zjc
/
yolov5
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Creado con Colaboratory

This commit is contained in:
Glenn Jocher 2020-11-11 16:11:49 +01:00
parent 104f5418ea
commit 9cd46427e4
1 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

12
tutorial.ipynb vendored
View File

@ -824,7 +824,7 @@
"source": [ "source": [
"# 3. Train\n", "# 3. Train\n",
"\n", "\n",
"Download [COCO128](https://www.kaggle.com/ultralytics/coco128), a small 128-image tutorial dataset, start tensorboard and train YOLOv5s from a pretrained checkpoint for 3 epochs (actual training is typically much longer, around **300-1000 epochs**, depending on your dataset)." "Download [COCO128](https://www.kaggle.com/ultralytics/coco128), a small 128-image tutorial dataset, start tensorboard and train YOLOv5s from a pretrained checkpoint for 3 epochs (note actual training is typically much longer, around **300-1000 epochs**, depending on your dataset)."
] ]
}, },
{ {
@ -885,9 +885,9 @@
"id": "_pOkGLv1dMqh" "id": "_pOkGLv1dMqh"
}, },
"source": [ "source": [
"Train a YOLOv5s model on [COCO128](https://www.kaggle.com/ultralytics/coco128) with dataset `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and **COCO, COCO128, and VOC datasets are downloaded automatically** on first use.\n", "Train a YOLOv5s model on [COCO128](https://www.kaggle.com/ultralytics/coco128) with `--data coco128.yaml`, starting from pretrained `--weights yolov5s.pt`, or from randomly initialized `--weights '' --cfg yolov5s.yaml`. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases), and **COCO, COCO128, and VOC datasets are downloaded automatically** on first use.\n",
"\n", "\n",
"All training results are saved to `runs/train/exp0` for the first experiment, then `runs/exp1`, `runs/exp2` etc. for subsequent experiments.\n" "All training results are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp0`, `runs/train/exp1` etc.\n"
] ]
}, },
{ {
@ -1012,7 +1012,7 @@
"source": [ "source": [
"## Weights & Biases Logging (🚀 NEW)\n", "## Weights & Biases Logging (🚀 NEW)\n",
"\n", "\n",
"[Weights & Biases](https://www.wandb.com/) (W&B) is now integrated with YOLOv5 for real-time visualization and cloud logging of training runs. This allows for better run comparison and introspection, as well improved visibility and collaboration among team members. To enable W&B logging install `wandb`, and then train normally (you will be guided setup on first use).\n", "[Weights & Biases](https://www.wandb.com/) (W&B) is now integrated with YOLOv5 for real-time visualization and cloud logging of training runs. This allows for better run comparison and introspection, as well improved visibility and collaboration for teams. To enable W&B logging install `wandb`, and then train normally (you will be guided setup on first use).\n",
"```bash\n", "```bash\n",
"$ pip install wandb\n", "$ pip install wandb\n",
"```\n", "```\n",
@ -1030,7 +1030,7 @@
"source": [ "source": [
"## Local Logging\n", "## Local Logging\n",
"\n", "\n",
"All results are logged by default to the `runs/train/exp0` directory, with a new directory created for each new training as `runs/exp1`, `runs/exp2`, etc. View train and test jpgs to see mosaics, labels/predictions and augmentation effects. Note a **Mosaic Dataloader** is used for training (shown below), a new concept developed by Ultralytics and first featured in [YOLOv4](https://arxiv.org/abs/2004.10934)." "All results are logged by default to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp1`, `runs/train/exp2`, etc. View train and test jpgs to see mosaics, labels, predictions and augmentation effects. Note a **Mosaic Dataloader** is used for training (shown below), a new concept developed by Ultralytics and first featured in [YOLOv4](https://arxiv.org/abs/2004.10934)."
] ]
}, },
{ {
@ -1053,7 +1053,7 @@
}, },
"source": [ "source": [
"> <img src=\"https://user-images.githubusercontent.com/26833433/83667642-90fcb200-a583-11ea-8fa3-338bbf7da194.jpeg\" width=\"750\"> \n", "> <img src=\"https://user-images.githubusercontent.com/26833433/83667642-90fcb200-a583-11ea-8fa3-338bbf7da194.jpeg\" width=\"750\"> \n",
"`train_batch0.jpg` train batch 0 mosaics and labels\n", "`train_batch0.jpg` shows train batch 0 mosaics and labels\n",
"\n", "\n",
"> <img src=\"https://user-images.githubusercontent.com/26833433/83667626-8c37fe00-a583-11ea-997b-0923fe59b29b.jpeg\" width=\"750\"> \n", "> <img src=\"https://user-images.githubusercontent.com/26833433/83667626-8c37fe00-a583-11ea-997b-0923fe59b29b.jpeg\" width=\"750\"> \n",
"`test_batch0_labels.jpg` shows test batch 0 labels\n", "`test_batch0_labels.jpg` shows test batch 0 labels\n",