update mosaic border

utils/datasets.py

 
 
 class LoadImages:  # for inference
-    def __init__(self, path, img_size=416):
+    def __init__(self, path, img_size=640):
         path = str(Path(path))  # os-agnostic
         files = []
         if os.path.isdir(path):
 
 
 class LoadWebcam:  # for inference
-    def __init__(self, pipe=0, img_size=416):
+    def __init__(self, pipe=0, img_size=640):
         self.img_size = img_size
 
         if pipe == '0':
 
 
 class LoadStreams:  # multiple IP or RTSP cameras
-    def __init__(self, sources='streams.txt', img_size=416):
+    def __init__(self, sources='streams.txt', img_size=640):
         self.mode = 'images'
         self.img_size = img_size
 
 
 
 class LoadImagesAndLabels(Dataset):  # for training/testing
-    def __init__(self, path, img_size=416, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
+    def __init__(self, path, img_size=640, batch_size=16, augment=False, hyp=None, rect=False, image_weights=False,
                  cache_images=False, single_cls=False, stride=32, pad=0.0):
         try:
             path = str(Path(path))  # os-agnostic
         self.image_weights = image_weights
         self.rect = False if image_weights else rect
         self.mosaic = self.augment and not self.rect  # load 4 images at a time into a mosaic (only during training)
+        self.mosaic_border = None
+        self.stride = stride
+
 
         # Define labels
         self.label_files = [x.replace('images', 'labels').replace(os.path.splitext(x)[-1], '.txt')
 
     labels4 = []
     s = self.img_size
-    xc, yc = [int(random.uniform(s * 0.5, s * 1.5)) for _ in range(2)]  # mosaic center x, y
+    border = [-s // 2, -s // 2]  # self.mosaic_border
+    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in border]  # mosaic center x, y
     indices = [index] + [random.randint(0, len(self.labels) - 1) for _ in range(3)]  # 3 additional image indices
     for i, index in enumerate(indices):
         # Load image
                                   translate=self.hyp['translate'],
                                   scale=self.hyp['scale'],
                                   shear=self.hyp['shear'],
-                                  border=-s // 2)  # border to remove
+                                  border=border)  # border to remove
 
     return img4, labels4
 
 
-def letterbox(img, new_shape=(416, 416), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
+def letterbox(img, new_shape=(640, 640), color=(114, 114, 114), auto=True, scaleFill=False, scaleup=True):
     # Resize image to a 32-pixel-multiple rectangle https://github.com/ultralytics/yolov3/issues/232
     shape = img.shape[:2]  # current shape [height, width]
     if isinstance(new_shape, int):
     return img, ratio, (dw, dh)
 
 
-def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, border=0):
+def random_affine(img, targets=(), degrees=10, translate=.1, scale=.1, shear=10, border=(0, 0)):
     # torchvision.transforms.RandomAffine(degrees=(-10, 10), translate=(.1, .1), scale=(.9, 1.1), shear=(-10, 10))
     # https://medium.com/uruvideo/dataset-augmentation-with-random-homographies-a8f4b44830d4
     # targets = [cls, xyxy]
 
-    height = img.shape[0] + border * 2
-    width = img.shape[1] + border * 2
+    height = img.shape[0] + border[0] * 2  # shape(h,w,c)
+    width = img.shape[1] + border[1] * 2
 
     # Rotation and Scale
     R = np.eye(3)
 
     # Translation
     T = np.eye(3)
-    T[0, 2] = random.uniform(-translate, translate) * img.shape[0] + border  # x translation (pixels)
-    T[1, 2] = random.uniform(-translate, translate) * img.shape[1] + border  # y translation (pixels)
+    T[0, 2] = random.uniform(-translate, translate) * img.shape[1] + border[1]  # x translation (pixels)
+    T[1, 2] = random.uniform(-translate, translate) * img.shape[0] + border[0]  # y translation (pixels)
 
     # Shear
     S = np.eye(3)
 
     # Combined rotation matrix
     M = S @ T @ R  # ORDER IS IMPORTANT HERE!!
-    if (border != 0) or (M != np.eye(3)).any():  # image changed
+    if (border[0] != 0) or (border[1] != 0) or (M != np.eye(3)).any():  # image changed
         img = cv2.warpAffine(img, M[:2], dsize=(width, height), flags=cv2.INTER_LINEAR, borderValue=(114, 114, 114))
 
     # Transform label coordinates