat backbone P5
+    [ -1, 3, C3, [ 768, False ] ],  # 15
+
+    [ -1, 1, Conv, [ 512, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 6 ], 1, Concat, [ 1 ] ],  # cat backbone P4
+    [ -1, 3, C3, [ 512, False ] ],  # 19
+
+    [ -1, 1, Conv, [ 256, 1, 1 ] ],
+    [ -1, 1, nn.Upsample, [ None, 2, 'nearest' ] ],
+    [ [ -1, 4 ], 1, Concat, [ 1 ] ],  # cat backbone P3
+    [ -1, 3, C3, [ 256, False ] ],  # 23 (P3/8-small)
+
+    [ -1, 1, Conv, [ 256, 3, 2 ] ],
+    [ [ -1, 20 ], 1, Concat, [ 1 ] ],  # cat head P4
+    [ -1, 3, C3, [ 512, False ] ],  # 26 (P4/16-medium)
+
+    [ -1, 1, Conv, [ 512, 3, 2 ] ],
+    [ [ -1, 16 ], 1, Concat, [ 1 ] ],  # cat head P5
+    [ -1, 3, C3, [ 768, False ] ],  # 29 (P5/32-large)
+
+    [ -1, 1, Conv, [ 768, 3, 2 ] ],
+    [ [ -1, 12 ], 1, Concat, [ 1 ] ],  # cat head P6
+    [ -1, 3, C3, [ 1024, False ] ],  # 32 (P6/64-xlarge)
+
+    [ [ 23, 26, 29, 32 ], 1, Detect, [ nc, anchors ] ],  # Detect(P3, P4, P5, P6)
+  ]

models/yolo.py

@@ -0,0 +1,277 @@
+# YOLOv5 YOLO-specific modules
+
+import argparse
+import logging
+import sys
+from copy import deepcopy
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+logger = logging.getLogger(__name__)
+
+from models.common import *
+from models.experimental import *
+from utils.autoanchor import check_anchor_order
+from utils.general import make_divisible, check_file, set_logging
+from utils.torch_utils import time_synchronized, fuse_conv_and_bn, model_info, scale_img, initialize_weights, \
+    select_device, copy_attr
+
+try:
+    import thop  # for FLOPS computation
+except ImportError:
+    thop = None
+
+
+class Detect(nn.Module):
+    stride = None  # strides computed during build
+    export = False  # onnx export
+
+    def __init__(self, nc=80, anchors=(), ch=()):  # detection layer
+        super(Detect, self).__init__()
+        self.nc = nc  # number of classes
+        self.no = nc + 5  # number of outputs per anchor
+        self.nl = len(anchors)  # number of detection layers
+        self.na = len(anchors[0]) // 2  # number of anchors
+        self.grid = [torch.zeros(1)] * self.nl  # init grid
+        a = torch.tensor(anchors).float().view(self.nl, -1, 2)
+        self.register_buffer('anchors', a)  # shape(nl,na,2)
+        self.register_buffer('anchor_grid', a.clone().view(self.nl, 1, -1, 1, 1, 2))  # shape(nl,1,na,1,1,2)
+        self.m = nn.ModuleList(nn.Conv2d(x, self.no * self.na, 1) for x in ch)  # output conv
+
+    def forward(self, x):
+        # x = x.copy()  # for profiling
+        z = []  # inference output
+        self.training |= self.export
+        for i in range(self.nl):
+            x[i] = self.m[i](x[i])  # conv
+            bs, _, ny, nx = x[i].shape  # x(bs,255,20,20) to x(bs,3,20,20,85)
+            x[i] = x[i].view(bs, self.na, self.no, ny, nx).permute(0, 1, 3, 4, 2).contiguous()
+
+            if not self.training:  # inference
+                if self.grid[i].shape[2:4] != x[i].shape[2:4]:
+                    self.grid[i] = self._make_grid(nx, ny).to(x[i].device)
+
+                y = x[i].sigmoid()
+                y[..., 0:2] = (y[..., 0:2] * 2. - 0.5 + self.grid[i]) * self.stride[i]  # xy
+                y[..., 2:4] = (y[..., 2:4] * 2) ** 2 * self.anchor_grid[i]  # wh
+                z.append(y.view(bs, -1, self.no))
+
+        return x if self.training else (torch.cat(z, 1), x)
+
+    @staticmethod
+    def _make_grid(nx=20, ny=20):
+        yv, xv = torch.meshgrid([torch.arange(ny), torch.arange(nx)])
+        return torch.stack((xv, yv), 2).view((1, 1, ny, nx, 2)).float()
+
+
+class Model(nn.Module):
+    def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, anchors=None):  # model, input channels, number of classes
+        super(Model, self).__init__()
+        if isinstance(cfg, dict):
+            self.yaml = cfg  # model dict
+        else:  # is *.yaml
+            import yaml  # for torch hub
+            self.yaml_file = Path(cfg).name
+            with open(cfg) as f:
+                self.yaml = yaml.load(f, Loader=yaml.SafeLoader)  # model dict
+
+        # Define model
+        ch = self.yaml['ch'] = self.yaml.get('ch', ch)  # input channels
+        if nc and nc != self.yaml['nc']:
+            logger.info(f"Overriding model.yaml nc={self.yaml['nc']} with nc={nc}")
+            self.yaml['nc'] = nc  # override yaml value
+        if anchors:
+            logger.info(f'Overriding model.yaml anchors with anchors={anchors}')
+            self.yaml['anchors'] = round(anchors)  # override yaml value
+        self.model, self.save = parse_model(deepcopy(self.yaml), ch=[ch])  # model, savelist
+        self.names = [str(i) for i in range(self.yaml['nc'])]  # default names
+        # print([x.shape for x in self.forward(torch.zeros(1, ch, 64, 64))])
+
+        # Build strides, anchors
+        m = self.model[-1]  # Detect()
+        if isinstance(m, Detect):
+            s = 256  # 2x min stride
+            m.stride = torch.tensor([s / x.shape[-2] for x in self.forward(torch.zeros(1, ch, s, s))])  # forward
+            m.anchors /= m.stride.view(-1, 1, 1)
+            check_anchor_order(m)
+            self.stride = m.stride
+            self._initialize_biases()  # only run once
+            # print('Strides: %s' % m.stride.tolist())
+
+        # Init weights, biases
+        initialize_weights(self)
+        self.info()
+        logger.info('')
+
+    def forward(self, x, augment=False, profile=False):
+        if augment:
+            img_size = x.shape[-2:]  # height, width
+            s = [1, 0.83, 0.67]  # scales
+            f = [None, 3, None]  # flips (2-ud, 3-lr)
+            y = []  # outputs
+            for si, fi in zip(s, f):
+                xi = scale_img(x.flip(fi) if fi else x, si, gs=int(self.stride.max()))
+                yi = self.forward_once(xi)[0]  # forward
+                # cv2.imwrite(f'img_{si}.jpg', 255 * xi[0].cpu().numpy().transpose((1, 2, 0))[:, :, ::-1])  # save
+                yi[..., :4] /= si  # de-scale
+                if fi == 2:
+                    yi[..., 1] = img_size[0] - yi[..., 1]  # de-flip ud
+                elif fi == 3:
+                    yi[..., 0] = img_size[1] - yi[..., 0]  # de-flip lr
+                y.append(yi)
+            return torch.cat(y, 1), None  # augmented inference, train
+        else:
+            return self.forward_once(x, profile)  # single-scale inference, train
+
+    def forward_once(self, x, profile=False):
+        y, dt = [], []  # outputs
+        for m in self.model:
+            if m.f != -1:  # if not from previous layer
+                x = y[m.f] if isinstance(m.f, int) else [x if j == -1 else y[j] for j in m.f]  # from earlier layers
+
+            if profile:
+                o = thop.profile(m, inputs=(x,), verbose=False)[0] / 1E9 * 2 if thop else 0  # FLOPS
+                t = time_synchronized()
+                for _ in range(10):
+                    _ = m(x)
+                dt.append((time_synchronized() - t) * 100)
+                print('%10.1f%10.0f%10.1fms %-40s' % (o, m.np, dt[-1], m.type))
+
+            x = m(x)  # run
+            y.append(x if m.i in self.save else None)  # save output
+
+        if profile:
+            print('%.1fms total' % sum(dt))
+        return x
+
+    def _initialize_biases(self, cf=None):  # initialize biases into Detect(), cf is class frequency
+        # https://arxiv.org/abs/1708.02002 section 3.3
+        # cf = torch.bincount(torch.tensor(np.concatenate(dataset.labels, 0)[:, 0]).long(), minlength=nc) + 1.
+        m = self.model[-1]  # Detect() module
+        for mi, s in zip(m.m, m.stride):  # from
+            b = mi.bias.view(m.na, -1)  # conv.bias(255) to (3,85)
+            b.data[:, 4] += math.log(8 / (640 / s) ** 2)  # obj (8 objects per 640 image)
+            b.data[:, 5:] += math.log(0.6 / (m.nc - 0.99)) if cf is None else torch.log(cf / cf.sum())  # cls
+            mi.bias = torch.nn.Parameter(b.view(-1), requires_grad=True)
+
+    def _print_biases(self):
+        m = self.model[-1]  # Detect() module
+        for mi in m.m:  # from
+            b = mi.bias.detach().view(m.na, -1).T  # conv.bias(255) to (3,85)
+            print(('%6g Conv2d.bias:' + '%10.3g' * 6) % (mi.weight.shape[1], *b[:5].mean(1).tolist(), b[5:].mean()))
+
+    # def _print_weights(self):
+    #     for m in self.model.modules():
+    #         if type(m) is Bottleneck:
+    #             print('%10.3g' % (m.w.detach().sigmoid() * 2))  # shortcut weights
+
+    def fuse(self):  # fuse model Conv2d() + BatchNorm2d() layers
+        print('Fusing layers... ')
+        for m in self.model.modules():
+            if type(m) is Conv and hasattr(m, 'bn'):
+                m.conv = fuse_conv_and_bn(m.conv, m.bn)  # update conv
+                delattr(m, 'bn')  # remove batchnorm
+                m.forward = m.fuseforward  # update forward
+        self.info()
+        return self
+
+    def nms(self, mode=True):  # add or remove NMS module
+        present = type(self.model[-1]) is NMS  # last layer is NMS
+        if mode and not present:
+            print('Adding NMS... ')
+            m = NMS()  # module
+            m.f = -1  # from
+            m.i = self.model[-1].i + 1  # index
+            self.model.add_module(name='%s' % m.i, module=m)  # add
+            self.eval()
+        elif not mode and present:
+            print('Removing NMS... ')
+            self.model = self.model[:-1]  # remove
+        return self
+
+    def autoshape(self):  # add autoShape module
+        print('Adding autoShape... ')
+        m = autoShape(self)  # wrap model
+        copy_attr(m, self, include=('yaml', 'nc', 'hyp', 'names', 'stride'), exclude=())  # copy attributes
+        return m
+
+    def info(self, verbose=False, img_size=640):  # print model information
+        model_info(self, verbose, img_size)
+
+
+def parse_model(d, ch):  # model_dict, input_channels(3)
+    logger.info('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
+    anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
+    na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
+    no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
+
+    layers, save, c2 = [], [], ch[-1]  # layers, savelist, ch out
+    for i, (f, n, m, args) in enumerate(d['backbone'] + d['head']):  # from, number, module, args
+        m = eval(m) if isinstance(m, str) else m  # eval strings
+        for j, a in enumerate(args):
+            try:
+                args[j] = eval(a) if isinstance(a, str) else a  # eval strings
+            except:
+                pass
+
+        n = max(round(n * gd), 1) if n > 1 else n  # depth gain
+        if m in [Conv, GhostConv, Bottleneck, GhostBottleneck, SPP, DWConv, MixConv2d, Focus, CrossConv, BottleneckCSP,
+                 C3, C3TR]:
+            c1, c2 = ch[f], args[0]
+            if c2 != no:  # if not output
+                c2 = make_divisible(c2 * gw, 8)
+
+            args = [c1, c2, *args[1:]]
+            if m in [BottleneckCSP, C3, C3TR]:
+                args.insert(2, n)  # number of repeats
+                n = 1
+        elif m is nn.BatchNorm2d:
+            args = [ch[f]]
+        elif m is Concat:
+            c2 = sum([ch[x] for x in f])
+        elif m is Detect:
+            args.append([ch[x] for x in f])
+            if isinstance(args[1], int):  # number of anchors
+                args[1] = [list(range(args[1] * 2))] * len(f)
+        elif m is Contract:
+            c2 = ch[f] * args[0] ** 2
+        elif m is Expand:
+            c2 = ch[f] // args[0] ** 2
+        else:
+            c2 = ch[f]
+
+        m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)  # module
+        t = str(m)[8:-2].replace('__main__.', '')  # module type
+        np = sum([x.numel() for x in m_.parameters()])  # number params
+        m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
+        logger.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n, np, t, args))  # print
+        save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
+        layers.append(m_)
+        if i == 0:
+            ch = []
+        ch.append(c2)
+    return nn.Sequential(*layers), sorted(save)
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--cfg', type=str, default='yolov5s.yaml', help='model.yaml')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    opt = parser.parse_args()
+    opt.cfg = check_file(opt.cfg)  # check file
+    set_logging()
+    device = select_device(opt.device)
+
+    # Create model
+    model = Model(opt.cfg).to(device)
+    model.train()
+
+    # Profile
+    # img = torch.rand(8 if torch.cuda.is_available() else 1, 3, 640, 640).to(device)
+    # y = model(img, profile=True)
+
+    # Tensorboard
+    # from torch.utils.tensorboard import SummaryWriter
+    # tb_writer = SummaryWriter()
+    # print("Run 'tensorboard --logdir=models/runs' to view tensorboard at http://localhost:6006/")
+    # tb_writer.add_graph(model.model, img)  # add model to tensorboard
+    # tb_writer.add_image('test', img[0], dataformats='CWH')  # add model to tensorboard

models/yolov5l.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.0  # model depth multiple
+width_multiple: 1.0  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolov5m.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 0.67  # model depth multiple
+width_multiple: 0.75  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolov5s.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 0.33  # model depth multiple
+width_multiple: 0.50  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

