\n",
"\n",
" \n",
" \n",
"\n",
"\n",
" \n",
" \n",
" \n",
" \n",
" \n",
"\n",
"This YOLOv5 π notebook by Ultralytics presents simple train, validate and predict examples to help start your AI adventure. See GitHub for community support or contact us for professional support.\n",
"\n",
"
\n",
"Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n",
"
\n",
"\n",
"Train a YOLOv5s Classification model on the [Imagenette](https://image-net.org/) dataset with `--data imagenet`, starting from pretrained `--pretrained yolov5s-cls.pt`.\n",
"\n",
"- **Pretrained [Models](https://github.com/ultralytics/yolov5/tree/master/models)** are downloaded\n",
"automatically from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases)\n",
"- **Training Results** are saved to `runs/train-cls/` with incrementing run directories, i.e. `runs/train-cls/exp2`, `runs/train-cls/exp3` etc.\n",
"
\n",
"\n",
"A **Mosaic Dataloader** is used for training which combines 4 images into 1 mosaic.\n",
"\n",
"## Train on Custom Data with Roboflow π NEW\n",
"\n",
"[Roboflow](https://roboflow.com/?ref=ultralytics) enables you to easily **organize, label, and prepare** a high quality dataset with your own custom data. Roboflow also makes it easy to establish an active learning pipeline, collaborate with your team on dataset improvement, and integrate directly into your model building workflow with the `roboflow` pip package.\n",
"\n",
"- Custom Training Example: [https://blog.roboflow.com/train-yolov5-classification-custom-data/](https://blog.roboflow.com/train-yolov5-classification-custom-data/?ref=ultralytics)\n",
"- Custom Training Notebook: [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1KZiKUAjtARHAfZCXbJRv14-pOnIsBLPV?usp=sharing)\n",
" \n",
"\n",
"
Label images lightning fast (including with model-assisted labeling)"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "i3oKtE4g-aNn"
},
"outputs": [],
"source": [
"#@title Select YOLOv5 π logger {run: 'auto'}\n",
"logger = 'Comet' #@param ['Comet', 'ClearML', 'TensorBoard']\n",
"\n",
"if logger == 'Comet':\n",
" %pip install -q comet_ml\n",
" import comet_ml; comet_ml.init()\n",
"elif logger == 'ClearML':\n",
" %pip install -q clearml\n",
" import clearml; clearml.browser_login()\n",
"elif logger == 'TensorBoard':\n",
" %load_ext tensorboard\n",
" %tensorboard --logdir runs/train"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"colab": {
"base_uri": "https://localhost:8080/"
},
"id": "1NcFxRcFdJ_O",
"outputId": "77c8d487-16db-4073-b3ea-06cabf2e7766"
},
"outputs": [
{
"output_type": "stream",
"name": "stdout",
"text": [
"\u001b[34m\u001b[1mclassify/train: \u001b[0mmodel=yolov5s-cls.pt, data=imagenette160, epochs=5, batch_size=64, imgsz=224, nosave=False, cache=ram, device=, workers=8, project=runs/train-cls, name=exp, exist_ok=False, pretrained=True, optimizer=Adam, lr0=0.001, decay=5e-05, label_smoothing=0.1, cutoff=None, dropout=None, verbose=False, seed=0, local_rank=-1\n",
"\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov5 β \n",
"YOLOv5 π v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
"\n",
"\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train-cls', view at http://localhost:6006/\n",
"\n",
"Dataset not found β οΈ, missing path /content/datasets/imagenette160, attempting download...\n",
"Downloading https://github.com/ultralytics/yolov5/releases/download/v1.0/imagenette160.zip to /content/datasets/imagenette160.zip...\n",
"100% 103M/103M [00:00<00:00, 347MB/s] \n",
"Unzipping /content/datasets/imagenette160.zip...\n",
"Dataset download success β (3.3s), saved to \u001b[1m/content/datasets/imagenette160\u001b[0m\n",
"\n",
"\u001b[34m\u001b[1malbumentations: \u001b[0mRandomResizedCrop(p=1.0, height=224, width=224, scale=(0.08, 1.0), ratio=(0.75, 1.3333333333333333), interpolation=1), HorizontalFlip(p=0.5), ColorJitter(p=0.5, brightness=[0.6, 1.4], contrast=[0.6, 1.4], saturation=[0.6, 1.4], hue=[0, 0]), Normalize(p=1.0, mean=(0.485, 0.456, 0.406), std=(0.229, 0.224, 0.225), max_pixel_value=255.0), ToTensorV2(always_apply=True, p=1.0, transpose_mask=False)\n",
"Model summary: 149 layers, 4185290 parameters, 4185290 gradients, 10.5 GFLOPs\n",
"\u001b[34m\u001b[1moptimizer:\u001b[0m Adam(lr=0.001) with parameter groups 32 weight(decay=0.0), 33 weight(decay=5e-05), 33 bias\n",
"Image sizes 224 train, 224 test\n",
"Using 1 dataloader workers\n",
"Logging results to \u001b[1mruns/train-cls/exp\u001b[0m\n",
"Starting yolov5s-cls.pt training on imagenette160 dataset with 10 classes for 5 epochs...\n",
"\n",
" Epoch GPU_mem train_loss val_loss top1_acc top5_acc\n",
" 1/5 1.47G 1.05 0.974 0.828 0.975: 100% 148/148 [00:38<00:00, 3.82it/s]\n",
" 2/5 1.73G 0.895 0.766 0.911 0.994: 100% 148/148 [00:36<00:00, 4.03it/s]\n",
" 3/5 1.73G 0.82 0.704 0.934 0.996: 100% 148/148 [00:35<00:00, 4.20it/s]\n",
" 4/5 1.73G 0.766 0.664 0.951 0.998: 100% 148/148 [00:36<00:00, 4.05it/s]\n",
" 5/5 1.73G 0.724 0.634 0.959 0.997: 100% 148/148 [00:37<00:00, 3.94it/s]\n",
"\n",
"Training complete (0.052 hours)\n",
