![](\"https://github.com/ultralytics/assets/raw/master/yolov5/v62/splash_notebook.png\")
\n",
"\n",
"\n",
"![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
\n",
" ![\"Open](\"https://kaggle.com/static/images/open-in-kaggle.svg\")
\n",
"![](\"https://user-images.githubusercontent.com/26833433/127574988-6a558aa1-d268-44b9-bf6b-62d4c605cc72.jpg\")
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "0eq1SMWl6Sfn"
},
"source": [
"# 2. Validate\n",
"Validate a model's accuracy on the [COCO](https://cocodataset.org/#home) dataset's `val` or `test` splits. Models are downloaded automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases). To show results by class use the `--verbose` flag."
]
},
{
"cell_type": "code",
"metadata": {
"id": "WQPtK1QYVaD_",
"colab": {
"base_uri": "https://localhost:8080/",
"height": 49,
"referenced_widgets": [
"9b8caa3522fc4cbab31e13b5dfc7808d",
"574140e4c4bc48c9a171541a02cd0211",
"35e03ce5090346c9ae602891470fc555",
"c942c208e72d46568b476bb0f2d75496",
"65881db1db8a4e9c930fab9172d45143",
"60b913d755b34d638478e30705a2dde1",
"0856bea36ec148b68522ff9c9eb258d8",
"76879f6f2aa54637a7a07faeea2bd684",
"0ace3934ec6f4d36a1b3a9e086390926",
"d6b7a2243e0c4beca714d99dceec23d6",
"5966ba6e6f114d8c9d8d1d6b1bd4f4c7"
]
},
"outputId": "102dabed-bc31-42fe-9133-d9ce28a2c01e"
},
"source": [
"# Download COCO val\n",
"torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip') # download (780M - 5000 images)\n",
"!unzip -q tmp.zip -d ../datasets && rm tmp.zip # unzip"
],
"execution_count": 3,
"outputs": [
{
"output_type": "display_data",
"data": {
"text/plain": [
" 0%| | 0.00/780M [00:00![](\"https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/615627e5824c9c6195abfda9_computer-vision-cycle.png\"/)
\n",
"Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n",
"![](\"https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a275ad4b4ac20cd2e21a_roboflow-annotate.gif\"/)
![\"ClearML](\"https://github.com/thepycoder/clearml_screenshots/raw/main/scalars.jpg\")
"
],
"metadata": {
"id": "Lay2WsTjNJzP"
}
},
{
"cell_type": "markdown",
"metadata": {
"id": "DLI1JmHU7B0l"
},
"source": [
"## Weights & Biases Logging\n",
"\n",
"[Weights & Biases](https://wandb.ai/site?utm_campaign=repo_yolo_notebook) (W&B) is 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 `pip install wandb`, and then train normally (you will be guided through setup on first use). \n",
"\n",
"During training you will see live updates at [https://wandb.ai/home](https://wandb.ai/home?utm_campaign=repo_yolo_notebook), and you can create and share detailed [Reports](https://wandb.ai/glenn-jocher/yolov5_tutorial/reports/YOLOv5-COCO128-Tutorial-Results--VmlldzozMDI5OTY) of your results. For more information see the [YOLOv5 Weights & Biases Tutorial](https://github.com/ultralytics/yolov5/issues/1289). \n",
"\n",
"\n",
"![\"Weights](\"https://user-images.githubusercontent.com/26833433/182482859-288a9622-4661-48db-99de-650d1dead5c6.jpg\")
"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "-WPvRbS5Swl6"
},
"source": [
"## Local Logging\n",
"\n",
"Training results are automatically logged with [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) loggers to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc.\n",
"\n",
"This directory contains train and val statistics, mosaics, labels, predictions and augmentated mosaics, as well as metrics and charts including precision-recall (PR) curves and confusion matrices. \n",
"\n",
"![\"Local](\"https://user-images.githubusercontent.com/26833433/183222430-e1abd1b7-782c-4cde-b04d-ad52926bf818.jpg\")
\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Zelyeqbyt3GD"
},
"source": [
"# Environments\n",
"\n",
"YOLOv5 may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled):\n",
"\n",
"- **Google Colab and Kaggle** notebooks with free GPU: \n",
"- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/GCP-Quickstart)\n",
"- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/AWS-Quickstart)\n",
"- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov5/wiki/Docker-Quickstart) ![\"Docker](\"https://img.shields.io/docker/pulls/ultralytics/yolov5?logo=docker\")
\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6Qu7Iesl0p54"
},
"source": [
"# Status\n",
"\n",
"\n",
"\n",
"If this badge is green, all [YOLOv5 GitHub Actions](https://github.com/ultralytics/yolov5/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv5 training ([train.py](https://github.com/ultralytics/yolov5/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov5/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov5/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov5/blob/master/export.py)) on macOS, Windows, and Ubuntu every 24 hours and on every commit.\n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "IEijrePND_2I"
},
"source": [
"# Appendix\n",
"\n",
"Additional content below for PyTorch Hub, CI, reproducing results, profiling speeds, VOC training, classification training and TensorRT example."