models/yolov5x.yaml

@@ -0,0 +1,48 @@
+# parameters
+nc: 80  # number of classes
+depth_multiple: 1.33  # model depth multiple
+width_multiple: 1.25  # layer channel multiple
+
+# anchors
+anchors:
+  - [10,13, 16,30, 33,23]  # P3/8
+  - [30,61, 62,45, 59,119]  # P4/16
+  - [116,90, 156,198, 373,326]  # P5/32
+
+# YOLOv5 backbone
+backbone:
+  # [from, number, module, args]
+  [[-1, 1, Focus, [64, 3]],  # 0-P1/2
+   [-1, 1, Conv, [128, 3, 2]],  # 1-P2/4
+   [-1, 3, C3, [128]],
+   [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
+   [-1, 9, C3, [256]],
+   [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
+   [-1, 9, C3, [512]],
+   [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
+   [-1, 1, SPP, [1024, [5, 9, 13]]],
+   [-1, 3, C3, [1024, False]],  # 9
+  ]
+
+# YOLOv5 head
+head:
+  [[-1, 1, Conv, [512, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 6], 1, Concat, [1]],  # cat backbone P4
+   [-1, 3, C3, [512, False]],  # 13
+
+   [-1, 1, Conv, [256, 1, 1]],
+   [-1, 1, nn.Upsample, [None, 2, 'nearest']],
+   [[-1, 4], 1, Concat, [1]],  # cat backbone P3
+   [-1, 3, C3, [256, False]],  # 17 (P3/8-small)
+
+   [-1, 1, Conv, [256, 3, 2]],
+   [[-1, 14], 1, Concat, [1]],  # cat head P4
+   [-1, 3, C3, [512, False]],  # 20 (P4/16-medium)
+
+   [-1, 1, Conv, [512, 3, 2]],
+   [[-1, 10], 1, Concat, [1]],  # cat head P5
+   [-1, 3, C3, [1024, False]],  # 23 (P5/32-large)
+
+   [[17, 20, 23], 1, Detect, [nc, anchors]],  # Detect(P3, P4, P5)
+  ]

run.sh

@@ -0,0 +1,2 @@
+python  train.py --img 640 --batch 32 --epochs 100 --data  exitStone.yaml  --weights yolov5s.pt
+

runs/train/exp/hyp.yaml

@@ -0,0 +1,27 @@
+lr0: 0.01
+lrf: 0.2
+momentum: 0.937
+weight_decay: 0.0005
+warmup_epochs: 3.0
+warmup_momentum: 0.8
+warmup_bias_lr: 0.1
+box: 0.05
+cls: 0.5
+cls_pw: 1.0
+obj: 1.0
+obj_pw: 1.0
+iou_t: 0.2
+anchor_t: 4.0
+fl_gamma: 0.0
+hsv_h: 0.015
+hsv_s: 0.7
+hsv_v: 0.4
+degrees: 0.0
+translate: 0.1
+scale: 0.5
+shear: 0.0
+perspective: 0.0
+flipud: 0.0
+fliplr: 0.5
+mosaic: 1.0
+mixup: 0.0

runs/train/exp/opt.yaml

@@ -0,0 +1,40 @@
+weights: yolov5s.pt
+cfg: ''
+data: ./data/exitStone.yaml
+hyp: data/hyp.scratch.yaml
+epochs: 100
+batch_size: 32
+img_size:
+- 640
+- 640
+rect: false
+resume: false
+nosave: false
+notest: false
+noautoanchor: false
+evolve: false
+bucket: ''
+cache_images: false
+image_weights: false
+device: ''
+multi_scale: false
+single_cls: false
+adam: false
+sync_bn: false
+local_rank: -1
+workers: 8
+project: runs/train
+entity: null
+name: exp
+exist_ok: false
+quad: false
+linear_lr: false
+label_smoothing: 0.0
+upload_dataset: false
+bbox_interval: -1
+save_period: -1
+artifact_alias: latest
+world_size: 1
+global_rank: -1
+save_dir: runs/train/exp
+total_batch_size: 32

test.py

@@ -0,0 +1,345 @@
+import argparse
+import json
+import os
+from pathlib import Path
+from threading import Thread
+
+import numpy as np
+import torch
+import yaml
+from tqdm import tqdm
+
+from models.experimental import attempt_load
+from utils.datasets import create_dataloader
+from utils.general import coco80_to_coco91_class, check_dataset, check_file, check_img_size, check_requirements, \
+    box_iou, non_max_suppression, scale_coords, xyxy2xywh, xywh2xyxy, set_logging, increment_path, colorstr
+from utils.metrics import ap_per_class, ConfusionMatrix
+from utils.plots import plot_images, output_to_target, plot_study_txt
+from utils.torch_utils import select_device, time_synchronized
+
+
+def test(data,
+         weights=None,
+         batch_size=32,
+         imgsz=640,
+         conf_thres=0.001,
+         iou_thres=0.6,  # for NMS
+         save_json=False,
+         single_cls=False,
+         augment=False,
+         verbose=False,
+         model=None,
+         dataloader=None,
+         save_dir=Path(''),  # for saving images
+         save_txt=False,  # for auto-labelling
+         save_hybrid=False,  # for hybrid auto-labelling
+         save_conf=False,  # save auto-label confidences
+         plots=True,
+         wandb_logger=None,
+         compute_loss=None,
+         half_precision=True,
+         is_coco=False):
+    # Initialize/load model and set device
+    training = model is not None
+    if training:  # called by train.py
+        device = next(model.parameters()).device  # get model device
+
+    else:  # called directly
+        set_logging()
+        device = select_device(opt.device, batch_size=batch_size)
+
+        # Directories
+        save_dir = Path(increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok))  # increment run
+        (save_dir / 'labels' if save_txt else save_dir).mkdir(parents=True, exist_ok=True)  # make dir
+
+        # Load model
+        model = attempt_load(weights, map_location=device)  # load FP32 model
+        gs = max(int(model.stride.max()), 32)  # grid size (max stride)
+        imgsz = check_img_size(imgsz, s=gs)  # check img_size
+
+        # Multi-GPU disabled, incompatible with .half() https://github.com/ultralytics/yolov5/issues/99
+        # if device.type != 'cpu' and torch.cuda.device_count() > 1:
+        #     model = nn.DataParallel(model)
+
+    # Half
+    half = device.type != 'cpu' and half_precision  # half precision only supported on CUDA
+    if half:
+        model.half()
+
+    # Configure
+    model.eval()
+    if isinstance(data, str):
+        is_coco = data.endswith('coco.yaml')
+        with open(data) as f:
+            data = yaml.load(f, Loader=yaml.SafeLoader)
+    check_dataset(data)  # check
+    nc = 1 if single_cls else int(data['nc'])  # number of classes
+    iouv = torch.linspace(0.5, 0.95, 10).to(device)  # iou vector for mAP@0.5:0.95
+    niou = iouv.numel()
+
+    # Logging
+    log_imgs = 0
+    if wandb_logger and wandb_logger.wandb:
+        log_imgs = min(wandb_logger.log_imgs, 100)
+    # Dataloader
+    if not training:
+        if device.type != 'cpu':
+            model(torch.zeros(1, 3, imgsz, imgsz).to(device).type_as(next(model.parameters())))  # run once
+        task = opt.task if opt.task in ('train', 'val', 'test') else 'val'  # path to train/val/test images
+        dataloader = create_dataloader(data[task], imgsz, batch_size, gs, opt, pad=0.5, rect=True,
+                                       prefix=colorstr(f'{task}: '))[0]
+
+    seen = 0
+    confusion_matrix = ConfusionMatrix(nc=nc)
+    names = {k: v for k, v in enumerate(model.names if hasattr(model, 'names') else model.module.names)}
+    coco91class = coco80_to_coco91_class()
+    s = ('%20s' + '%12s' * 6) % ('Class', 'Images', 'Labels', 'P', 'R', 'mAP@.5', 'mAP@.5:.95')
+    p, r, f1, mp, mr, map50, map, t0, t1 = 0., 0., 0., 0., 0., 0., 0., 0., 0.
+    loss = torch.zeros(3, device=device)
+    jdict, stats, ap, ap_class, wandb_images = [], [], [], [], []
+    for batch_i, (img, targets, paths, shapes) in enumerate(tqdm(dataloader, desc=s)):
+        img = img.to(device, non_blocking=True)
+        img = img.half() if half else img.float()  # uint8 to fp16/32
+        img /= 255.0  # 0 - 255 to 0.0 - 1.0
+        targets = targets.to(device)
+        nb, _, height, width = img.shape  # batch size, channels, height, width
+
+        with torch.no_grad():
+            # Run model
+            t = time_synchronized()
+            out, train_out = model(img, augment=augment)  # inference and training outputs
+            t0 += time_synchronized() - t
+
+            # Compute loss
+            if compute_loss:
+                loss += compute_loss([x.float() for x in train_out], targets)[1][:3]  # box, obj, cls
+
+            # Run NMS
+            targets[:, 2:] *= torch.Tensor([width, height, width, height]).to(device)  # to pixels
+            lb = [targets[targets[:, 0] == i, 1:] for i in range(nb)] if save_hybrid else []  # for autolabelling
+            t = time_synchronized()
+            out = non_max_suppression(out, conf_thres=conf_thres, iou_thres=iou_thres, labels=lb, multi_label=True)
+            t1 += time_synchronized() - t
+
+        # Statistics per image
+        for si, pred in enumerate(out):
+            labels = targets[targets[:, 0] == si, 1:]
+            nl = len(labels)
+            tcls = labels[:, 0].tolist() if nl else []  # target class
+            path = Path(paths[si])
+            seen += 1
+
+            if len(pred) == 0:
+                if nl:
+                    stats.append((torch.zeros(0, niou, dtype=torch.bool), torch.Tensor(), torch.Tensor(), tcls))
+                continue
+
+            # Predictions
+            predn = pred.clone()
+            scale_coords(img[si].shape[1:], predn[:, :4], shapes[si][0], shapes[si][1])  # native-space pred
+
+            # Append to text file
+            if save_txt:
+                gn = torch.tensor(shapes[si][0])[[1, 0, 1, 0]]  # normalization gain whwh
+                for *xyxy, conf, cls in predn.tolist():
+                    xywh = (xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
+                    line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
+                    with open(save_dir / 'labels' / (path.stem + '.txt'), 'a') as f:
+                        f.write(('%g ' * len(line)).rstrip() % line + '\n')
+
+            # W&B logging - Media Panel Plots
+            if len(wandb_images) < log_imgs and wandb_logger.current_epoch > 0:  # Check for test operation
+                if wandb_logger.current_epoch % wandb_logger.bbox_interval == 0:
+                    box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
+                                 "class_id": int(cls),
+                                 "box_caption": "%s %.3f" % (names[cls], conf),
+                                 "scores": {"class_score": conf},
+                                 "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
+                    boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space
+                    wandb_images.append(wandb_logger.wandb.Image(img[si], boxes=boxes, caption=path.name))
+            wandb_logger.log_training_progress(predn, path, names) if wandb_logger and wandb_logger.wandb_run else None
+
+            # Append to pycocotools JSON dictionary
+            if save_json:
+                # [{"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}, ...
+                image_id = int(path.stem) if path.stem.isnumeric() else path.stem
+                box = xyxy2xywh(predn[:, :4])  # xywh
+                box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
+                for p, b in zip(pred.tolist(), box.tolist()):
+                    jdict.append({'image_id': image_id,
+                                  'category_id': coco91class[int(p[5])] if is_coco else int(p[5]),
+                                  'bbox': [round(x, 3) for x in b],
+                                  'score': round(p[4], 5)})
+
+            # Assign all predictions as incorrect
+            correct = torch.zeros(pred.shape[0], niou, dtype=torch.bool, device=device)
+            if nl:
+                detected = []  # target indices
+                tcls_tensor = labels[:, 0]
+
+                # target boxes
+                tbox = xywh2xyxy(labels[:, 1:5])
+                scale_coords(img[si].shape[1:], tbox, shapes[si][0], shapes[si][1])  # native-space labels
+                if plots:
+                    confusion_matrix.process_batch(predn, torch.cat((labels[:, 0:1], tbox), 1))
+
+                # Per target class
+                for cls in torch.unique(tcls_tensor):
+                    ti = (cls == tcls_tensor).nonzero(as_tuple=False).view(-1)  # prediction indices
+                    pi = (cls == pred[:, 5]).nonzero(as_tuple=False).view(-1)  # target indices
+
+                    # Search for detections
+                    if pi.shape[0]:
+                        # Prediction to target ious
+                        ious, i = box_iou(predn[pi, :4], tbox[ti]).max(1)  # best ious, indices
+
+                        # Append detections
+                        detected_set = set()
+                        for j in (ious > iouv[0]).nonzero(as_tuple=False):
+                            d = ti[i[j]]  # detected target
+                            if d.item() not in detected_set:
+                                detected_set.add(d.item())
+                                detected.append(d)
+                                correct[pi[j]] = ious[j] > iouv  # iou_thres is 1xn
+                                if len(detected) == nl:  # all targets already located in image
+                                    break
+
+            # Append statistics (correct, conf, pcls, tcls)
+            stats.append((correct.cpu(), pred[:, 4].cpu(), pred[:, 5].cpu(), tcls))
+
+        # Plot images
+        if plots and batch_i < 3:
+            f = save_dir / f'test_batch{batch_i}_labels.jpg'  # labels
+            Thread(target=plot_images, args=(img, targets, paths, f, names), daemon=True).start()
+            f = save_dir / f'test_batch{batch_i}_pred.jpg'  # predictions
+            Thread(target=plot_images, args=(img, output_to_target(out), paths, f, names), daemon=True).start()
+
+    # Compute statistics
+    stats = [np.concatenate(x, 0) for x in zip(*stats)]  # to numpy
+    if len(stats) and stats[0].any():
+        p, r, ap, f1, ap_class = ap_per_class(*stats, plot=plots, save_dir=save_dir, names=names)
+        ap50, ap = ap[:, 0], ap.mean(1)  # AP@0.5, AP@0.5:0.95
+        mp, mr, map50, map = p.mean(), r.mean(), ap50.mean(), ap.mean()
+        nt = np.bincount(stats[3].astype(np.int64), minlength=nc)  # number of targets per class
+    else:
+        nt = torch.zeros(1)
+
+    # Print results
+    pf = '%20s' + '%12i' * 2 + '%12.3g' * 4  # print format
+    print(pf % ('all', seen, nt.sum(), mp, mr, map50, map))
+
+    # Print results per class
+    if (verbose or (nc < 50 and not training)) and nc > 1 and len(stats):
+        for i, c in enumerate(ap_class):
+            print(pf % (names[c], seen, nt[c], p[i], r[i], ap50[i], ap[i]))
+
+    # Print speeds
+    t = tuple(x / seen * 1E3 for x in (t0, t1, t0 + t1)) + (imgsz, imgsz, batch_size)  # tuple
+    if not training:
+        print('Speed: %.1f/%.1f/%.1f ms inference/NMS/total per %gx%g image at batch-size %g' % t)
+
+    # Plots
+    if plots:
+        confusion_matrix.plot(save_dir=save_dir, names=list(names.values()))
+        if wandb_logger and wandb_logger.wandb:
+            val_batches = [wandb_logger.wandb.Image(str(f), caption=f.name) for f in sorted(save_dir.glob('test*.jpg'))]
+            wandb_logger.log({"Validation": val_batches})
+    if wandb_images:
+        wandb_logger.log({"Bounding Box Debugger/Images": wandb_images})
+
+    # Save JSON
+    if save_json and len(jdict):
+        w = Path(weights[0] if isinstance(weights, list) else weights).stem if weights is not None else ''  # weights
+        anno_json = '../coco/annotations/instances_val2017.json'  # annotations json
+        pred_json = str(save_dir / f"{w}_predictions.json")  # predictions json
+        print('\nEvaluating pycocotools mAP... saving %s...' % pred_json)
+        with open(pred_json, 'w') as f:
+            json.dump(jdict, f)
+
+        try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
+            from pycocotools.coco import COCO
+            from pycocotools.cocoeval import COCOeval
+
+            anno = COCO(anno_json)  # init annotations api
+            pred = anno.loadRes(pred_json)  # init predictions api
+            eval = COCOeval(anno, pred, 'bbox')
+            if is_coco:
+                eval.params.imgIds = [int(Path(x).stem) for x in dataloader.dataset.img_files]  # image IDs to evaluate
+            eval.evaluate()
+            eval.accumulate()
+            eval.summarize()
+            map, map50 = eval.stats[:2]  # update results (mAP@0.5:0.95, mAP@0.5)
+        except Exception as e:
+            print(f'pycocotools unable to run: {e}')
+
+    # Return results
+    model.float()  # for training
+    if not training:
+        s = f"\n{len(list(save_dir.glob('labels/*.txt')))} labels saved to {save_dir / 'labels'}" if save_txt else ''
+        print(f"Results saved to {save_dir}{s}")
+    maps = np.zeros(nc) + map
+    for i, c in enumerate(ap_class):
+        maps[c] = ap[i]
+    return (mp, mr, map50, map, *(loss.cpu() / len(dataloader)).tolist()), maps, t
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(prog='test.py')
+    parser.add_argument('--weights', nargs='+', type=str, default='yolov5s.pt', help='model.pt path(s)')
+    parser.add_argument('--data', type=str, default='data/coco128.yaml', help='*.data path')
+    parser.add_argument('--batch-size', type=int, default=32, help='size of each image batch')
+    parser.add_argument('--img-size', type=int, default=640, help='inference size (pixels)')
+    parser.add_argument('--conf-thres', type=float, default=0.001, help='object confidence threshold')
+    parser.add_argument('--iou-thres', type=float, default=0.6, help='IOU threshold for NMS')
+    parser.add_argument('--task', default='val', help='train, val, test, speed or study')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--single-cls', action='store_true', help='treat as single-class dataset')
+    parser.add_argument('--augment', action='store_true', help='augmented inference')
+    parser.add_argument('--verbose', action='store_true', help='report mAP by class')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
+    parser.add_argument('--save-hybrid', action='store_true', help='save label+prediction hybrid results to *.txt')
+    parser.add_argument('--save-conf', action='store_true', help='save confidences in --save-txt labels')
+    parser.add_argument('--save-json', action='store_true', help='save a cocoapi-compatible JSON results file')
+    parser.add_argument('--project', default='runs/test', help='save to project/name')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    opt = parser.parse_args()
+    opt.save_json |= opt.data.endswith('coco.yaml')
+    opt.data = check_file(opt.data)  # check file
+    print(opt)
+    check_requirements()
+
+    if opt.task in ('train', 'val', 'test'):  # run normally
+        test(opt.data,
+             opt.weights,
+             opt.batch_size,
+             opt.img_size,
+             opt.conf_thres,
+             opt.iou_thres,
+             opt.save_json,
+             opt.single_cls,
+             opt.augment,
+             opt.verbose,
+             save_txt=opt.save_txt | opt.save_hybrid,
+             save_hybrid=opt.save_hybrid,
+             save_conf=opt.save_conf,
+             )
+
+    elif opt.task == 'speed':  # speed benchmarks
+        for w in opt.weights:
+            test(opt.data, w, opt.batch_size, opt.img_size, 0.25, 0.45, save_json=False, plots=False)
+
+    elif opt.task == 'study':  # run over a range of settings and save/plot
+        # python test.py --task study --data coco.yaml --iou 0.7 --weights yolov5s.pt yolov5m.pt yolov5l.pt yolov5x.pt
+        x = list(range(256, 1536 + 128, 128))  # x axis (image sizes)
+        for w in opt.weights:
+            f = f'study_{Path(opt.data).stem}_{Path(w).stem}.txt'  # filename to save to
+            y = []  # y axis
+            for i in x:  # img-size
+                print(f'\nRunning {f} point {i}...')
+                r, _, t = test(opt.data, w, opt.batch_size, i, opt.conf_thres, opt.iou_thres, opt.save_json,
+                               plots=False)
+                y.append(r + t)  # results and times
+            np.savetxt(f, y, fmt='%10.4g')  # save
+        os.system('zip -r study.zip study_*.txt')
+        plot_study_txt(x=x)  # plot

