{ "nbformat": 4, "nbformat_minor": 0, "metadata": { "colab": { "name": "YOLOv3 Tutorial", "provenance": [], "include_colab_link": true }, "kernelspec": { "name": "python3", "display_name": "Python 3" }, "accelerator": "GPU", "widgets": { "application/vnd.jupyter.widget-state+json": { "eeda9d6850e8406f9bbc5b06051b3710": { "model_module": "@jupyter-widgets/controls", "model_name": "HBoxModel", "model_module_version": "1.5.0", "state": { "_view_name": "HBoxView", "_dom_classes": [], "_model_name": "HBoxModel", "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "_view_count": null, "_view_module_version": "1.5.0", "box_style": "", "layout": "IPY_MODEL_1e823c45174a4216be7234a6cc5cfd99", "_model_module": "@jupyter-widgets/controls", "children": [ "IPY_MODEL_cd8efd6c5de94ea8848a7d5b8766a4d6", "IPY_MODEL_a4ec69c4697c4b0e84e6193be227f63e", "IPY_MODEL_9a5694c133be46df8d2fe809b77c1c35" ] } }, "1e823c45174a4216be7234a6cc5cfd99": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_view_name": "LayoutView", "grid_template_rows": null, "right": null, "justify_content": null, "_view_module": "@jupyter-widgets/base", "overflow": null, "_model_module_version": "1.2.0", "_view_count": null, "flex_flow": null, "width": null, "min_width": null, "border": null, "align_items": null, "bottom": null, "_model_module": "@jupyter-widgets/base", "top": null, "grid_column": null, "overflow_y": null, "overflow_x": null, "grid_auto_flow": null, "grid_area": null, "grid_template_columns": null, "flex": null, "_model_name": "LayoutModel", "justify_items": null, "grid_row": null, "max_height": null, "align_content": null, "visibility": null, "align_self": null, "height": null, "min_height": null, "padding": null, "grid_auto_rows": null, "grid_gap": null, "max_width": null, "order": null, "_view_module_version": "1.2.0", "grid_template_areas": null, "object_position": null, "object_fit": null, "grid_auto_columns": null, "margin": null, "display": null, "left": null } }, "cd8efd6c5de94ea8848a7d5b8766a4d6": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_view_name": "HTMLView", "style": "IPY_MODEL_d584167143f84a0484006dded3fd2620", "_dom_classes": [], "description": "", "_model_name": "HTMLModel", "placeholder": "​", "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "value": "100%", "_view_count": null, "_view_module_version": "1.5.0", "description_tooltip": null, "_model_module": "@jupyter-widgets/controls", "layout": "IPY_MODEL_b9a25c0d425c4fe4b8cd51ae6a301b0d" } }, "a4ec69c4697c4b0e84e6193be227f63e": { "model_module": "@jupyter-widgets/controls", "model_name": "FloatProgressModel", "model_module_version": "1.5.0", "state": { "_view_name": "ProgressView", "style": "IPY_MODEL_654525fe1ed34d5fbe1c36ed80ae1c1c", "_dom_classes": [], "description": "", "_model_name": "FloatProgressModel", "bar_style": "success", "max": 818322941, "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "value": 818322941, "_view_count": null, "_view_module_version": "1.5.0", "orientation": "horizontal", "min": 0, "description_tooltip": null, "_model_module": "@jupyter-widgets/controls", "layout": "IPY_MODEL_09544845070e47baafc5e37d45ff23e9" } }, "9a5694c133be46df8d2fe809b77c1c35": { "model_module": "@jupyter-widgets/controls", "model_name": "HTMLModel", "model_module_version": "1.5.0", "state": { "_view_name": "HTMLView", "style": "IPY_MODEL_1066f1d5b6104a3dae19f26269745bd0", "_dom_classes": [], "description": "", "_model_name": "HTMLModel", "placeholder": "​", "_view_module": "@jupyter-widgets/controls", "_model_module_version": "1.5.0", "value": " 