]
},
{
"cell_type": "code",
"metadata": {
"id": "GMusP4OAxFu6"
},
"source": [
"import torch\n",
"\n",
"# PyTorch Hub Model\n",
"model = torch.hub.load('ultralytics/yolov5', 'yolov5s') # or yolov5n - yolov5x6, custom\n",
"\n",
"# Images\n",
"img = 'https://ultralytics.com/images/zidane.jpg' # or file, Path, PIL, OpenCV, numpy, list\n",
"\n",
"# Inference\n",
"results = model(img)\n",
"\n",
"# Results\n",
"results.print() # or .show(), .save(), .crop(), .pandas(), etc."
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "FGH0ZjkGjejy"
},
"source": [
"# YOLOv5 CI\n",
"%%shell\n",
"rm -rf runs # remove runs/\n",
"m=yolov5n # official weights\n",
"b=runs/train/exp/weights/best # best.pt checkpoint\n",
"python train.py --imgsz 64 --batch 32 --weights $m.pt --cfg $m.yaml --epochs 1 --device 0 # train\n",
"for d in 0 cpu; do # devices\n",
" for w in $m $b; do # weights\n",
" python val.py --imgsz 64 --batch 32 --weights $w.pt --device $d # val\n",
" python detect.py --imgsz 64 --weights $w.pt --device $d # detect\n",
" done\n",
"done\n",
"python hubconf.py --model $m # hub\n",
"python models/tf.py --weights $m.pt # build TF model\n",
"python models/yolo.py --cfg $m.yaml # build PyTorch model\n",
"python export.py --weights $m.pt --img 64 --include torchscript # export"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "mcKoSIK2WSzj"
},
"source": [
"# Reproduce\n",
"for x in (f'yolov5{x}' for x in 'nsmlx'):\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --task speed # speed\n",
" !python val.py --weights {x}.pt --data coco.yaml --img 640 --conf 0.001 --iou 0.65 # mAP"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "gogI-kwi3Tye"
},
"source": [
"# Profile\n",
"from utils.torch_utils import profile\n",
"\n",
"m1 = lambda x: x * torch.sigmoid(x)\n",
"m2 = torch.nn.SiLU()\n",
"results = profile(input=torch.randn(16, 3, 640, 640), ops=[m1, m2], n=100)"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "BSgFCAcMbk1R"
},
"source": [
"# VOC\n",
"for b, m in zip([64, 64, 64, 32, 16], [f'yolov5{x}' for x in 'nsmlx']): # batch, model\n",
" !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --img 512 --hyp hyp.VOC.yaml --project VOC --name {m} --cache"
],
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Classification train\n",
"for m in [*(f'yolov5{x}-cls.pt' for x in 'nsmlx'), 'resnet50.pt', 'resnet101.pt', 'efficientnet_b0.pt', 'efficientnet_b1.pt']:\n",
" for d in 'mnist', 'fashion-mnist', 'cifar10', 'cifar100', 'imagenette160', 'imagenette320', 'imagenette', 'imagewoof160', 'imagewoof320', 'imagewoof':\n",
" !python classify/train.py --model {m} --data {d} --epochs 10 --project YOLOv5-cls --name {m}-{d}"
],
"metadata": {
"id": "UWGH7H6yakVl"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Classification val\n",
"!bash data/scripts/get_imagenet.sh --val # download ImageNet val split (6.3G - 50000 images)\n",
"!python classify/val.py --weights yolov5m-cls.pt --data ../datasets/imagenet --img 224 # validate"
],
"metadata": {
"id": "yYgOiFNHZx-1"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"source": [
"# Validate on COCO test. Zip results.json and submit to eval server at https://competitions.codalab.org/competitions/20794\n",
"!bash data/scripts/get_coco.sh --test # download COCO test-dev2017 (7G - 40000 images, test 20000)\n",
"!python val.py --weights yolov5x.pt --data coco.yaml --img 640 --iou 0.65 --half --task test"
],
"metadata": {
"id": "aq4DPWGu0Bl1"
},
"execution_count": null,
"outputs": []
},
{
"cell_type": "code",
"metadata": {
"id": "VTRwsvA9u7ln"
},
"source": [
"# TensorRT \n",
"!pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com # install\n",
"!python export.py --weights yolov5s.pt --include engine --imgsz 640 --device 0 # export\n",
"!python detect.py --weights yolov5s.engine --imgsz 640 --device 0 # inference"
],
"execution_count": null,
"outputs": []
}
]
}