train.py

@@ -0,0 +1,627 @@
+import argparse
+import logging
+import math
+import os
+import random
+import time
+from copy import deepcopy
+from pathlib import Path
+from threading import Thread
+
+import numpy as np
+import torch.distributed as dist
+import torch.nn as nn
+import torch.nn.functional as F
+import torch.optim as optim
+import torch.optim.lr_scheduler as lr_scheduler
+import torch.utils.data
+import yaml
+from torch.cuda import amp
+from torch.nn.parallel import DistributedDataParallel as DDP
+from torch.utils.tensorboard import SummaryWriter
+from tqdm import tqdm
+
+import test  # import test.py to get mAP after each epoch
+from models.experimental import attempt_load
+from models.yolo import Model
+from utils.autoanchor import check_anchors
+from utils.datasets import create_dataloader
+from utils.general import labels_to_class_weights, increment_path, labels_to_image_weights, init_seeds, \
+    fitness, strip_optimizer, get_latest_run, check_dataset, check_file, check_git_status, check_img_size, \
+    check_requirements, print_mutation, set_logging, one_cycle, colorstr
+from utils.google_utils import attempt_download
+from utils.loss import ComputeLoss
+from utils.plots import plot_images, plot_labels, plot_results, plot_evolution
+from utils.torch_utils import ModelEMA, select_device, intersect_dicts, torch_distributed_zero_first, is_parallel
+from utils.wandb_logging.wandb_utils import WandbLogger, check_wandb_resume
+
+logger = logging.getLogger(__name__)
+
+
+def train(hyp, opt, device, tb_writer=None):
+    logger.info(colorstr('hyperparameters: ') + ', '.join(f'{k}={v}' for k, v in hyp.items()))
+    save_dir, epochs, batch_size, total_batch_size, weights, rank = \
+        Path(opt.save_dir), opt.epochs, opt.batch_size, opt.total_batch_size, opt.weights, opt.global_rank
+
+    # Directories
+    wdir = save_dir / 'weights'
+    wdir.mkdir(parents=True, exist_ok=True)  # make dir
+    last = wdir / 'last.pt'
+    best = wdir / 'best.pt'
+    results_file = save_dir / 'results.txt'
+
+    # Save run settings
+    with open(save_dir / 'hyp.yaml', 'w') as f:
+        yaml.dump(hyp, f, sort_keys=False)
+    with open(save_dir / 'opt.yaml', 'w') as f:
+        yaml.dump(vars(opt), f, sort_keys=False)
+
+    # Configure
+    plots = not opt.evolve  # create plots
+    cuda = device.type != 'cpu'
+    init_seeds(2 + rank)
+    with open(opt.data) as f:
+        data_dict = yaml.load(f, Loader=yaml.SafeLoader)  # data dict
+    is_coco = opt.data.endswith('coco.yaml')
+
+    # Logging- Doing this before checking the dataset. Might update data_dict
+    loggers = {'wandb': None}  # loggers dict
+    if rank in [-1, 0]:
+        opt.hyp = hyp  # add hyperparameters
+        run_id = torch.load(weights).get('wandb_id') if weights.endswith('.pt') and os.path.isfile(weights) else None
+        wandb_logger = WandbLogger(opt, Path(opt.save_dir).stem, run_id, data_dict)
+        loggers['wandb'] = wandb_logger.wandb
+        data_dict = wandb_logger.data_dict
+        if wandb_logger.wandb:
+            weights, epochs, hyp = opt.weights, opt.epochs, opt.hyp  # WandbLogger might update weights, epochs if resuming
+
+    nc = 1 if opt.single_cls else int(data_dict['nc'])  # number of classes
+    names = ['item'] if opt.single_cls and len(data_dict['names']) != 1 else data_dict['names']  # class names
+    assert len(names) == nc, '%g names found for nc=%g dataset in %s' % (len(names), nc, opt.data)  # check
+
+    # Model
+    pretrained = weights.endswith('.pt')
+    if pretrained:
+        with torch_distributed_zero_first(rank):
+            attempt_download(weights)  # download if not found locally
+        ckpt = torch.load(weights, map_location=device)  # load checkpoint
+        model = Model(opt.cfg or ckpt['model'].yaml, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
+        exclude = ['anchor'] if (opt.cfg or hyp.get('anchors')) and not opt.resume else []  # exclude keys
+        state_dict = ckpt['model'].float().state_dict()  # to FP32
+        state_dict = intersect_dicts(state_dict, model.state_dict(), exclude=exclude)  # intersect
+        model.load_state_dict(state_dict, strict=False)  # load
+        logger.info('Transferred %g/%g items from %s' % (len(state_dict), len(model.state_dict()), weights))  # report
+    else:
+        model = Model(opt.cfg, ch=3, nc=nc, anchors=hyp.get('anchors')).to(device)  # create
+    with torch_distributed_zero_first(rank):
+        check_dataset(data_dict)  # check
+    train_path = data_dict['train']
+    test_path = data_dict['val']
+
+    # Freeze
+    freeze = []  # parameter names to freeze (full or partial)
+    for k, v in model.named_parameters():
+        v.requires_grad = True  # train all layers
+        if any(x in k for x in freeze):
+            print('freezing %s' % k)
+            v.requires_grad = False
+
+    # Optimizer
+    nbs = 64  # nominal batch size
+    accumulate = max(round(nbs / total_batch_size), 1)  # accumulate loss before optimizing
+    hyp['weight_decay'] *= total_batch_size * accumulate / nbs  # scale weight_decay
+    logger.info(f"Scaled weight_decay = {hyp['weight_decay']}")
+
+    pg0, pg1, pg2 = [], [], []  # optimizer parameter groups
+    for k, v in model.named_modules():
+        if hasattr(v, 'bias') and isinstance(v.bias, nn.Parameter):
+            pg2.append(v.bias)  # biases
+        if isinstance(v, nn.BatchNorm2d):
+            pg0.append(v.weight)  # no decay
+        elif hasattr(v, 'weight') and isinstance(v.weight, nn.Parameter):
+            pg1.append(v.weight)  # apply decay
+
+    if opt.adam:
+        optimizer = optim.Adam(pg0, lr=hyp['lr0'], betas=(hyp['momentum'], 0.999))  # adjust beta1 to momentum
+    else:
+        optimizer = optim.SGD(pg0, lr=hyp['lr0'], momentum=hyp['momentum'], nesterov=True)
+
+    optimizer.add_param_group({'params': pg1, 'weight_decay': hyp['weight_decay']})  # add pg1 with weight_decay
+    optimizer.add_param_group({'params': pg2})  # add pg2 (biases)
+    logger.info('Optimizer groups: %g .bias, %g conv.weight, %g other' % (len(pg2), len(pg1), len(pg0)))
+    del pg0, pg1, pg2
+
+    # Scheduler https://arxiv.org/pdf/1812.01187.pdf
+    # https://pytorch.org/docs/stable/_modules/torch/optim/lr_scheduler.html#OneCycleLR
+    if opt.linear_lr:
+        lf = lambda x: (1 - x / (epochs - 1)) * (1.0 - hyp['lrf']) + hyp['lrf']  # linear
+    else:
+        lf = one_cycle(1, hyp['lrf'], epochs)  # cosine 1->hyp['lrf']
+    scheduler = lr_scheduler.LambdaLR(optimizer, lr_lambda=lf)
+    # plot_lr_scheduler(optimizer, scheduler, epochs)
+
+    # EMA
+    ema = ModelEMA(model) if rank in [-1, 0] else None
+
+    # Resume
+    start_epoch, best_fitness = 0, 0.0
+    if pretrained:
+        # Optimizer
+        if ckpt['optimizer'] is not None:
+            optimizer.load_state_dict(ckpt['optimizer'])
+            best_fitness = ckpt['best_fitness']
+
+        # EMA
+        if ema and ckpt.get('ema'):
+            ema.ema.load_state_dict(ckpt['ema'].float().state_dict())
+            ema.updates = ckpt['updates']
+
+        # Results
+        if ckpt.get('training_results') is not None:
+            results_file.write_text(ckpt['training_results'])  # write results.txt
+
+        # Epochs
+        start_epoch = ckpt['epoch'] + 1
+        if opt.resume:
+            assert start_epoch > 0, '%s training to %g epochs is finished, nothing to resume.' % (weights, epochs)
+        if epochs < start_epoch:
+            logger.info('%s has been trained for %g epochs. Fine-tuning for %g additional epochs.' %
+                        (weights, ckpt['epoch'], epochs))
+            epochs += ckpt['epoch']  # finetune additional epochs
+
+        del ckpt, state_dict
+
+    # Image sizes
+    gs = max(int(model.stride.max()), 32)  # grid size (max stride)
+    nl = model.model[-1].nl  # number of detection layers (used for scaling hyp['obj'])
+    imgsz, imgsz_test = [check_img_size(x, gs) for x in opt.img_size]  # verify imgsz are gs-multiples
+
+    # DP mode
+    if cuda and rank == -1 and torch.cuda.device_count() > 1:
+        model = torch.nn.DataParallel(model)
+
+    # SyncBatchNorm
+    if opt.sync_bn and cuda and rank != -1:
+        model = torch.nn.SyncBatchNorm.convert_sync_batchnorm(model).to(device)
+        logger.info('Using SyncBatchNorm()')
+
+    # Trainloader
+    dataloader, dataset = create_dataloader(train_path, imgsz, batch_size, gs, opt,
+                                            hyp=hyp, augment=True, cache=opt.cache_images, rect=opt.rect, rank=rank,
+                                            world_size=opt.world_size, workers=opt.workers,
+                                            image_weights=opt.image_weights, quad=opt.quad, prefix=colorstr('train: '))
+    mlc = np.concatenate(dataset.labels, 0)[:, 0].max()  # max label class
+    nb = len(dataloader)  # number of batches
+    logger.info('#####bs:%d steps:%d ' % (batch_size, nb))
+    
+    assert mlc < nc, 'Label class %g exceeds nc=%g in %s. Possible class labels are 0-%g' % (mlc, nc, opt.data, nc - 1)
+
+    # Process 0
+    if rank in [-1, 0]:
+        testloader = create_dataloader(test_path, imgsz_test, batch_size * 2, gs, opt,  # testloader
+                                       hyp=hyp, cache=opt.cache_images and not opt.notest, rect=True, rank=-1,
+                                       world_size=opt.world_size, workers=opt.workers,
+                                       pad=0.5, prefix=colorstr('val: '))[0]
+
+        if not opt.resume:
+            labels = np.concatenate(dataset.labels, 0)
+            c = torch.tensor(labels[:, 0])  # classes
+            # cf = torch.bincount(c.long(), minlength=nc) + 1.  # frequency
+            # model._initialize_biases(cf.to(device))
+            if plots:
+                plot_labels(labels, names, save_dir, loggers)
+                if tb_writer:
+                    tb_writer.add_histogram('classes', c, 0)
+
+            # Anchors
+            if not opt.noautoanchor:
+                check_anchors(dataset, model=model, thr=hyp['anchor_t'], imgsz=imgsz)
+            model.half().float()  # pre-reduce anchor precision
+
+    # DDP mode
+    if cuda and rank != -1:
+        model = DDP(model, device_ids=[opt.local_rank], output_device=opt.local_rank,
+                    # nn.MultiheadAttention incompatibility with DDP https://github.com/pytorch/pytorch/issues/26698
+                    find_unused_parameters=any(isinstance(layer, nn.MultiheadAttention) for layer in model.modules()))
+
+    # Model parameters
+    hyp['box'] *= 3. / nl  # scale to layers
+    hyp['cls'] *= nc / 80. * 3. / nl  # scale to classes and layers
+    hyp['obj'] *= (imgsz / 640) ** 2 * 3. / nl  # scale to image size and layers
+    hyp['label_smoothing'] = opt.label_smoothing
+    model.nc = nc  # attach number of classes to model
+    model.hyp = hyp  # attach hyperparameters to model
+    model.gr = 1.0  # iou loss ratio (obj_loss = 1.0 or iou)
+    model.class_weights = labels_to_class_weights(dataset.labels, nc).to(device) * nc  # attach class weights
+    model.names = names
+
+    # Start training
+    t0 = time.time()
+    nw = max(round(hyp['warmup_epochs'] * nb), 1000)  # number of warmup iterations, max(3 epochs, 1k iterations)
+    # nw = min(nw, (epochs - start_epoch) / 2 * nb)  # limit warmup to < 1/2 of training
+    maps = np.zeros(nc)  # mAP per class
+    results = (0, 0, 0, 0, 0, 0, 0)  # P, R, mAP@.5, mAP@.5-.95, val_loss(box, obj, cls)
+    scheduler.last_epoch = start_epoch - 1  # do not move
+    scaler = amp.GradScaler(enabled=cuda)
+    compute_loss = ComputeLoss(model)  # init loss class
+    logger.info(f'Image sizes {imgsz} train, {imgsz_test} test\n'
+                f'Using {dataloader.num_workers} dataloader workers\n'
+                f'Logging results to {save_dir}\n'
+                f'Starting training for {epochs} epochs...')
+    for epoch in range(start_epoch, epochs):  # epoch ------------------------------------------------------------------
+        model.train()
+
+        # Update image weights (optional)
+        if opt.image_weights:
+            # Generate indices
+            if rank in [-1, 0]:
+                cw = model.class_weights.cpu().numpy() * (1 - maps) ** 2 / nc  # class weights
+                iw = labels_to_image_weights(dataset.labels, nc=nc, class_weights=cw)  # image weights
+                dataset.indices = random.choices(range(dataset.n), weights=iw, k=dataset.n)  # rand weighted idx
+            # Broadcast if DDP
+            if rank != -1:
+                indices = (torch.tensor(dataset.indices) if rank == 0 else torch.zeros(dataset.n)).int()
+                dist.broadcast(indices, 0)
+                if rank != 0:
+                    dataset.indices = indices.cpu().numpy()
+
+        # Update mosaic border
+        # b = int(random.uniform(0.25 * imgsz, 0.75 * imgsz + gs) // gs * gs)
+        # dataset.mosaic_border = [b - imgsz, -b]  # height, width borders
+
+        mloss = torch.zeros(4, device=device)  # mean losses
+        if rank != -1:
+            dataloader.sampler.set_epoch(epoch)
+        pbar = enumerate(dataloader)
+        logger.info(('\n' + '%10s' * 8) % ('Epoch', 'gpu_mem', 'box', 'obj', 'cls', 'total', 'labels', 'img_size'))
+        if rank in [-1, 0]:
+            pbar = tqdm(pbar, total=nb)  # progress bar
+        optimizer.zero_grad()
+        for i, (imgs, targets, paths, _) in pbar:  # batch -------------------------------------------------------------
+            ni = i + nb * epoch  # number integrated batches (since train start)
+            imgs = imgs.to(device, non_blocking=True).float() / 255.0  # uint8 to float32, 0-255 to 0.0-1.0
+
+            # Warmup
+            if ni <= nw:
+                xi = [0, nw]  # x interp
+                # model.gr = np.interp(ni, xi, [0.0, 1.0])  # iou loss ratio (obj_loss = 1.0 or iou)
+                accumulate = max(1, np.interp(ni, xi, [1, nbs / total_batch_size]).round())
+                for j, x in enumerate(optimizer.param_groups):
+                    # bias lr falls from 0.1 to lr0, all other lrs rise from 0.0 to lr0
+                    x['lr'] = np.interp(ni, xi, [hyp['warmup_bias_lr'] if j == 2 else 0.0, x['initial_lr'] * lf(epoch)])
+                    if 'momentum' in x:
+                        x['momentum'] = np.interp(ni, xi, [hyp['warmup_momentum'], hyp['momentum']])
+
+            # Multi-scale
+            if opt.multi_scale:
+                sz = random.randrange(imgsz * 0.5, imgsz * 1.5 + gs) // gs * gs  # size
+                sf = sz / max(imgs.shape[2:])  # scale factor
+                if sf != 1:
+                    ns = [math.ceil(x * sf / gs) * gs for x in imgs.shape[2:]]  # new shape (stretched to gs-multiple)
+                    imgs = F.interpolate(imgs, size=ns, mode='bilinear', align_corners=False)
+
+            # Forward
+            with amp.autocast(enabled=cuda):
+                pred = model(imgs)  # forward
+                loss, loss_items = compute_loss(pred, targets.to(device))  # loss scaled by batch_size
+                if rank != -1:
+                    loss *= opt.world_size  # gradient averaged between devices in DDP mode
+                if opt.quad:
+                    loss *= 4.
+
+            # Backward
+            scaler.scale(loss).backward()
+
+            # Optimize
+            if ni % accumulate == 0:
+                scaler.step(optimizer)  # optimizer.step
+                scaler.update()
+                optimizer.zero_grad()
+                if ema:
+                    ema.update(model)
+
+            # Print
+            if rank in [-1, 0]:
+                mloss = (mloss * i + loss_items) / (i + 1)  # update mean losses
+                mem = '%.3gG' % (torch.cuda.memory_reserved() / 1E9 if torch.cuda.is_available() else 0)  # (GB)
+                s = ('%10s' * 2 + '%10.4g' * 6) % (
+                    '%g/%g' % (epoch, epochs - 1), mem, *mloss, targets.shape[0], imgs.shape[-1])
+                pbar.set_description(s)
+
+                # Plot
+                if plots and ni < 3:
+                    f = save_dir / f'train_batch{ni}.jpg'  # filename
+                    Thread(target=plot_images, args=(imgs, targets, paths, f), daemon=True).start()
+                    # if tb_writer:
+                    #     tb_writer.add_image(f, result, dataformats='HWC', global_step=epoch)
+                    #     tb_writer.add_graph(torch.jit.trace(model, imgs, strict=False), [])  # add model graph
+                elif plots and ni == 10 and wandb_logger.wandb:
+                    wandb_logger.log({"Mosaics": [wandb_logger.wandb.Image(str(x), caption=x.name) for x in
+                                                  save_dir.glob('train*.jpg') if x.exists()]})
+
+            # end batch ------------------------------------------------------------------------------------------------
+        # end epoch ----------------------------------------------------------------------------------------------------
+
+        # Scheduler
+        lr = [x['lr'] for x in optimizer.param_groups]  # for tensorboard