780M/780M [00:03<00:00, 200MB/s]", "_view_count": null, "_view_module_version": "1.5.0", "description_tooltip": null, "_model_module": "@jupyter-widgets/controls", "layout": "IPY_MODEL_dd3a70e1ef4547ec8d3463749ce06285" } }, "d584167143f84a0484006dded3fd2620": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_view_name": "StyleView", "_model_name": "DescriptionStyleModel", "description_width": "", "_view_module": "@jupyter-widgets/base", "_model_module_version": "1.5.0", "_view_count": null, "_view_module_version": "1.2.0", "_model_module": "@jupyter-widgets/controls" } }, "b9a25c0d425c4fe4b8cd51ae6a301b0d": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_view_name": "LayoutView", "grid_template_rows": null, "right": null, "justify_content": null, "_view_module": "@jupyter-widgets/base", "overflow": null, "_model_module_version": "1.2.0", "_view_count": null, "flex_flow": null, "width": null, "min_width": null, "border": null, "align_items": null, "bottom": null, "_model_module": "@jupyter-widgets/base", "top": null, "grid_column": null, "overflow_y": null, "overflow_x": null, "grid_auto_flow": null, "grid_area": null, "grid_template_columns": null, "flex": null, "_model_name": "LayoutModel", "justify_items": null, "grid_row": null, "max_height": null, "align_content": null, "visibility": null, "align_self": null, "height": null, "min_height": null, "padding": null, "grid_auto_rows": null, "grid_gap": null, "max_width": null, "order": null, "_view_module_version": "1.2.0", "grid_template_areas": null, "object_position": null, "object_fit": null, "grid_auto_columns": null, "margin": null, "display": null, "left": null } }, "654525fe1ed34d5fbe1c36ed80ae1c1c": { "model_module": "@jupyter-widgets/controls", "model_name": "ProgressStyleModel", "model_module_version": "1.5.0", "state": { "_view_name": "StyleView", "_model_name": "ProgressStyleModel", "description_width": "", "_view_module": "@jupyter-widgets/base", "_model_module_version": "1.5.0", "_view_count": null, "_view_module_version": "1.2.0", "bar_color": null, "_model_module": "@jupyter-widgets/controls" } }, "09544845070e47baafc5e37d45ff23e9": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_view_name": "LayoutView", "grid_template_rows": null, "right": null, "justify_content": null, "_view_module": "@jupyter-widgets/base", "overflow": null, "_model_module_version": "1.2.0", "_view_count": null, "flex_flow": null, "width": null, "min_width": null, "border": null, "align_items": null, "bottom": null, "_model_module": "@jupyter-widgets/base", "top": null, "grid_column": null, "overflow_y": null, "overflow_x": null, "grid_auto_flow": null, "grid_area": null, "grid_template_columns": null, "flex": null, "_model_name": "LayoutModel", "justify_items": null, "grid_row": null, "max_height": null, "align_content": null, "visibility": null, "align_self": null, "height": null, "min_height": null, "padding": null, "grid_auto_rows": null, "grid_gap": null, "max_width": null, "order": null, "_view_module_version": "1.2.0", "grid_template_areas": null, "object_position": null, "object_fit": null, "grid_auto_columns": null, "margin": null, "display": null, "left": null } }, "1066f1d5b6104a3dae19f26269745bd0": { "model_module": "@jupyter-widgets/controls", "model_name": "DescriptionStyleModel", "model_module_version": "1.5.0", "state": { "_view_name": "StyleView", "_model_name": "DescriptionStyleModel", "description_width": "", "_view_module": "@jupyter-widgets/base", "_model_module_version": "1.5.0", "_view_count": null, "_view_module_version": "1.2.0", "_model_module": "@jupyter-widgets/controls" } }, "dd3a70e1ef4547ec8d3463749ce06285": { "model_module": "@jupyter-widgets/base", "model_name": "LayoutModel", "model_module_version": "1.2.0", "state": { "_view_name": "LayoutView", "grid_template_rows": null, "right": null, "justify_content": null, "_view_module": "@jupyter-widgets/base", "overflow": null, "_model_module_version": "1.2.0", "_view_count": null, "flex_flow": null, "width": null, "min_width": null, "border": null, "align_items": null, "bottom": null, "_model_module": "@jupyter-widgets/base", "top": null, "grid_column": null, "overflow_y": null, "overflow_x": null, "grid_auto_flow": null, "grid_area": null, "grid_template_columns": null, "flex": null, "_model_name": "LayoutModel", "justify_items": null, "grid_row": null, "max_height": null, "align_content": null, "visibility": null, "align_self": null, "height": null, "min_height": null, "padding": null, "grid_auto_rows": null, "grid_gap": null, "max_width": null, "order": null, "_view_module_version": "1.2.0", "grid_template_areas": null, "object_position": null, "object_fit": null, "grid_auto_columns": null, "margin": null, "display": null, "left": null } } } } }, "cells": [ { "cell_type": "markdown", "metadata": { "id": "view-in-github", "colab_type": "text" }, "source": [ "\"Open" ] }, { "cell_type": "markdown", "metadata": { "id": "t6MPjfT5NrKQ" }, "source": [ "\n", "\n", "\n", "This is the **official YOLOv3 🚀 notebook** by **Ultralytics**, and is freely available for redistribution under the [GPL-3.0 license](https://choosealicense.com/licenses/gpl-3.0/). \n", "For more information please visit https://github.com/ultralytics/yolov3 and https://ultralytics.com. Thank you!" ] }, { "cell_type": "markdown", "metadata": { "id": "7mGmQbAO5pQb" }, "source": [ "# Setup\n", "\n", "Clone repo, install dependencies and check PyTorch and GPU." ] }, { "cell_type": "code", "metadata": { "id": "wbvMlHd_QwMG", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "141002fc-fe49-48d2-a575-2555bf903413" }, "source": [ "!git clone https://github.com/ultralytics/yolov3 # clone\n", "%cd yolov3\n", "%pip install -qr requirements.txt # install\n", "\n", "import torch\n", "from yolov3 import utils\n", "display = utils.notebook_init() # checks" ], "execution_count": 1, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "Setup complete ✅\n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "4JnkELT0cIJg" }, "source": [ "# 1. Inference\n", "\n", "`detect.py` runs YOLOv3 inference on a variety of sources, downloading models automatically from the [latest YOLOv3 release](https://github.com/ultralytics/yolov3/releases), and saving results to `runs/detect`. Example inference sources are:\n", "\n", "```shell\n", "python detect.py --source 0 # webcam\n", " img.jpg # image \n", " vid.mp4 # video\n", " path/ # directory\n", " path/*.jpg # glob\n", " 'https://youtu.be/Zgi9g1ksQHc' # YouTube\n", " 'rtsp://example.com/media.mp4' # RTSP, RTMP, HTTP stream\n", "```" ] }, { "cell_type": "code", "metadata": { "id": "zR9ZbuQCH7FX", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "c29b082a-8e56-4799-b32a-056425f130d1" }, "source": [ "!python detect.py --weights yolov3.pt --img 640 --conf 0.25 --source data/images\n", "# display.Image(filename='runs/detect/exp/zidane.jpg', width=600)" ], "execution_count": 4, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[34m\u001b[1mdetect: \u001b[0mweights=['yolov3.pt'], source=data/images, imgsz=[640, 640], conf_thres=0.25, iou_thres=0.45, max_det=1000, device=, view_img=False, save_txt=False, save_conf=False, save_crop=False, nosave=False, classes=None, agnostic_nms=False, augment=False, visualize=False, update=False, project=runs/detect, name=exp, exist_ok=False, line_thickness=3, hide_labels=False, hide_conf=False, half=False, dnn=False\n", "YOLOv3 🚀 v9.6.0-29-ga441ab1 torch 1.13.0+cu116 CUDA:0 (Tesla T4, 15110MiB)\n", "\n", "Fusing layers... \n", "Model Summary: 261 layers, 61922845 parameters, 0 gradients\n", "image 1/2 /content/yolov3/data/images/bus.jpg: 640x480 4 persons, 1 bicycle, 1 bus, Done. (0.050s)\n", "image 2/2 /content/yolov3/data/images/zidane.jpg: 384x640 2 persons, 2 ties, Done. (0.038s)\n", "Speed: 0.5ms pre-process, 44.3ms inference, 1.3ms NMS per image at shape (1, 3, 640, 640)\n", "Results saved to \u001b[1mruns/detect/exp2\u001b[0m\n" ] } ] }, { "cell_type": "markdown", "metadata": { "id": "hkAzDWJ7cWTr" }, "source": [ "        \n", "" ] }, { "cell_type": "markdown", "metadata": { "id": "0eq1SMWl6Sfn" }, "source": [ "# 2. Validate\n", "Validate a model's accuracy on [COCO](https://cocodataset.org/#home) val or test-dev datasets. Models are downloaded automatically from the [latest YOLOv3 release](https://github.com/ultralytics/yolov3/releases). To show results by class use the `--verbose` flag. Note that `pycocotools` metrics may be ~1% better than the equivalent repo metrics, as is visible below, due to slight differences in mAP computation." ] }, { "cell_type": "markdown", "metadata": { "id": "eyTZYGgRjnMc" }, "source": [ "## COCO val\n", "Download [COCO val 2017](https://github.com/ultralytics/yolov3/blob/master/data/coco.yaml) dataset (1GB - 5000 images), and test model accuracy." ] }, { "cell_type": "code", "metadata": { "id": "WQPtK1QYVaD_", "colab": { "base_uri": "https://localhost:8080/", "height": 48, "referenced_widgets": [ "eeda9d6850e8406f9bbc5b06051b3710", "1e823c45174a4216be7234a6cc5cfd99", "cd8efd6c5de94ea8848a7d5b8766a4d6", "a4ec69c4697c4b0e84e6193be227f63e", "9a5694c133be46df8d2fe809b77c1c35", "d584167143f84a0484006dded3fd2620", "b9a25c0d425c4fe4b8cd51ae6a301b0d", "654525fe1ed34d5fbe1c36ed80ae1c1c", "09544845070e47baafc5e37d45ff23e9", "1066f1d5b6104a3dae19f26269745bd0", "dd3a70e1ef4547ec8d3463749ce06285" ] }, "outputId": "56199bac-5a5e-41eb-8892-bf387a1ec7cb" }, "source": [ "# Download COCO val\n", "torch.hub.download_url_to_file('https://ultralytics.com/assets/coco2017val.zip', 'tmp.zip')\n", "!unzip -q tmp.zip -d ../datasets && rm tmp.zip" ], "execution_count": null, "outputs": [ { "output_type": "display_data", "data": { "application/vnd.jupyter.widget-view+json": { "model_id": "eeda9d6850e8406f9bbc5b06051b3710", "version_minor": 0, "version_major": 2 }, "text/plain": [ " 0%| | 0.00/780M [00:00

\n", "Close the active learning loop by sampling images from your inference conditions with the `roboflow` pip package\n", "