"Results saved to \u001b[1mruns/train-cls/exp\u001b[0m\n",
"Predict: python classify/predict.py --weights runs/train-cls/exp/weights/best.pt --source im.jpg\n",
"Validate: python classify/val.py --weights runs/train-cls/exp/weights/best.pt --data /content/datasets/imagenette160\n",
"Export: python export.py --weights runs/train-cls/exp/weights/best.pt --include onnx\n",
"PyTorch Hub: model = torch.hub.load('ultralytics/yolov5', 'custom', 'runs/train-cls/exp/weights/best.pt')\n",
"Visualize: https://netron.app\n",
"\n"
]
}
],
"source": [
"# Train YOLOv5s Classification on Imagenette160 for 3 epochs\n",
"!python classify/train.py --model yolov5s-cls.pt --data imagenette160 --epochs 5 --img 224 --cache"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "15glLzbQx5u0"
},
"source": [
"# 4. Visualize"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "nWOsI5wJR1o3"
},
"source": [
"## Comet Logging and Visualization π NEW\n",
"\n",
"[Comet](https://www.comet.com/site/lp/yolov5-with-comet/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=yolov5_colab) is now fully integrated with YOLOv5. Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with [Comet Custom Panels](https://www.comet.com/docs/v2/guides/comet-dashboard/code-panels/about-panels/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=yolov5_colab)! Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes!\n",
"\n",
"Getting started is easy:\n",
"```shell\n",
"pip install comet_ml # 1. install\n",
"export COMET_API_KEY= # 2. paste API key\n",
"python train.py --img 640 --epochs 3 --data coco128.yaml --weights yolov5s.pt # 3. train\n",
"```\n",
"To learn more about all of the supported Comet features for this integration, check out the [Comet Tutorial](https://docs.ultralytics.com/yolov5/tutorials/comet_logging_integration). If you'd like to learn more about Comet, head over to our [documentation](https://www.comet.com/docs/v2/?utm_source=yolov5&utm_medium=partner&utm_campaign=partner_yolov5_2022&utm_content=yolov5_colab). Get started by trying out the Comet Colab Notebook:\n",
"[![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/drive/1RG0WOQyxlDlo5Km8GogJpIEJlg_5lyYO?usp=sharing)\n",
"\n",
"\n",
""
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "Lay2WsTjNJzP"
},
"source": [
"## ClearML Logging and Automation π NEW\n",
"\n",
"[ClearML](https://cutt.ly/yolov5-notebook-clearml) is completely integrated into YOLOv5 to track your experimentation, manage dataset versions and even remotely execute training runs. To enable ClearML (check cells above):\n",
"\n",
"- `pip install clearml`\n",
"- run `clearml-init` to connect to a ClearML server (**deploy your own [open-source server](https://github.com/allegroai/clearml-server)**, or use our [free hosted server](https://cutt.ly/yolov5-notebook-clearml))\n",
"\n",
"You'll get all the great expected features from an experiment manager: live updates, model upload, experiment comparison etc. but ClearML also tracks uncommitted changes and installed packages for example. Thanks to that ClearML Tasks (which is what we call experiments) are also reproducible on different machines! With only 1 extra line, we can schedule a YOLOv5 training task on a queue to be executed by any number of ClearML Agents (workers).\n",
"\n",
"You can use ClearML Data to version your dataset and then pass it to YOLOv5 simply using its unique ID. This will help you keep track of your data without adding extra hassle. Explore the [ClearML Tutorial](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration) for details!\n",
"\n",
"\n",
""
]
},
{
"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",
"\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",
"- **Notebooks** with free GPU: \n",
"- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/google_cloud_quickstart_tutorial/)\n",
"- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/aws_quickstart_tutorial/)\n",
"- **Docker Image**. See [Docker Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/docker_image_quickstart_tutorial/) \n"
]
},
{
"cell_type": "markdown",
"metadata": {
"id": "6Qu7Iesl0p54"
},
"source": [
"# Status\n",
"\n",
"![YOLOv5 CI](https://github.com/ultralytics/yolov5/actions/workflows/ci-testing.yml/badge.svg)\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."
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {
"id": "GMusP4OAxFu6"
},
"outputs": [],
"source": [
"# YOLOv5 PyTorch HUB Inference (DetectionModels only)\n",
"import torch\n",
"\n",
"model = torch.hub.load('ultralytics/yolov5', 'yolov5s') # yolov5n - yolov5x6 or custom\n",
"im = 'https://ultralytics.com/images/zidane.jpg' # file, Path, PIL.Image, OpenCV, nparray, list\n",
"results = model(im) # inference\n",
"results.print() # or .show(), .save(), .crop(), .pandas(), etc."
]
}
],
"metadata": {
"accelerator": "GPU",
"colab": {
"name": "YOLOv5 Classification Tutorial",
"provenance": []
},
"kernelspec": {
"display_name": "Python 3 (ipykernel)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.7.12"
}
},
"nbformat": 4,
"nbformat_minor": 0
}