+        scheduler.step()
+
+        # DDP process 0 or single-GPU
+        if rank in [-1, 0]:
+            # mAP
+            ema.update_attr(model, include=['yaml', 'nc', 'hyp', 'gr', 'names', 'stride', 'class_weights'])
+            final_epoch = epoch + 1 == epochs
+            if not opt.notest or final_epoch:  # Calculate mAP
+                wandb_logger.current_epoch = epoch + 1
+                results, maps, times = test.test(data_dict,
+                                                 batch_size=batch_size * 2,
+                                                 imgsz=imgsz_test,
+                                                 model=ema.ema,
+                                                 single_cls=opt.single_cls,
+                                                 dataloader=testloader,
+                                                 save_dir=save_dir,
+                                                 verbose=nc < 50 and final_epoch,
+                                                 plots=plots and final_epoch,
+                                                 wandb_logger=wandb_logger,
+                                                 compute_loss=compute_loss,
+                                                 is_coco=is_coco)
+
+            # Write
+            with open(results_file, 'a') as f:
+                f.write(s + '%10.4g' * 7 % results + '\n')  # append metrics, val_loss
+            if len(opt.name) and opt.bucket:
+                os.system('gsutil cp %s gs://%s/results/results%s.txt' % (results_file, opt.bucket, opt.name))
+
+            # Log
+            tags = ['train/box_loss', 'train/obj_loss', 'train/cls_loss',  # train loss
+                    'metrics/precision', 'metrics/recall', 'metrics/mAP_0.5', 'metrics/mAP_0.5:0.95',
+                    'val/box_loss', 'val/obj_loss', 'val/cls_loss',  # val loss
+                    'x/lr0', 'x/lr1', 'x/lr2']  # params
+            for x, tag in zip(list(mloss[:-1]) + list(results) + lr, tags):
+                if tb_writer:
+                    tb_writer.add_scalar(tag, x, epoch)  # tensorboard
+                if wandb_logger.wandb:
+                    wandb_logger.log({tag: x})  # W&B
+
+            # Update best mAP
+            fi = fitness(np.array(results).reshape(1, -1))  # weighted combination of [P, R, mAP@.5, mAP@.5-.95]
+            if fi > best_fitness:
+                best_fitness = fi
+            wandb_logger.end_epoch(best_result=best_fitness == fi)
+
+            # Save model
+            if (not opt.nosave) or (final_epoch and not opt.evolve):  # if save
+                ckpt = {'epoch': epoch,
+                        'best_fitness': best_fitness,
+                        'training_results': results_file.read_text(),
+                        'model': deepcopy(model.module if is_parallel(model) else model).half(),
+                        'ema': deepcopy(ema.ema).half(),
+                        'updates': ema.updates,
+                        'optimizer': optimizer.state_dict(),
+                        'wandb_id': wandb_logger.wandb_run.id if wandb_logger.wandb else None}
+
+                # Save last, best and delete
+                torch.save(ckpt, last)
+                if best_fitness == fi:
+                    torch.save(ckpt, best)
+                if wandb_logger.wandb:
+                    if ((epoch + 1) % opt.save_period == 0 and not final_epoch) and opt.save_period != -1:
+                        wandb_logger.log_model(
+                            last.parent, opt, epoch, fi, best_model=best_fitness == fi)
+                del ckpt
+
+        # end epoch ----------------------------------------------------------------------------------------------------
+    # end training
+    if rank in [-1, 0]:
+        # Plots
+        if plots:
+            plot_results(save_dir=save_dir)  # save as results.png
+            if wandb_logger.wandb:
+                files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
+                wandb_logger.log({"Results": [wandb_logger.wandb.Image(str(save_dir / f), caption=f) for f in files
+                                              if (save_dir / f).exists()]})
+        # Test best.pt
+        logger.info('%g epochs completed in %.3f hours.\n' % (epoch - start_epoch + 1, (time.time() - t0) / 3600))
+        if opt.data.endswith('coco.yaml') and nc == 80:  # if COCO
+            for m in (last, best) if best.exists() else (last):  # speed, mAP tests
+                results, _, _ = test.test(opt.data,
+                                          batch_size=batch_size * 2,
+                                          imgsz=imgsz_test,
+                                          conf_thres=0.001,
+                                          iou_thres=0.7,
+                                          model=attempt_load(m, device).half(),
+                                          single_cls=opt.single_cls,
+                                          dataloader=testloader,
+                                          save_dir=save_dir,
+                                          save_json=True,
+                                          plots=False,
+                                          is_coco=is_coco)
+
+        # Strip optimizers
+        final = best if best.exists() else last  # final model
+        for f in last, best:
+            if f.exists():
+                strip_optimizer(f)  # strip optimizers
+        if opt.bucket:
+            os.system(f'gsutil cp {final} gs://{opt.bucket}/weights')  # upload
+        if wandb_logger.wandb and not opt.evolve:  # Log the stripped model
+            wandb_logger.wandb.log_artifact(str(final), type='model',
+                                            name='run_' + wandb_logger.wandb_run.id + '_model',
+                                            aliases=['last', 'best', 'stripped'])
+        wandb_logger.finish_run()
+    else:
+        dist.destroy_process_group()
+    torch.cuda.empty_cache()
+    return results
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser()
+    parser.add_argument('--weights', type=str, default='yolov5s.pt', help='initial weights path')
+    parser.add_argument('--cfg', type=str, default='', help='model.yaml path')
+    parser.add_argument('--data', type=str, default='data/coco128.yaml', help='data.yaml path')
+    parser.add_argument('--hyp', type=str, default='data/hyp.scratch.yaml', help='hyperparameters path')
+    parser.add_argument('--epochs', type=int, default=300)
+    parser.add_argument('--batch-size', type=int, default=16, help='total batch size for all GPUs')
+    parser.add_argument('--img-size', nargs='+', type=int, default=[640, 640], help='[train, test] image sizes')
+    parser.add_argument('--rect', action='store_true', help='rectangular training')
+    parser.add_argument('--resume', nargs='?', const=True, default=False, help='resume most recent training')
+    parser.add_argument('--nosave', action='store_true', help='only save final checkpoint')
+    parser.add_argument('--notest', action='store_true', help='only test final epoch')
+    parser.add_argument('--noautoanchor', action='store_true', help='disable autoanchor check')
+    parser.add_argument('--evolve', action='store_true', help='evolve hyperparameters')
+    parser.add_argument('--bucket', type=str, default='', help='gsutil bucket')
+    parser.add_argument('--cache-images', action='store_true', help='cache images for faster training')
+    parser.add_argument('--image-weights', action='store_true', help='use weighted image selection for training')
+    parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
+    parser.add_argument('--multi-scale', action='store_true', help='vary img-size +/- 50%%')
+    parser.add_argument('--single-cls', action='store_true', help='train multi-class data as single-class')
+    parser.add_argument('--adam', action='store_true', help='use torch.optim.Adam() optimizer')
+    parser.add_argument('--sync-bn', action='store_true', help='use SyncBatchNorm, only available in DDP mode')
+    parser.add_argument('--local_rank', type=int, default=-1, help='DDP parameter, do not modify')
+    parser.add_argument('--workers', type=int, default=8, help='maximum number of dataloader workers')
+    parser.add_argument('--project', default='runs/train', help='save to project/name')
+    parser.add_argument('--entity', default=None, help='W&B entity')
+    parser.add_argument('--name', default='exp', help='save to project/name')
+    parser.add_argument('--exist-ok', action='store_true', help='existing project/name ok, do not increment')
+    parser.add_argument('--quad', action='store_true', help='quad dataloader')
+    parser.add_argument('--linear-lr', action='store_true', help='linear LR')
+    parser.add_argument('--label-smoothing', type=float, default=0.0, help='Label smoothing epsilon')
+    parser.add_argument('--upload_dataset', action='store_true', help='Upload dataset as W&B artifact table')
+    parser.add_argument('--bbox_interval', type=int, default=-1, help='Set bounding-box image logging interval for W&B')
+    parser.add_argument('--save_period', type=int, default=-1, help='Log model after every "save_period" epoch')
+    parser.add_argument('--artifact_alias', type=str, default="latest", help='version of dataset artifact to be used')
+    opt = parser.parse_args()
+
+    # Set DDP variables
+    opt.world_size = int(os.environ['WORLD_SIZE']) if 'WORLD_SIZE' in os.environ else 1
+    opt.global_rank = int(os.environ['RANK']) if 'RANK' in os.environ else -1
+    set_logging(opt.global_rank)
+    if opt.global_rank in [-1, 0]:
+        check_git_status()
+        check_requirements()
+
+    # Resume
+    wandb_run = check_wandb_resume(opt)
+    if opt.resume and not wandb_run:  # resume an interrupted run
+        ckpt = opt.resume if isinstance(opt.resume, str) else get_latest_run()  # specified or most recent path
+        assert os.path.isfile(ckpt), 'ERROR: --resume checkpoint does not exist'
+        apriori = opt.global_rank, opt.local_rank
+        with open(Path(ckpt).parent.parent / 'opt.yaml') as f:
+            opt = argparse.Namespace(**yaml.load(f, Loader=yaml.SafeLoader))  # replace
+        opt.cfg, opt.weights, opt.resume, opt.batch_size, opt.global_rank, opt.local_rank = '', ckpt, True, opt.total_batch_size, *apriori  # reinstate
+        logger.info('Resuming training from %s' % ckpt)
+    else:
+        # opt.hyp = opt.hyp or ('hyp.finetune.yaml' if opt.weights else 'hyp.scratch.yaml')
+        opt.data, opt.cfg, opt.hyp = check_file(opt.data), check_file(opt.cfg), check_file(opt.hyp)  # check files
+        assert len(opt.cfg) or len(opt.weights), 'either --cfg or --weights must be specified'
+        opt.img_size.extend([opt.img_size[-1]] * (2 - len(opt.img_size)))  # extend to 2 sizes (train, test)
+        opt.name = 'evolve' if opt.evolve else opt.name
+        opt.save_dir = increment_path(Path(opt.project) / opt.name, exist_ok=opt.exist_ok | opt.evolve)  # increment run
+
+    # DDP mode
+    opt.total_batch_size = opt.batch_size
+    device = select_device(opt.device, batch_size=opt.batch_size)
+    if opt.local_rank != -1:
+        assert torch.cuda.device_count() > opt.local_rank
+        torch.cuda.set_device(opt.local_rank)
+        device = torch.device('cuda', opt.local_rank)
+        dist.init_process_group(backend='nccl', init_method='env://')  # distributed backend
+        assert opt.batch_size % opt.world_size == 0, '--batch-size must be multiple of CUDA device count'
+        opt.batch_size = opt.total_batch_size // opt.world_size
+
+    # Hyperparameters
+    with open(opt.hyp) as f:
+        hyp = yaml.load(f, Loader=yaml.SafeLoader)  # load hyps
+
+    # Train
+    logger.info(opt)
+    if not opt.evolve:
+        tb_writer = None  # init loggers
+        if opt.global_rank in [-1, 0]:
+            prefix = colorstr('tensorboard: ')
+            logger.info(f"{prefix}Start with 'tensorboard --logdir {opt.project}', view at http://localhost:6006/")
+            tb_writer = SummaryWriter(opt.save_dir)  # Tensorboard
+        train(hyp, opt, device, tb_writer)
+
+    # Evolve hyperparameters (optional)
+    else:
+        # Hyperparameter evolution metadata (mutation scale 0-1, lower_limit, upper_limit)
+        meta = {'lr0': (1, 1e-5, 1e-1),  # initial learning rate (SGD=1E-2, Adam=1E-3)
+                'lrf': (1, 0.01, 1.0),  # final OneCycleLR learning rate (lr0 * lrf)
+                'momentum': (0.3, 0.6, 0.98),  # SGD momentum/Adam beta1
+                'weight_decay': (1, 0.0, 0.001),  # optimizer weight decay
+                'warmup_epochs': (1, 0.0, 5.0),  # warmup epochs (fractions ok)
+                'warmup_momentum': (1, 0.0, 0.95),  # warmup initial momentum
+                'warmup_bias_lr': (1, 0.0, 0.2),  # warmup initial bias lr
+                'box': (1, 0.02, 0.2),  # box loss gain
+                'cls': (1, 0.2, 4.0),  # cls loss gain
+                'cls_pw': (1, 0.5, 2.0),  # cls BCELoss positive_weight
+                'obj': (1, 0.2, 4.0),  # obj loss gain (scale with pixels)
+                'obj_pw': (1, 0.5, 2.0),  # obj BCELoss positive_weight
+                'iou_t': (0, 0.1, 0.7),  # IoU training threshold
+                'anchor_t': (1, 2.0, 8.0),  # anchor-multiple threshold
+                'anchors': (2, 2.0, 10.0),  # anchors per output grid (0 to ignore)
+                'fl_gamma': (0, 0.0, 2.0),  # focal loss gamma (efficientDet default gamma=1.5)
+                'hsv_h': (1, 0.0, 0.1),  # image HSV-Hue augmentation (fraction)
+                'hsv_s': (1, 0.0, 0.9),  # image HSV-Saturation augmentation (fraction)
+                'hsv_v': (1, 0.0, 0.9),  # image HSV-Value augmentation (fraction)
+                'degrees': (1, 0.0, 45.0),  # image rotation (+/- deg)
+                'translate': (1, 0.0, 0.9),  # image translation (+/- fraction)
+                'scale': (1, 0.0, 0.9),  # image scale (+/- gain)
+                'shear': (1, 0.0, 10.0),  # image shear (+/- deg)
+                'perspective': (0, 0.0, 0.001),  # image perspective (+/- fraction), range 0-0.001
+                'flipud': (1, 0.0, 1.0),  # image flip up-down (probability)
+                'fliplr': (0, 0.0, 1.0),  # image flip left-right (probability)
+                'mosaic': (1, 0.0, 1.0),  # image mixup (probability)
+                'mixup': (1, 0.0, 1.0)}  # image mixup (probability)
+
+        assert opt.local_rank == -1, 'DDP mode not implemented for --evolve'
+        opt.notest, opt.nosave = True, True  # only test/save final epoch
+        # ei = [isinstance(x, (int, float)) for x in hyp.values()]  # evolvable indices
+        yaml_file = Path(opt.save_dir) / 'hyp_evolved.yaml'  # save best result here
+        if opt.bucket:
+            os.system('gsutil cp gs://%s/evolve.txt .' % opt.bucket)  # download evolve.txt if exists
+
+        for _ in range(300):  # generations to evolve
+            if Path('evolve.txt').exists():  # if evolve.txt exists: select best hyps and mutate
+                # Select parent(s)
+                parent = 'single'  # parent selection method: 'single' or 'weighted'
+                x = np.loadtxt('evolve.txt', ndmin=2)
+                n = min(5, len(x))  # number of previous results to consider
+                x = x[np.argsort(-fitness(x))][:n]  # top n mutations
+                w = fitness(x) - fitness(x).min()  # weights
+                if parent == 'single' or len(x) == 1:
+                    # x = x[random.randint(0, n - 1)]  # random selection
+                    x = x[random.choices(range(n), weights=w)[0]]  # weighted selection
+                elif parent == 'weighted':
+                    x = (x * w.reshape(n, 1)).sum(0) / w.sum()  # weighted combination
+
+                # Mutate
+                mp, s = 0.8, 0.2  # mutation probability, sigma
+                npr = np.random
+                npr.seed(int(time.time()))
+                g = np.array([x[0] for x in meta.values()])  # gains 0-1
+                ng = len(meta)
+                v = np.ones(ng)
+                while all(v == 1):  # mutate until a change occurs (prevent duplicates)
+                    v = (g * (npr.random(ng) < mp) * npr.randn(ng) * npr.random() * s + 1).clip(0.3, 3.0)
+                for i, k in enumerate(hyp.keys()):  # plt.hist(v.ravel(), 300)
+                    hyp[k] = float(x[i + 7] * v[i])  # mutate
+
+            # Constrain to limits
+            for k, v in meta.items():
+                hyp[k] = max(hyp[k], v[1])  # lower limit
+                hyp[k] = min(hyp[k], v[2])  # upper limit
+                hyp[k] = round(hyp[k], 5)  # significant digits
+
+            # Train mutation
+            results = train(hyp.copy(), opt, device)
+
+            # Write mutation results
+            print_mutation(hyp.copy(), results, yaml_file, opt.bucket)
+
+        # Plot results
+        plot_evolution(yaml_file)
+        print(f'Hyperparameter evolution complete. Best results saved as: {yaml_file}\n'
+              f'Command to train a new model with these hyperparameters: $ python train.py --hyp {yaml_file}')