\n", "\n", "Train a YOLOv3 model on the [COCO128](https://www.kaggle.com/ultralytics/coco128) dataset with `--data coco128.yaml`, starting from pretrained `--weights yolov3.pt`, or from randomly initialized `--weights '' --cfg yolov3yaml`.\n", "\n", "- **Pretrained [Models](https://github.com/ultralytics/yolov3/tree/master/models)** are downloaded\n", "automatically from the [latest YOLOv3 release](https://github.com/ultralytics/yolov3/releases)\n", "- **[Datasets](https://github.com/ultralytics/yolov3/tree/master/data)** available for autodownload include: [COCO](https://github.com/ultralytics/yolov3/blob/master/data/coco.yaml), [COCO128](https://github.com/ultralytics/yolov3/blob/master/data/coco128.yaml), [VOC](https://github.com/ultralytics/yolov3/blob/master/data/VOC.yaml), [Argoverse](https://github.com/ultralytics/yolov3/blob/master/data/Argoverse.yaml), [VisDrone](https://github.com/ultralytics/yolov3/blob/master/data/VisDrone.yaml), [GlobalWheat](https://github.com/ultralytics/yolov3/blob/master/data/GlobalWheat2020.yaml), [xView](https://github.com/ultralytics/yolov3/blob/master/data/xView.yaml), [Objects365](https://github.com/ultralytics/yolov3/blob/master/data/Objects365.yaml), [SKU-110K](https://github.com/ultralytics/yolov3/blob/master/data/SKU-110K.yaml).\n", "- **Training Results** are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc.\n", "

\n" ] }, { "cell_type": "code", "metadata": { "id": "bOy5KI2ncnWd" }, "source": [ "# Tensorboard (optional)\n", "%load_ext tensorboard\n", "%tensorboard --logdir runs/train" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "1NcFxRcFdJ_O", "colab": { "base_uri": "https://localhost:8080/" }, "outputId": "c77013e3-347d-42a4-84de-3ca42ea3aee9" }, "source": [ "# Train YOLOv3 on COCO128 for 3 epochs\n", "!python train.py --img 640 --batch 16 --epochs 3 --data coco128.yaml --weights yolov3.pt --cache" ], "execution_count": 3, "outputs": [ { "output_type": "stream", "name": "stdout", "text": [ "\u001b[34m\u001b[1mtrain: \u001b[0mweights=yolov3.pt, cfg=, data=coco128.yaml, hyp=data/hyps/hyp.scratch.yaml, epochs=3, batch_size=16, imgsz=640, rect=False, resume=False, nosave=False, noval=False, noautoanchor=False, evolve=None, bucket=, cache=ram, image_weights=False, device=, multi_scale=False, single_cls=False, adam=False, sync_bn=False, workers=8, project=runs/train, name=exp, exist_ok=False, quad=False, linear_lr=False, label_smoothing=0.0, patience=100, freeze=0, save_period=-1, local_rank=-1, entity=None, upload_dataset=False, bbox_interval=-1, artifact_alias=latest\n", "\u001b[34m\u001b[1mgithub: \u001b[0mup to date with https://github.com/ultralytics/yolov3 ✅\n", "YOLOv3 🚀 v9.6.0-29-ga441ab1 torch 1.13.0+cu116 CUDA:0 (Tesla T4, 15110MiB)\n", "\n", "\u001b[34m\u001b[1mhyperparameters: \u001b[0mlr0=0.01, lrf=0.1, 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, copy_paste=0.0\n", "\u001b[34m\u001b[1mWeights & Biases: \u001b[0mrun 'pip install wandb' to automatically track and visualize YOLOv3 🚀 runs (RECOMMENDED)\n", "\u001b[34m\u001b[1mTensorBoard: \u001b[0mStart with 'tensorboard --logdir runs/train', view at http://localhost:6006/\n", "\n", "WARNING: Dataset not found, nonexistent paths: ['/content/datasets/coco128/images/train2017']\n", "Downloading https://ultralytics.com/assets/coco128.zip to coco128.zip...\n", "100% 6.66M/6.66M [00:00<00:00, 10.2MB/s]\n", "Dataset autodownload success, saved to ../datasets\n", "\n", "\n", " from n params module arguments \n", " 0 -1 1 928 models.common.Conv [3, 32, 3, 1] \n", " 1 -1 1 18560 models.common.Conv [32, 64, 3, 2] \n", " 2 -1 1 20672 models.common.Bottleneck [64, 64] \n", " 3 -1 1 73984 models.common.Conv [64, 128, 3, 2] \n", " 4 -1 2 164608 models.common.Bottleneck [128, 128] \n", " 5 -1 1 295424 models.common.Conv [128, 256, 3, 2] \n", " 6 -1 8 2627584 models.common.Bottleneck [256, 256] \n", " 7 -1 1 1180672 models.common.Conv [256, 