Merge branch 'ultralytics:master' into trtNMS

Author: triple-Mu

.github/README_cn.md

@@ -0,0 +1,26 @@
+# YOLOv5 🚀 by Ultralytics, GPL-3.0 license
+# README translation action to translate README.md to Chinese as README.zh-CN.md on any change to README.md
+
+name: Translate README
+
+on:
+  push:
+    branches:
+      - translate_readme  # replace with 'master' to enable action
+    paths:
+      - README.md
+
+jobs:
+  Translate:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v3
+      - name: Setup Node.js
+        uses: actions/setup-node@v3
+        with:
+          node-version: 16
+      # ISO Langusge Codes: https://cloud.google.com/translate/docs/languages
+      - name: Adding README - Chinese Simplified
+        uses: dephraiim/translate-readme@main
+        with:
+          LANG: zh-CN

.github/workflows/translate-readme.yml

@@ -13,7 +13,7 @@ ci:
 
 repos:
   - repo: https://github.com/pre-commit/pre-commit-hooks
-    rev: v4.3.0
+    rev: v4.4.0
     hooks:
       # - id: end-of-file-fixer
       - id: trailing-whitespace
@@ -24,7 +24,7 @@ repos:
       - id: check-docstring-first
 
   - repo: https://github.com/asottile/pyupgrade
-    rev: v3.2.0
+    rev: v3.3.0
     hooks:
       - id: pyupgrade
         name: Upgrade code
@@ -50,15 +50,15 @@ repos:
         additional_dependencies:
           - mdformat-gfm
           - mdformat-black
-        exclude: "README.md|README_cn.md"
+        exclude: "README.md|README.zh-CN.md"
 
   - repo: https://github.com/asottile/yesqa
     rev: v1.4.0
     hooks:
       - id: yesqa
 
   - repo: https://github.com/PyCQA/flake8
-    rev: 5.0.4
+    rev: 6.0.0
     hooks:
       - id: flake8
         name: PEP8

.pre-commit-config.yaml

@@ -0,0 +1,14 @@
+cff-version: 1.2.0
+preferred-citation:
+  type: software
+  message: If you use YOLOv5, please cite it as below.
+  authors:
+  - family-names: Jocher
+    given-names: Glenn
+    orcid: "https://orcid.org/0000-0001-5950-6979"
+  title: "YOLOv5 by Ultralytics"
+  version: 7.0
+  doi: 10.5281/zenodo.3908559
+  date-released: 2020-5-29
+  license: GPL-3.0
+  url: "https://github.com/ultralytics/yolov5"

CITATION.cff

@@ -8,6 +8,8 @@
                                                                    vid.mp4                         # video
                                                                    screen                          # screenshot
                                                                    path/                           # directory
+                                                                   list.txt                        # list of images
+                                                                   list.streams                    # list of streams
                                                                    'path/*.jpg'                    # glob
                                                                    'https://youtu.be/Zgi9g1ksQHc'  # YouTube
                                                                    'rtsp://example.com/media.mp4'  # RTSP, RTMP, HTTP stream
@@ -74,7 +76,7 @@ def run(
     save_img = not nosave and not source.endswith('.txt')  # save inference images
     is_file = Path(source).suffix[1:] in (IMG_FORMATS + VID_FORMATS)
     is_url = source.lower().startswith(('rtsp://', 'rtmp://', 'http://', 'https://'))
-    webcam = source.isnumeric() or source.endswith('.txt') or (is_url and not is_file)
+    webcam = source.isnumeric() or source.endswith('.streams') or (is_url and not is_file)
     screenshot = source.lower().startswith('screen')
     if is_url and is_file:
         source = check_file(source)  # download

README.md

@@ -6,7 +6,7 @@
     $ python classify/train.py --model yolov5s-cls.pt --data imagenette160 --epochs 5 --img 224
 
 Usage - Multi-GPU DDP training:
-    $ python -m torch.distributed.run --nproc_per_node 4 --master_port 1 classify/train.py --model yolov5s-cls.pt --data imagenet --epochs 5 --img 224 --device 0,1,2,3
+    $ python -m torch.distributed.run --nproc_per_node 4 --master_port 2022 classify/train.py --model yolov5s-cls.pt --data imagenet --epochs 5 --img 224 --device 0,1,2,3
 