train.sh

@@ -0,0 +1 @@
+python  train.py --img 640 --batch 64 --epochs 100 --data exitPPS.yaml  --resume ../../cby/yolov5-master/runs/train/outlet-x11/weights/best.pt

utils/SendLog/platformQueryOfftask.json

@@ -0,0 +1 @@
+{"code": 0, "msg": "操作成功", "data": []}

utils/activations.py

@@ -0,0 +1,72 @@
+# Activation functions
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+# SiLU https://arxiv.org/pdf/1606.08415.pdf ----------------------------------------------------------------------------
+class SiLU(nn.Module):  # export-friendly version of nn.SiLU()
+    @staticmethod
+    def forward(x):
+        return x * torch.sigmoid(x)
+
+
+class Hardswish(nn.Module):  # export-friendly version of nn.Hardswish()
+    @staticmethod
+    def forward(x):
+        # return x * F.hardsigmoid(x)  # for torchscript and CoreML
+        return x * F.hardtanh(x + 3, 0., 6.) / 6.  # for torchscript, CoreML and ONNX
+
+
+class MemoryEfficientSwish(nn.Module):
+    class F(torch.autograd.Function):
+        @staticmethod
+        def forward(ctx, x):
+            ctx.save_for_backward(x)
+            return x * torch.sigmoid(x)
+
+        @staticmethod
+        def backward(ctx, grad_output):
+            x = ctx.saved_tensors[0]
+            sx = torch.sigmoid(x)
+            return grad_output * (sx * (1 + x * (1 - sx)))
+
+    def forward(self, x):
+        return self.F.apply(x)
+
+
+# Mish https://github.com/digantamisra98/Mish --------------------------------------------------------------------------
+class Mish(nn.Module):
+    @staticmethod
+    def forward(x):
+        return x * F.softplus(x).tanh()
+
+
+class MemoryEfficientMish(nn.Module):
+    class F(torch.autograd.Function):
+        @staticmethod
+        def forward(ctx, x):
+            ctx.save_for_backward(x)
+            return x.mul(torch.tanh(F.softplus(x)))  # x * tanh(ln(1 + exp(x)))
+
+        @staticmethod
+        def backward(ctx, grad_output):
+            x = ctx.saved_tensors[0]
+            sx = torch.sigmoid(x)
+            fx = F.softplus(x).tanh()
+            return grad_output * (fx + x * sx * (1 - fx * fx))
+
+    def forward(self, x):
+        return self.F.apply(x)
+
+
+# FReLU https://arxiv.org/abs/2007.11824 -------------------------------------------------------------------------------
+class FReLU(nn.Module):
+    def __init__(self, c1, k=3):  # ch_in, kernel
+        super().__init__()
+        self.conv = nn.Conv2d(c1, c1, k, 1, 1, groups=c1, bias=False)
+        self.bn = nn.BatchNorm2d(c1)
+
+    def forward(self, x):
+        return torch.max(x, self.bn(self.conv(x)))