512, 3, 2] \n", " 8 -1 8 10498048 models.common.Bottleneck [512, 512] \n", " 9 -1 1 4720640 models.common.Conv [512, 1024, 3, 2] \n", " 10 -1 4 20983808 models.common.Bottleneck [1024, 1024] \n", " 11 -1 1 5245952 models.common.Bottleneck [1024, 1024, False] \n", " 12 -1 1 525312 models.common.Conv [1024, 512, 1, 1] \n", " 13 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n", " 14 -1 1 525312 models.common.Conv [1024, 512, 1, 1] \n", " 15 -1 1 4720640 models.common.Conv [512, 1024, 3, 1] \n", " 16 -2 1 131584 models.common.Conv [512, 256, 1, 1] \n", " 17 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", " 18 [-1, 8] 1 0 models.common.Concat [1] \n", " 19 -1 1 1377792 models.common.Bottleneck [768, 512, False] \n", " 20 -1 1 1312256 models.common.Bottleneck [512, 512, False] \n", " 21 -1 1 131584 models.common.Conv [512, 256, 1, 1] \n", " 22 -1 1 1180672 models.common.Conv [256, 512, 3, 1] \n", " 23 -2 1 33024 models.common.Conv [256, 128, 1, 1] \n", " 24 -1 1 0 torch.nn.modules.upsampling.Upsample [None, 2, 'nearest'] \n", " 25 [-1, 6] 1 0 models.common.Concat [1] \n", " 26 -1 1 344832 models.common.Bottleneck [384, 256, False] \n", " 27 -1 2 656896 models.common.Bottleneck [256, 256, False] \n", " 28 [27, 22, 15] 1 457725 models.yolo.Detect [80, [[10, 13, 16, 30, 33, 23], [30, 61, 62, 45, 59, 119], [116, 90, 156, 198, 373, 326]], [256, 512, 1024]]\n", "Model Summary: 333 layers, 61949149 parameters, 61949149 gradients, 156.6 GFLOPs\n", "\n", "Transferred 439/439 items from yolov3.pt\n", "Scaled weight_decay = 0.0005\n", "\u001b[34m\u001b[1moptimizer:\u001b[0m SGD with parameter groups 72 weight, 75 weight (no decay), 75 bias\n", "\u001b[34m\u001b[1malbumentations: \u001b[0mBlur(always_apply=False, p=0.01, blur_limit=(3, 7)), MedianBlur(always_apply=False, p=0.01, blur_limit=(3, 7)), ToGray(always_apply=False, p=0.01), CLAHE(always_apply=False, p=0.01, clip_limit=(1, 4.0), tile_grid_size=(8, 8))\n", "\u001b[34m\u001b[1mtrain: \u001b[0mScanning '../datasets/coco128/labels/train2017' images and labels...126 found, 2 missing, 0 empty, 0 corrupted: 100% 128/128 [00:00<00:00, 1542.80it/s]\n", "\u001b[34m\u001b[1mtrain: \u001b[0mNew cache created: ../datasets/coco128/labels/train2017.cache\n", "\u001b[34m\u001b[1mtrain: \u001b[0mCaching images (0.1GB ram): 100% 128/128 [00:00<00:00, 327.35it/s]\n", "\u001b[34m\u001b[1mval: \u001b[0mScanning '../datasets/coco128/labels/train2017.cache' images and labels... 126 found, 2 missing, 0 empty, 0 corrupted: 100% 128/128 [00:00 \n", "`train_batch0.jpg` shows train batch 0 mosaics and labels\n", "\n", "> \n", "`test_batch0_labels.jpg` shows val batch 0 labels\n", "\n", "> \n", "`test_batch0_pred.jpg` shows val batch 0 _predictions_\n", "\n", "Training results are automatically logged to [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) as `results.csv`, which is plotted as `results.png` (below) after training completes. You can also plot any `results.csv` file manually:\n", "\n", "```python\n", "from utils.plots import plot_results \n", "plot_results('path/to/results.csv') # plot 'results.csv' as 'results.png'\n", "```\n", "\n", "\"COCO128" ] }, { "cell_type": "markdown", "metadata": { "id": "Zelyeqbyt3GD" }, "source": [ "# Environments\n", "\n", "YOLOv3 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: \"Open \"Open\n", "- **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/GCP-Quickstart)\n", "- **Amazon** Deep Learning AMI. See [AWS Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/AWS-Quickstart)\n", "- **Docker Image**. See [Docker Quickstart Guide](https://github.com/ultralytics/yolov3/wiki/Docker-Quickstart) \"Docker\n" ] }, { "cell_type": "markdown", "metadata": { "id": "6Qu7Iesl0p54" }, "source": [ "# Status\n", "\n", "![CI CPU testing](https://github.com/ultralytics/yolov3/workflows/CI%20CPU%20testing/badge.svg)\n", "\n", "If this badge is green, all [YOLOv3 GitHub Actions](https://github.com/ultralytics/yolov3/actions) Continuous Integration (CI) tests are currently passing. CI tests verify correct operation of YOLOv3 training ([train.py](https://github.com/ultralytics/yolov3/blob/master/train.py)), testing ([val.py](https://github.com/ultralytics/yolov3/blob/master/val.py)), inference ([detect.py](https://github.com/ultralytics/yolov3/blob/master/detect.py)) and export ([export.py](https://github.com/ultralytics/yolov3/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", "Optional extras below. Unit tests validate repo functionality and should be run on any PRs submitted.\n" ] }, { "cell_type": "code", "metadata": { "id": "mcKoSIK2WSzj" }, "source": [ "# Reproduce\n", "for x in 'yolov3', 'yolov3-spp', 'yolov3-tiny':\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": "GMusP4OAxFu6" }, "source": [ "# PyTorch Hub\n", "import torch\n", "\n", "# Model\n", "model = torch.hub.load('ultralytics/yolov3', 'yolov3')\n", "\n", "# Images\n", "dir = 'https://ultralytics.com/images/'\n", "imgs = [dir + f for f in ('zidane.jpg', 'bus.jpg')] # batch of images\n", "\n", "# Inference\n", "results = model(imgs)\n", "results.print() # or .show(), .save()" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "FGH0ZjkGjejy" }, "source": [ "# CI Checks\n", "%%shell\n", "export PYTHONPATH=\"$PWD\" # to run *.py. files in subdirectories\n", "rm -rf runs # remove runs/\n", "for m in yolov3-tiny; do # models\n", " python train.py --img 64 --batch 32 --weights $m.pt --epochs 1 --device 0 # train pretrained\n", " python train.py --img 64 --batch 32 --weights '' --cfg $m.yaml --epochs 1 --device 0 # train scratch\n", " for d in 0 cpu; do # devices\n", " python val.py --weights $m.pt --device $d # val official\n", " python val.py --weights runs/train/exp/weights/best.pt --device $d # val custom\n", " python detect.py --weights $m.pt --device $d # detect official\n", " python detect.py --weights runs/train/exp/weights/best.pt --device $d # detect custom\n", " done\n", " python hubconf.py # hub\n", " python models/yolo.py --cfg $m.yaml # build PyTorch model\n", " python models/tf.py --weights $m.pt # build TensorFlow model\n", " python export.py --img 64 --batch 1 --weights $m.pt --include torchscript onnx # export\n", "done" ], "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": "RVRSOhEvUdb5" }, "source": [ "# Evolve\n", "!python train.py --img 640 --batch 64 --epochs 100 --data coco128.yaml --weights yolov3.pt --cache --noautoanchor --evolve\n", "!d=runs/train/evolve && cp evolve.* $d && zip -r evolve.zip $d && gsutil mv evolve.zip gs://bucket # upload results (optional)" ], "execution_count": null, "outputs": [] }, { "cell_type": "code", "metadata": { "id": "BSgFCAcMbk1R" }, "source": [ "# VOC\n", "for b, m in zip([24, 24, 64], ['yolov3', 'yolov3-spp', 'yolov3-tiny']): # zip(batch_size, model)\n", " !python train.py --batch {b} --weights {m}.pt --data VOC.yaml --epochs 50 --cache --img 512 --nosave --hyp hyp.finetune.yaml --project VOC --name {m}" ], "execution_count": null, "outputs": [] } ] }