utils/autoanchor.py

@@ -0,0 +1,160 @@
+# Auto-anchor utils
+
+import numpy as np
+import torch
+import yaml
+from scipy.cluster.vq import kmeans
+from tqdm import tqdm
+
+from utils.general import colorstr
+
+
+def check_anchor_order(m):
+    # Check anchor order against stride order for YOLOv5 Detect() module m, and correct if necessary
+    a = m.anchor_grid.prod(-1).view(-1)  # anchor area
+    da = a[-1] - a[0]  # delta a
+    ds = m.stride[-1] - m.stride[0]  # delta s
+    if da.sign() != ds.sign():  # same order
+        print('Reversing anchor order')
+        m.anchors[:] = m.anchors.flip(0)
+        m.anchor_grid[:] = m.anchor_grid.flip(0)
+
+
+def check_anchors(dataset, model, thr=4.0, imgsz=640):
+    # Check anchor fit to data, recompute if necessary
+    prefix = colorstr('autoanchor: ')
+    print(f'\n{prefix}Analyzing anchors... ', end='')
+    m = model.module.model[-1] if hasattr(model, 'module') else model.model[-1]  # Detect()
+    shapes = imgsz * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    scale = np.random.uniform(0.9, 1.1, size=(shapes.shape[0], 1))  # augment scale
+    wh = torch.tensor(np.concatenate([l[:, 3:5] * s for s, l in zip(shapes * scale, dataset.labels)])).float()  # wh
+
+    def metric(k):  # compute metric
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        best = x.max(1)[0]  # best_x
+        aat = (x > 1. / thr).float().sum(1).mean()  # anchors above threshold
+        bpr = (best > 1. / thr).float().mean()  # best possible recall
+        return bpr, aat
+
+    anchors = m.anchor_grid.clone().cpu().view(-1, 2)  # current anchors
+    bpr, aat = metric(anchors)
+    print(f'anchors/target = {aat:.2f}, Best Possible Recall (BPR) = {bpr:.4f}', end='')
+    if bpr < 0.98:  # threshold to recompute
+        print('. Attempting to improve anchors, please wait...')
+        na = m.anchor_grid.numel() // 2  # number of anchors
+        try:
+            anchors = kmean_anchors(dataset, n=na, img_size=imgsz, thr=thr, gen=1000, verbose=False)
+        except Exception as e:
+            print(f'{prefix}ERROR: {e}')
+        new_bpr = metric(anchors)[0]
+        if new_bpr > bpr:  # replace anchors
+            anchors = torch.tensor(anchors, device=m.anchors.device).type_as(m.anchors)
+            m.anchor_grid[:] = anchors.clone().view_as(m.anchor_grid)  # for inference
+            m.anchors[:] = anchors.clone().view_as(m.anchors) / m.stride.to(m.anchors.device).view(-1, 1, 1)  # loss
+            check_anchor_order(m)
+            print(f'{prefix}New anchors saved to model. Update model *.yaml to use these anchors in the future.')
+        else:
+            print(f'{prefix}Original anchors better than new anchors. Proceeding with original anchors.')
+    print('')  # newline
+
+
+def kmean_anchors(path='./data/coco128.yaml', n=9, img_size=640, thr=4.0, gen=1000, verbose=True):
+    """ Creates kmeans-evolved anchors from training dataset
+
+        Arguments:
+            path: path to dataset *.yaml, or a loaded dataset
+            n: number of anchors
+            img_size: image size used for training
+            thr: anchor-label wh ratio threshold hyperparameter hyp['anchor_t'] used for training, default=4.0
+            gen: generations to evolve anchors using genetic algorithm
+            verbose: print all results
+
+        Return:
+            k: kmeans evolved anchors
+
+        Usage:
+            from utils.autoanchor import *; _ = kmean_anchors()
+    """
+    thr = 1. / thr
+    prefix = colorstr('autoanchor: ')
+
+    def metric(k, wh):  # compute metrics
+        r = wh[:, None] / k[None]
+        x = torch.min(r, 1. / r).min(2)[0]  # ratio metric
+        # x = wh_iou(wh, torch.tensor(k))  # iou metric
+        return x, x.max(1)[0]  # x, best_x
+
+    def anchor_fitness(k):  # mutation fitness
+        _, best = metric(torch.tensor(k, dtype=torch.float32), wh)
+        return (best * (best > thr).float()).mean()  # fitness
+
+    def print_results(k):
+        k = k[np.argsort(k.prod(1))]  # sort small to large
+        x, best = metric(k, wh0)
+        bpr, aat = (best > thr).float().mean(), (x > thr).float().mean() * n  # best possible recall, anch > thr
+        print(f'{prefix}thr={thr:.2f}: {bpr:.4f} best possible recall, {aat:.2f} anchors past thr')
+        print(f'{prefix}n={n}, img_size={img_size}, metric_all={x.mean():.3f}/{best.mean():.3f}-mean/best, '
+              f'past_thr={x[x > thr].mean():.3f}-mean: ', end='')
+        for i, x in enumerate(k):
+            print('%i,%i' % (round(x[0]), round(x[1])), end=',  ' if i < len(k) - 1 else '\n')  # use in *.cfg
+        return k
+
+    if isinstance(path, str):  # *.yaml file
+        with open(path) as f:
+            data_dict = yaml.load(f, Loader=yaml.SafeLoader)  # model dict
+        from utils.datasets import LoadImagesAndLabels
+        dataset = LoadImagesAndLabels(data_dict['train'], augment=True, rect=True)
+    else:
+        dataset = path  # dataset
+
+    # Get label wh
+    shapes = img_size * dataset.shapes / dataset.shapes.max(1, keepdims=True)
+    wh0 = np.concatenate([l[:, 3:5] * s for s, l in zip(shapes, dataset.labels)])  # wh
+
+    # Filter
+    i = (wh0 < 3.0).any(1).sum()
+    if i:
+        print(f'{prefix}WARNING: Extremely small objects found. {i} of {len(wh0)} labels are < 3 pixels in size.')
+    wh = wh0[(wh0 >= 2.0).any(1)]  # filter > 2 pixels
+    # wh = wh * (np.random.rand(wh.shape[0], 1) * 0.9 + 0.1)  # multiply by random scale 0-1
+
+    # Kmeans calculation
+    print(f'{prefix}Running kmeans for {n} anchors on {len(wh)} points...')
+    s = wh.std(0)  # sigmas for whitening
+    k, dist = kmeans(wh / s, n, iter=30)  # points, mean distance
+    assert len(k) == n, print(f'{prefix}ERROR: scipy.cluster.vq.kmeans requested {n} points but returned only {len(k)}')
+    k *= s
+    wh = torch.tensor(wh, dtype=torch.float32)  # filtered
+    wh0 = torch.tensor(wh0, dtype=torch.float32)  # unfiltered
+    k = print_results(k)
+
+    # Plot
+    # k, d = [None] * 20, [None] * 20
+    # for i in tqdm(range(1, 21)):
+    #     k[i-1], d[i-1] = kmeans(wh / s, i)  # points, mean distance
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7), tight_layout=True)
+    # ax = ax.ravel()
+    # ax[0].plot(np.arange(1, 21), np.array(d) ** 2, marker='.')
+    # fig, ax = plt.subplots(1, 2, figsize=(14, 7))  # plot wh
+    # ax[0].hist(wh[wh[:, 0]<100, 0],400)
+    # ax[1].hist(wh[wh[:, 1]<100, 1],400)
+    # fig.savefig('wh.png', dpi=200)
+
+    # Evolve
+    npr = np.random
+    f, sh, mp, s = anchor_fitness(k), k.shape, 0.9, 0.1  # fitness, generations, mutation prob, sigma
+    pbar = tqdm(range(gen), desc=f'{prefix}Evolving anchors with Genetic Algorithm:')  # progress bar
+    for _ in pbar:
+        v = np.ones(sh)
+        while (v == 1).all():  # mutate until a change occurs (prevent duplicates)
+            v = ((npr.random(sh) < mp) * npr.random() * npr.randn(*sh) * s + 1).clip(0.3, 3.0)
+        kg = (k.copy() * v).clip(min=2.0)
+        fg = anchor_fitness(kg)
+        if fg > f:
+            f, k = fg, kg.copy()
+            pbar.desc = f'{prefix}Evolving anchors with Genetic Algorithm: fitness = {f:.4f}'
+            if verbose:
+                print_results(k)
+
+    return print_results(k)

utils/aws/mime.sh

@@ -0,0 +1,26 @@
+# AWS EC2 instance startup 'MIME' script https://aws.amazon.com/premiumsupport/knowledge-center/execute-user-data-ec2/
+# This script will run on every instance restart, not only on first start
+# --- DO NOT COPY ABOVE COMMENTS WHEN PASTING INTO USERDATA ---
+
+Content-Type: multipart/mixed; boundary="//"
+MIME-Version: 1.0
+
+--//
+Content-Type: text/cloud-config; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="cloud-config.txt"
+
+#cloud-config
+cloud_final_modules:
+- [scripts-user, always]
+
+--//
+Content-Type: text/x-shellscript; charset="us-ascii"
+MIME-Version: 1.0
+Content-Transfer-Encoding: 7bit
+Content-Disposition: attachment; filename="userdata.txt"
+
+#!/bin/bash
+# --- paste contents of userdata.sh here ---
+--//

utils/aws/resume.py

@@ -0,0 +1,37 @@
+# Resume all interrupted trainings in yolov5/ dir including DDP trainings
+# Usage: $ python utils/aws/resume.py
+
+import os
+import sys
+from pathlib import Path
+
+import torch
+import yaml
+
+sys.path.append('./')  # to run '$ python *.py' files in subdirectories
+
+port = 0  # --master_port
+path = Path('').resolve()
+for last in path.rglob('*/**/last.pt'):
+    ckpt = torch.load(last)
+    if ckpt['optimizer'] is None:
+        continue
+
+    # Load opt.yaml
+    with open(last.parent.parent / 'opt.yaml') as f:
+        opt = yaml.load(f, Loader=yaml.SafeLoader)
+
+    # Get device count
+    d = opt['device'].split(',')  # devices
+    nd = len(d)  # number of devices
+    ddp = nd > 1 or (nd == 0 and torch.cuda.device_count() > 1)  # distributed data parallel
+
+    if ddp:  # multi-GPU
+        port += 1
+        cmd = f'python -m torch.distributed.launch --nproc_per_node {nd} --master_port {port} train.py --resume {last}'
+    else:  # single-GPU
+        cmd = f'python train.py --resume {last}'
+
+    cmd += ' > /dev/null 2>&1 &'  # redirect output to dev/null and run in daemon thread
+    print(cmd)
+    os.system(cmd)

utils/aws/userdata.sh

@@ -0,0 +1,27 @@
+#!/bin/bash
+# AWS EC2 instance startup script https://docs.aws.amazon.com/AWSEC2/latest/UserGuide/user-data.html
+# This script will run only once on first instance start (for a re-start script see mime.sh)
+# /home/ubuntu (ubuntu) or /home/ec2-user (amazon-linux) is working dir
+# Use >300 GB SSD
+
+cd home/ubuntu
+if [ ! -d yolov5 ]; then
+  echo "Running first-time script." # install dependencies, download COCO, pull Docker
+  git clone https://github.com/ultralytics/yolov5 && sudo chmod -R 777 yolov5
+  cd yolov5
+  bash data/scripts/get_coco.sh && echo "Data done." &
+  sudo docker pull ultralytics/yolov5:latest && echo "Docker done." &
+  python -m pip install --upgrade pip && pip install -r requirements.txt && python detect.py && echo "Requirements done." &
+  wait && echo "All tasks done." # finish background tasks
+else
+  echo "Running re-start script." # resume interrupted runs
+  i=0
+  list=$(sudo docker ps -qa) # container list i.e. $'one\ntwo\nthree\nfour'
+  while IFS= read -r id; do
+    ((i++))
+    echo "restarting container $i: $id"
+    sudo docker start $id
+    # sudo docker exec -it $id python train.py --resume # single-GPU
+    sudo docker exec -d $id python utils/aws/resume.py # multi-scenario
+  done <<<"$list"
+fi

utils/flask_rest_api/README.md

@@ -0,0 +1,51 @@
+# Flask REST API
+[REST](https://en.wikipedia.org/wiki/Representational_state_transfer) [API](https://en.wikipedia.org/wiki/API)s are commonly used to expose Machine Learning (ML)  models to other services. This folder contains an example REST API created using Flask to expose the `yolov5s` model from [PyTorch Hub](https://pytorch.org/hub/ultralytics_yolov5/).
+
+## Requirements
+
+[Flask](https://palletsprojects.com/p/flask/) is required. Install with:
+```shell
+$ pip install Flask
+```
+
+## Run
+
+After Flask installation run:
+
+```shell
+$ python3 restapi.py --port 5000
+```
+
+Then use [curl](https://curl.se/) to perform a request:
+
+```shell
+$ curl -X POST -F image=@zidane.jpg 'http://localhost:5000/v1/object-detection/yolov5s'`
+```
+
+The model inference results are returned:
+
+```shell
+[{'class': 0,
+  'confidence': 0.8197850585,
+  'name': 'person',
+  'xmax': 1159.1403808594,
+  'xmin': 750.912902832,
+  'ymax': 711.2583007812,
+  'ymin': 44.0350036621},
+ {'class': 0,
+  'confidence': 0.5667674541,
+  'name': 'person',
+  'xmax': 1065.5523681641,
+  'xmin': 116.0448303223,
+  'ymax': 713.8904418945,
+  'ymin': 198.4603881836},
+ {'class': 27,
+  'confidence': 0.5661227107,
+  'name': 'tie',
+  'xmax': 516.7975463867,
+  'xmin': 416.6880187988,
+  'ymax': 717.0524902344,
+  'ymin': 429.2020568848}]
+```
+
+An example python script to perform inference using [requests](https://docs.python-requests.org/en/master/) is given in `example_request.py`

utils/flask_rest_api/example_request.py

@@ -0,0 +1,13 @@
+"""Perform test request"""
+import pprint
+
+import requests
+
+DETECTION_URL = "http://localhost:5000/v1/object-detection/yolov5s"
+TEST_IMAGE = "zidane.jpg"
+
+image_data = open(TEST_IMAGE, "rb").read()
+
+response = requests.post(DETECTION_URL, files={"image": image_data}).json()
+
+pprint.pprint(response)

utils/flask_rest_api/restapi.py

@@ -0,0 +1,38 @@
+"""
+Run a rest API exposing the yolov5s object detection model
+"""
+import argparse
+import io
+
+import torch
+from PIL import Image
+from flask import Flask, request
+
+app = Flask(__name__)
+
+DETECTION_URL = "/v1/object-detection/yolov5s"
+
+
+@app.route(DETECTION_URL, methods=["POST"])
+def predict():
+    if not request.method == "POST":
+        return
+
+    if request.files.get("image"):
+        image_file = request.files["image"]
+        image_bytes = image_file.read()
+
+        img = Image.open(io.BytesIO(image_bytes))
+
+        results = model(img, size=640)
+        data = results.pandas().xyxy[0].to_json(orient="records")
+        return data
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser(description="Flask api exposing yolov5 model")
+    parser.add_argument("--port", default=5000, type=int, help="port number")
+    args = parser.parse_args()
+
+    model = torch.hub.load("ultralytics/yolov5", "yolov5s", force_reload=True).autoshape()  # force_reload to recache
+    app.run(host="0.0.0.0", port=args.port)  # debug=True causes Restarting with stat

utils/general.py

@@ -0,0 +1,604 @@
+# YOLOv5 general utils
+
+import glob
+import logging
+import math
+import os
+import platform
+import random
+import re
+import subprocess
+import time
+from pathlib import Path
+
+import cv2
+import numpy as np
+import pandas as pd
+import torch
+import torchvision
+import yaml
+
+from utils.google_utils import gsutil_getsize
+from utils.metrics import fitness
+from utils.torch_utils import init_torch_seeds
+
+# Settings
+torch.set_printoptions(linewidth=320, precision=5, profile='long')
+np.set_printoptions(linewidth=320, formatter={'float_kind': '{:11.5g}'.format})  # format short g, %precision=5
+pd.options.display.max_columns = 10
+cv2.setNumThreads(0)  # prevent OpenCV from multithreading (incompatible with PyTorch DataLoader)
+os.environ['NUMEXPR_MAX_THREADS'] = str(min(os.cpu_count(), 8))  # NumExpr max threads
+
+
+def set_logging(rank=-1):
+    logging.basicConfig(
+        format="%(message)s",
+        level=logging.INFO if rank in [-1, 0] else logging.WARN)
+
+
+def init_seeds(seed=0):
+    # Initialize random number generator (RNG) seeds
+    random.seed(seed)
+    np.random.seed(seed)
+    init_torch_seeds(seed)
+
+
+def get_latest_run(search_dir='.'):
+    # Return path to most recent 'last.pt' in /runs (i.e. to --resume from)
+    last_list = glob.glob(f'{search_dir}/**/last*.pt', recursive=True)
+    return max(last_list, key=os.path.getctime) if last_list else ''
+
+
+def isdocker():
+    # Is environment a Docker container
+    return Path('/workspace').exists()  # or Path('/.dockerenv').exists()
+
+
+def emojis(str=''):
+    # Return platform-dependent emoji-safe version of string
+    return str.encode().decode('ascii', 'ignore') if platform.system() == 'Windows' else str
+
+
+def check_online():
+    # Check internet connectivity
+    import socket
+    try:
+        socket.create_connection(("1.1.1.1", 443), 5)  # check host accesability
+        return True
+    except OSError:
+        return False
+
+
+def check_git_status():
+    # Recommend 'git pull' if code is out of date
+    print(colorstr('github: '), end='')
+    try:
+        assert Path('.git').exists(), 'skipping check (not a git repository)'
+        assert not isdocker(), 'skipping check (Docker image)'
+        assert check_online(), 'skipping check (offline)'
+
+        cmd = 'git fetch && git config --get remote.origin.url'
+        url = subprocess.check_output(cmd, shell=True).decode().strip().rstrip('.git')  # github repo url
+        branch = subprocess.check_output('git rev-parse --abbrev-ref HEAD', shell=True).decode().strip()  # checked out
+        n = int(subprocess.check_output(f'git rev-list {branch}..origin/master --count', shell=True))  # commits behind
+        if n > 0:
+            s = f"⚠️ WARNING: code is out of date by {n} commit{'s' * (n > 1)}. " \
+                f"Use 'git pull' to update or 'git clone {url}' to download latest."
+        else:
+            s = f'up to date with {url} ✅'
+        print(emojis(s))  # emoji-safe
+    except Exception as e:
+        print(e)
+
+
+def check_requirements(requirements='requirements.txt', exclude=()):
+    # Check installed dependencies meet requirements (pass *.txt file or list of packages)
+    import pkg_resources as pkg
+    prefix = colorstr('red', 'bold', 'requirements:')
+    if isinstance(requirements, (str, Path)):  # requirements.txt file
+        file = Path(requirements)
+        if not file.exists():
+            print(f"{prefix} {file.resolve()} not found, check failed.")
+            return
+        requirements = [f'{x.name}{x.specifier}' for x in pkg.parse_requirements(file.open()) if x.name not in exclude]
+    else:  # list or tuple of packages
+        requirements = [x for x in requirements if x not in exclude]
+
+    n = 0  # number of packages updates
+    for r in requirements:
+        try:
+            pkg.require(r)
+        except Exception as e:  # DistributionNotFound or VersionConflict if requirements not met
+            n += 1
+            print(f"{prefix} {e.req} not found and is required by YOLOv5, attempting auto-update...")
+            print(subprocess.check_output(f"pip install {e.req}", shell=True).decode())
+
+    if n:  # if packages updated
+        source = file.resolve() if 'file' in locals() else requirements
+        s = f"{prefix} {n} package{'s' * (n > 1)} updated per {source}\n" \
+            f"{prefix} ⚠️ {colorstr('bold', 'Restart runtime or rerun command for updates to take effect')}\n"
+        print(emojis(s))  # emoji-safe
+
+
+def check_img_size(img_size, s=32):
+    # Verify img_size is a multiple of stride s
+    new_size = make_divisible(img_size, int(s))  # ceil gs-multiple
+    if new_size != img_size:
+        print('WARNING: --img-size %g must be multiple of max stride %g, updating to %g' % (img_size, s, new_size))
+    return new_size
+
+
+def check_imshow():
+    # Check if environment supports image displays
+    try:
+        assert not isdocker(), 'cv2.imshow() is disabled in Docker environments'
+        cv2.imshow('test', np.zeros((1, 1, 3)))
+        cv2.waitKey(1)
+        cv2.destroyAllWindows()
+        cv2.waitKey(1)
+        return True
+    except Exception as e:
+        print(f'WARNING: Environment does not support cv2.imshow() or PIL Image.show() image displays\n{e}')
+        return False
+
+
+def check_file(file):
+    # Search for file if not found
+    if Path(file).is_file() or file == '':
+        return file
+    else:
+        files = glob.glob('./**/' + file, recursive=True)  # find file
+        assert len(files), f'File Not Found: {file}'  # assert file was found
+        assert len(files) == 1, f"Multiple files match '{file}', specify exact path: {files}"  # assert unique
+        return files[0]  # return file
+
+
+def check_dataset(dict):
+    # Download dataset if not found locally
+    val, s = dict.get('val'), dict.get('download')
+    if val and len(val):
+        val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])]  # val path
+        if not all(x.exists() for x in val):
+            print('\nWARNING: Dataset not found, nonexistent paths: %s' % [str(x) for x in val if not x.exists()])
+            if s and len(s):  # download script
+                print('Downloading %s ...' % s)
+                if s.startswith('http') and s.endswith('.zip'):  # URL
+                    f = Path(s).name  # filename
+                    torch.hub.download_url_to_file(s, f)
+                    r = os.system('unzip -q %s -d ../ && rm %s' % (f, f))  # unzip
+                else:  # bash script
+                    r = os.system(s)
+                print('Dataset autodownload %s\n' % ('success' if r == 0 else 'failure'))  # analyze return value
+            else:
+                raise Exception('Dataset not found.')
+
+
+def make_divisible(x, divisor):
+    # Returns x evenly divisible by divisor
+    return math.ceil(x / divisor) * divisor
+
+
+def clean_str(s):
+    # Cleans a string by replacing special characters with underscore _
+    return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s)
+
+
+def one_cycle(y1=0.0, y2=1.0, steps=100):
+    # lambda function for sinusoidal ramp from y1 to y2
+    return lambda x: ((1 - math.cos(x * math.pi / steps)) / 2) * (y2 - y1) + y1
+
+
+def colorstr(*input):
+    # Colors a string https://en.wikipedia.org/wiki/ANSI_escape_code, i.e.  colorstr('blue', 'hello world')
+    *args, string = input if len(input) > 1 else ('blue', 'bold', input[0])  # color arguments, string
+    colors = {'black': '\033[30m',  # basic colors
+              'red': '\033[31m',
+              'green': '\033[32m',
+              'yellow': '\033[33m',
+              'blue': '\033[34m',
+              'magenta': '\033[35m',
+              'cyan': '\033[36m',
+              'white': '\033[37m',
+              'bright_black': '\033[90m',  # bright colors
+              'bright_red': '\033[91m',
+              'bright_green': '\033[92m',
+              'bright_yellow': '\033[93m',
+              'bright_blue': '\033[94m',
+              'bright_magenta': '\033[95m',
+              'bright_cyan': '\033[96m',
+              'bright_white': '\033[97m',
+              'end': '\033[0m',  # misc
+              'bold': '\033[1m',
+              'underline': '\033[4m'}
+    return ''.join(colors[x] for x in args) + f'{string}' + colors['end']
+
+
+def labels_to_class_weights(labels, nc=80):
+    # Get class weights (inverse frequency) from training labels
+    if labels[0] is None:  # no labels loaded
+        return torch.Tensor()
+
+    labels = np.concatenate(labels, 0)  # labels.shape = (866643, 5) for COCO
+    classes = labels[:, 0].astype(np.int)  # labels = [class xywh]
+    weights = np.bincount(classes, minlength=nc)  # occurrences per class
+
+    # Prepend gridpoint count (for uCE training)
+    # gpi = ((320 / 32 * np.array([1, 2, 4])) ** 2 * 3).sum()  # gridpoints per image
+    # weights = np.hstack([gpi * len(labels)  - weights.sum() * 9, weights * 9]) ** 0.5  # prepend gridpoints to start
+
+    weights[weights == 0] = 1  # replace empty bins with 1
+    weights = 1 / weights  # number of targets per class
+    weights /= weights.sum()  # normalize
+    return torch.from_numpy(weights)
+
+
+def labels_to_image_weights(labels, nc=80, class_weights=np.ones(80)):
+    # Produces image weights based on class_weights and image contents
+    class_counts = np.array([np.bincount(x[:, 0].astype(np.int), minlength=nc) for x in labels])
+    image_weights = (class_weights.reshape(1, nc) * class_counts).sum(1)
+    # index = random.choices(range(n), weights=image_weights, k=1)  # weight image sample
+    return image_weights
+
+
+def coco80_to_coco91_class():  # converts 80-index (val2014) to 91-index (paper)
+    # https://tech.amikelive.com/node-718/what-object-categories-labels-are-in-coco-dataset/
+    # a = np.loadtxt('data/coco.names', dtype='str', delimiter='\n')
+    # b = np.loadtxt('data/coco_paper.names', dtype='str', delimiter='\n')
+    # x1 = [list(a[i] == b).index(True) + 1 for i in range(80)]  # darknet to coco
+    # x2 = [list(b[i] == a).index(True) if any(b[i] == a) else None for i in range(91)]  # coco to darknet
+    x = [1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23, 24, 25, 27, 28, 31, 32, 33, 34,
+         35, 36, 37, 38, 39, 40, 41, 42, 43, 44, 46, 47, 48, 49, 50, 51, 52, 53, 54, 55, 56, 57, 58, 59, 60, 61, 62, 63,
+         64, 65, 67, 70, 72, 73, 74, 75, 76, 77, 78, 79, 80, 81, 82, 84, 85, 86, 87, 88, 89, 90]
+    return x
+
+
+def xyxy2xywh(x):
+    # Convert nx4 boxes from [x1, y1, x2, y2] to [x, y, w, h] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = (x[:, 0] + x[:, 2]) / 2  # x center
+    y[:, 1] = (x[:, 1] + x[:, 3]) / 2  # y center
+    y[:, 2] = x[:, 2] - x[:, 0]  # width
+    y[:, 3] = x[:, 3] - x[:, 1]  # height
+    return y
+
+
+def xywh2xyxy(x):
+    # Convert nx4 boxes from [x, y, w, h] to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = x[:, 0] - x[:, 2] / 2  # top left x
+    y[:, 1] = x[:, 1] - x[:, 3] / 2  # top left y
+    y[:, 2] = x[:, 0] + x[:, 2] / 2  # bottom right x
+    y[:, 3] = x[:, 1] + x[:, 3] / 2  # bottom right y
+    return y
+
+
+def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0):
+    # Convert nx4 boxes from [x, y, w, h] normalized to [x1, y1, x2, y2] where xy1=top-left, xy2=bottom-right
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = w * (x[:, 0] - x[:, 2] / 2) + padw  # top left x
+    y[:, 1] = h * (x[:, 1] - x[:, 3] / 2) + padh  # top left y
+    y[:, 2] = w * (x[:, 0] + x[:, 2] / 2) + padw  # bottom right x
+    y[:, 3] = h * (x[:, 1] + x[:, 3] / 2) + padh  # bottom right y
+    return y
+
+
+def xyn2xy(x, w=640, h=640, padw=0, padh=0):
+    # Convert normalized segments into pixel segments, shape (n,2)
+    y = x.clone() if isinstance(x, torch.Tensor) else np.copy(x)
+    y[:, 0] = w * x[:, 0] + padw  # top left x
+    y[:, 1] = h * x[:, 1] + padh  # top left y
+    return y
+
+
+def segment2box(segment, width=640, height=640):
+    # Convert 1 segment label to 1 box label, applying inside-image constraint, i.e. (xy1, xy2, ...) to (xyxy)
+    x, y = segment.T  # segment xy
+    inside = (x >= 0) & (y >= 0) & (x <= width) & (y <= height)
+    x, y, = x[inside], y[inside]
+    return np.array([x.min(), y.min(), x.max(), y.max()]) if any(x) else np.zeros((1, 4))  # xyxy
+
+
+def segments2boxes(segments):
+    # Convert segment labels to box labels, i.e. (cls, xy1, xy2, ...) to (cls, xywh)
+    boxes = []
+    for s in segments:
+        x, y = s.T  # segment xy
+        boxes.append([x.min(), y.min(), x.max(), y.max()])  # cls, xyxy
+    return xyxy2xywh(np.array(boxes))  # cls, xywh
+
+
+def resample_segments(segments, n=1000):
+    # Up-sample an (n,2) segment
+    for i, s in enumerate(segments):
+        x = np.linspace(0, len(s) - 1, n)
+        xp = np.arange(len(s))
+        segments[i] = np.concatenate([np.interp(x, xp, s[:, i]) for i in range(2)]).reshape(2, -1).T  # segment xy
+    return segments
+
+
+def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None):
+    # Rescale coords (xyxy) from img1_shape to img0_shape
+    if ratio_pad is None:  # calculate from img0_shape
+        gain = min(img1_shape[0] / img0_shape[0], img1_shape[1] / img0_shape[1])  # gain  = old / new
+        pad = (img1_shape[1] - img0_shape[1] * gain) / 2, (img1_shape[0] - img0_shape[0] * gain) / 2  # wh padding
+    else:
+        gain = ratio_pad[0][0]
+        pad = ratio_pad[1]
+
+    coords[:, [0, 2]] -= pad[0]  # x padding
+    coords[:, [1, 3]] -= pad[1]  # y padding
+    coords[:, :4] /= gain
+    clip_coords(coords, img0_shape)
+    return coords
+
+
+def clip_coords(boxes, img_shape):
+    # Clip bounding xyxy bounding boxes to image shape (height, width)
+    boxes[:, 0].clamp_(0, img_shape[1])  # x1
+    boxes[:, 1].clamp_(0, img_shape[0])  # y1
+    boxes[:, 2].clamp_(0, img_shape[1])  # x2
+    boxes[:, 3].clamp_(0, img_shape[0])  # y2
+
+
+def bbox_iou(box1, box2, x1y1x2y2=True, GIoU=False, DIoU=False, CIoU=False, eps=1e-7):
+    # Returns the IoU of box1 to box2. box1 is 4, box2 is nx4
+    box2 = box2.T
+
+    # Get the coordinates of bounding boxes
+    if x1y1x2y2:  # x1, y1, x2, y2 = box1
+        b1_x1, b1_y1, b1_x2, b1_y2 = box1[0], box1[1], box1[2], box1[3]
+        b2_x1, b2_y1, b2_x2, b2_y2 = box2[0], box2[1], box2[2], box2[3]
+    else:  # transform from xywh to xyxy
+        b1_x1, b1_x2 = box1[0] - box1[2] / 2, box1[0] + box1[2] / 2
+        b1_y1, b1_y2 = box1[1] - box1[3] / 2, box1[1] + box1[3] / 2
+        b2_x1, b2_x2 = box2[0] - box2[2] / 2, box2[0] + box2[2] / 2
+        b2_y1, b2_y2 = box2[1] - box2[3] / 2, box2[1] + box2[3] / 2
+
+    # Intersection area
+    inter = (torch.min(b1_x2, b2_x2) - torch.max(b1_x1, b2_x1)).clamp(0) * \
+            (torch.min(b1_y2, b2_y2) - torch.max(b1_y1, b2_y1)).clamp(0)
+
+    # Union Area
+    w1, h1 = b1_x2 - b1_x1, b1_y2 - b1_y1 + eps
+    w2, h2 = b2_x2 - b2_x1, b2_y2 - b2_y1 + eps
+    union = w1 * h1 + w2 * h2 - inter + eps
+
+    iou = inter / union
+    if GIoU or DIoU or CIoU:
+        cw = torch.max(b1_x2, b2_x2) - torch.min(b1_x1, b2_x1)  # convex (smallest enclosing box) width
+        ch = torch.max(b1_y2, b2_y2) - torch.min(b1_y1, b2_y1)  # convex height
+        if CIoU or DIoU:  # Distance or Complete IoU https://arxiv.org/abs/1911.08287v1
+            c2 = cw ** 2 + ch ** 2 + eps  # convex diagonal squared
+            rho2 = ((b2_x1 + b2_x2 - b1_x1 - b1_x2) ** 2 +
+                    (b2_y1 + b2_y2 - b1_y1 - b1_y2) ** 2) / 4  # center distance squared
+            if DIoU:
+                return iou - rho2 / c2  # DIoU
+            elif CIoU:  # https://github.com/Zzh-tju/DIoU-SSD-pytorch/blob/master/utils/box/box_utils.py#L47
+                v = (4 / math.pi ** 2) * torch.pow(torch.atan(w2 / h2) - torch.atan(w1 / h1), 2)
+                with torch.no_grad():
+                    alpha = v / (v - iou + (1 + eps))
+                return iou - (rho2 / c2 + v * alpha)  # CIoU
+        else:  # GIoU https://arxiv.org/pdf/1902.09630.pdf
+            c_area = cw * ch + eps  # convex area
+            return iou - (c_area - union) / c_area  # GIoU
+    else:
+        return iou  # IoU
+
+
+def box_iou(box1, box2):
+    # https://github.com/pytorch/vision/blob/master/torchvision/ops/boxes.py
+    """
+    Return intersection-over-union (Jaccard index) of boxes.
+    Both sets of boxes are expected to be in (x1, y1, x2, y2) format.
+    Arguments:
+        box1 (Tensor[N, 4])
+        box2 (Tensor[M, 4])
+    Returns:
+        iou (Tensor[N, M]): the NxM matrix containing the pairwise
+            IoU values for every element in boxes1 and boxes2
+    """
+
+    def box_area(box):
+        # box = 4xn
+        return (box[2] - box[0]) * (box[3] - box[1])
+
+    area1 = box_area(box1.T)
+    area2 = box_area(box2.T)
+
+    # inter(N,M) = (rb(N,M,2) - lt(N,M,2)).clamp(0).prod(2)
+    inter = (torch.min(box1[:, None, 2:], box2[:, 2:]) - torch.max(box1[:, None, :2], box2[:, :2])).clamp(0).prod(2)
+    return inter / (area1[:, None] + area2 - inter)  # iou = inter / (area1 + area2 - inter)
+
+
+def wh_iou(wh1, wh2):
+    # Returns the nxm IoU matrix. wh1 is nx2, wh2 is mx2
+    wh1 = wh1[:, None]  # [N,1,2]
+    wh2 = wh2[None]  # [1,M,2]
+    inter = torch.min(wh1, wh2).prod(2)  # [N,M]
+    return inter / (wh1.prod(2) + wh2.prod(2) - inter)  # iou = inter / (area1 + area2 - inter)
+
+
+def non_max_suppression(prediction, conf_thres=0.25, iou_thres=0.45, classes=None, agnostic=False, multi_label=False,
+                        labels=()):
+    """Runs Non-Maximum Suppression (NMS) on inference results
+
+    Returns:
+         list of detections, on (n,6) tensor per image [xyxy, conf, cls]
+    """
+
+    nc = prediction.shape[2] - 5  # number of classes
+    xc = prediction[..., 4] > conf_thres  # candidates
+
+    # Settings
+    min_wh, max_wh = 2, 4096  # (pixels) minimum and maximum box width and height
+    max_det = 300  # maximum number of detections per image
+    max_nms = 30000  # maximum number of boxes into torchvision.ops.nms()
+    time_limit = 10.0  # seconds to quit after
+    redundant = True  # require redundant detections
+    multi_label &= nc > 1  # multiple labels per box (adds 0.5ms/img)
+    merge = False  # use merge-NMS
+
+    t = time.time()
+    output = [torch.zeros((0, 6), device=prediction.device)] * prediction.shape[0]
+    for xi, x in enumerate(prediction):  # image index, image inference
+        # Apply constraints
+        # x[((x[..., 2:4] < min_wh) | (x[..., 2:4] > max_wh)).any(1), 4] = 0  # width-height
+        x = x[xc[xi]]  # confidence
+
+        # Cat apriori labels if autolabelling
+        if labels and len(labels[xi]):
+            l = labels[xi]
+            v = torch.zeros((len(l), nc + 5), device=x.device)
+            v[:, :4] = l[:, 1:5]  # box
+            v[:, 4] = 1.0  # conf
+            v[range(len(l)), l[:, 0].long() + 5] = 1.0  # cls
+            x = torch.cat((x, v), 0)
+
+        # If none remain process next image
+        if not x.shape[0]:
+            continue
+
+        # Compute conf
+        x[:, 5:] *= x[:, 4:5]  # conf = obj_conf * cls_conf
+
+        # Box (center x, center y, width, height) to (x1, y1, x2, y2)
+        box = xywh2xyxy(x[:, :4])
+
+        # Detections matrix nx6 (xyxy, conf, cls)
+        if multi_label:
+            i, j = (x[:, 5:] > conf_thres).nonzero(as_tuple=False).T
+            x = torch.cat((box[i], x[i, j + 5, None], j[:, None].float()), 1)
+        else:  # best class only
+            conf, j = x[:, 5:].max(1, keepdim=True)
+            x = torch.cat((box, conf, j.float()), 1)[conf.view(-1) > conf_thres]
+
+        # Filter by class
+        if classes is not None:
+            x = x[(x[:, 5:6] == torch.tensor(classes, device=x.device)).any(1)]
+
+        # Apply finite constraint
+        # if not torch.isfinite(x).all():
+        #     x = x[torch.isfinite(x).all(1)]
+
+        # Check shape
+        n = x.shape[0]  # number of boxes
+        if not n:  # no boxes
+            continue
+        elif n > max_nms:  # excess boxes
+            x = x[x[:, 4].argsort(descending=True)[:max_nms]]  # sort by confidence
+
+        # Batched NMS
+        c = x[:, 5:6] * (0 if agnostic else max_wh)  # classes
+        boxes, scores = x[:, :4] + c, x[:, 4]  # boxes (offset by class), scores
+        i = torchvision.ops.nms(boxes, scores, iou_thres)  # NMS
+        if i.shape[0] > max_det:  # limit detections
+            i = i[:max_det]
+        if merge and (1 < n < 3E3):  # Merge NMS (boxes merged using weighted mean)
+            # update boxes as boxes(i,4) = weights(i,n) * boxes(n,4)
+            iou = box_iou(boxes[i], boxes) > iou_thres  # iou matrix
+            weights = iou * scores[None]  # box weights
+            x[i, :4] = torch.mm(weights, x[:, :4]).float() / weights.sum(1, keepdim=True)  # merged boxes
+            if redundant:
+                i = i[iou.sum(1) > 1]  # require redundancy
+
+        output[xi] = x[i]
+        if (time.time() - t) > time_limit:
+            print(f'WARNING: NMS time limit {time_limit}s exceeded')
+            break  # time limit exceeded
+
+    return output
+
+
+def strip_optimizer(f='best.pt', s=''):  # from utils.general import *; strip_optimizer()
+    # Strip optimizer from 'f' to finalize training, optionally save as 's'
+    x = torch.load(f, map_location=torch.device('cpu'))
+    if x.get('ema'):
+        x['model'] = x['ema']  # replace model with ema
+    for k in 'optimizer', 'training_results', 'wandb_id', 'ema', 'updates':  # keys
+        x[k] = None
+    x['epoch'] = -1
+    x['model'].half()  # to FP16
+    for p in x['model'].parameters():
+        p.requires_grad = False
+    torch.save(x, s or f)
+    mb = os.path.getsize(s or f) / 1E6  # filesize
+    print(f"Optimizer stripped from {f},{(' saved as %s,' % s) if s else ''} {mb:.1f}MB")
+
+
+def print_mutation(hyp, results, yaml_file='hyp_evolved.yaml', bucket=''):
+    # Print mutation results to evolve.txt (for use with train.py --evolve)
+    a = '%10s' * len(hyp) % tuple(hyp.keys())  # hyperparam keys
+    b = '%10.3g' * len(hyp) % tuple(hyp.values())  # hyperparam values
+    c = '%10.4g' * len(results) % results  # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
+    print('\n%s\n%s\nEvolved fitness: %s\n' % (a, b, c))
+
+    if bucket:
+        url = 'gs://%s/evolve.txt' % bucket
+        if gsutil_getsize(url) > (os.path.getsize('evolve.txt') if os.path.exists('evolve.txt') else 0):
+            os.system('gsutil cp %s .' % url)  # download evolve.txt if larger than local
+
+    with open('evolve.txt', 'a') as f:  # append result
+        f.write(c + b + '\n')
+    x = np.unique(np.loadtxt('evolve.txt', ndmin=2), axis=0)  # load unique rows
+    x = x[np.argsort(-fitness(x))]  # sort
+    np.savetxt('evolve.txt', x, '%10.3g')  # save sort by fitness
+
+    # Save yaml
+    for i, k in enumerate(hyp.keys()):
+        hyp[k] = float(x[0, i + 7])
+    with open(yaml_file, 'w') as f:
+        results = tuple(x[0, :7])
+        c = '%10.4g' * len(results) % results  # results (P, R, mAP@0.5, mAP@0.5:0.95, val_losses x 3)
+        f.write('# Hyperparameter Evolution Results\n# Generations: %g\n# Metrics: ' % len(x) + c + '\n\n')
+        yaml.dump(hyp, f, sort_keys=False)
+
+    if bucket:
+        os.system('gsutil cp evolve.txt %s gs://%s' % (yaml_file, bucket))  # upload
+
+
+def apply_classifier(x, model, img, im0):
+    # applies a second stage classifier to yolo outputs
+    im0 = [im0] if isinstance(im0, np.ndarray) else im0
+    for i, d in enumerate(x):  # per image
+        if d is not None and len(d):
+            d = d.clone()
+
+            # Reshape and pad cutouts
+            b = xyxy2xywh(d[:, :4])  # boxes
+            b[:, 2:] = b[:, 2:].max(1)[0].unsqueeze(1)  # rectangle to square
+            b[:, 2:] = b[:, 2:] * 1.3 + 30  # pad
+            d[:, :4] = xywh2xyxy(b).long()
+
+            # Rescale boxes from img_size to im0 size
+            scale_coords(img.shape[2:], d[:, :4], im0[i].shape)
+
+            # Classes
+            pred_cls1 = d[:, 5].long()
+            ims = []
+            for j, a in enumerate(d):  # per item
+                cutout = im0[i][int(a[1]):int(a[3]), int(a[0]):int(a[2])]
+                im = cv2.resize(cutout, (224, 224))  # BGR
+                # cv2.imwrite('test%i.jpg' % j, cutout)
+
+                im = im[:, :, ::-1].transpose(2, 0, 1)  # BGR to RGB, to 3x416x416
+                im = np.ascontiguousarray(im, dtype=np.float32)  # uint8 to float32
+                im /= 255.0  # 0 - 255 to 0.0 - 1.0
+                ims.append(im)
+
+            pred_cls2 = model(torch.Tensor(ims).to(d.device)).argmax(1)  # classifier prediction
+            x[i] = x[i][pred_cls1 == pred_cls2]  # retain matching class detections
+
+    return x
+
+
+def increment_path(path, exist_ok=True, sep=''):
+    # Increment path, i.e. runs/exp --> runs/exp{sep}0, runs/exp{sep}1 etc.
+    path = Path(path)  # os-agnostic
+    if (path.exists() and exist_ok) or (not path.exists()):
+        return str(path)
+    else:
+        dirs = glob.glob(f"{path}{sep}*")  # similar paths
+        matches = [re.search(rf"%s{sep}(\d+)" % path.stem, d) for d in dirs]
+        i = [int(m.groups()[0]) for m in matches if m]  # indices
+        n = max(i) + 1 if i else 2  # increment number
+        return f"{path}{sep}{n}"  # update path