 Datasets:           --data mnist, fashion-mnist, cifar10, cifar100, imagenette, imagewoof, imagenet, or 'path/to/data'
 YOLOv5-cls models:  --model yolov5n-cls.pt, yolov5s-cls.pt, yolov5m-cls.pt, yolov5l-cls.pt, yolov5x-cls.pt

README.zh-CN.md

@@ -9,7 +9,7 @@
         "<div align=\"center\">\n",
         "\n",
         "  <a href=\"https://ultralytics.com/yolov5\" target=\"_blank\">\n",
-        "    <img width=\"1024\", src=\"https://github.com/ultralytics/assets/raw/master/yolov5/v62/splash_readme.png\"></a>\n",
+        "    <img width=\"1024\", src=\"https://raw.githubusercontent.com/ultralytics/assets/master/yolov5/v70/splash.png\"></a>\n",
         "\n",
         "\n",
         "<br>\n",
@@ -36,20 +36,20 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 1,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "wbvMlHd_QwMG",
-        "outputId": "43b2e1b5-78d9-4e1d-8530-ee9779bba160"
+        "outputId": "0806e375-610d-4ec0-c867-763dbb518279"
       },
       "outputs": [
         {
           "output_type": "stream",
           "name": "stderr",
           "text": [
-            "YOLOv5 🚀 v6.2-258-g7fc7ed7 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n"
+            "YOLOv5 🚀 v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n"
           ]
         },
         {
@@ -94,30 +94,30 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 2,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "zR9ZbuQCH7FX",
-        "outputId": "1b610787-7cf7-4c33-aac2-aa50fbb84a94"
+        "outputId": "50504ef7-aa3e-4281-a4e3-d0c7df3c0ffe"
       },
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "\u001b[34m\u001b[1mclassify/predict: \u001b[0mweights=['yolov5s-cls.pt'], source=data/images, data=data/coco128.yaml, imgsz=[224, 224], device=, view_img=False, save_txt=True, nosave=False, augment=False, visualize=False, update=False, project=runs/predict-cls, name=exp, exist_ok=False, half=False, dnn=False, vid_stride=1\n",
-            "YOLOv5 🚀 v6.2-258-g7fc7ed7 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
+            "\u001b[34m\u001b[1mclassify/predict: \u001b[0mweights=['yolov5s-cls.pt'], source=data/images, data=data/coco128.yaml, imgsz=[224, 224], device=, view_img=False, save_txt=False, nosave=False, augment=False, visualize=False, update=False, project=runs/predict-cls, name=exp, exist_ok=False, half=False, dnn=False, vid_stride=1\n",
+            "YOLOv5 🚀 v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
             "\n",
-            "Downloading https://github.com/ultralytics/yolov5/releases/download/v6.2/yolov5s-cls.pt to yolov5s-cls.pt...\n",
-            "100% 10.5M/10.5M [00:03<00:00, 2.94MB/s]\n",
+            "Downloading https://github.com/ultralytics/yolov5/releases/download/v7.0/yolov5s-cls.pt to yolov5s-cls.pt...\n",
+            "100% 10.5M/10.5M [00:00<00:00, 12.3MB/s]\n",
             "\n",
             "Fusing layers... \n",
             "Model summary: 117 layers, 5447688 parameters, 0 gradients, 11.4 GFLOPs\n",
             "image 1/2 /content/yolov5/data/images/bus.jpg: 224x224 minibus 0.39, police van 0.24, amphibious vehicle 0.05, recreational vehicle 0.04, trolleybus 0.03, 3.9ms\n",
-            "image 2/2 /content/yolov5/data/images/zidane.jpg: 224x224 suit 0.38, bow tie 0.19, bridegroom 0.18, rugby ball 0.04, stage 0.02, 4.1ms\n",
-            "Speed: 0.3ms pre-process, 4.0ms inference, 1.5ms NMS per image at shape (1, 3, 224, 224)\n",
+            "image 2/2 /content/yolov5/data/images/zidane.jpg: 224x224 suit 0.38, bow tie 0.19, bridegroom 0.18, rugby ball 0.04, stage 0.02, 4.6ms\n",
+            "Speed: 0.3ms pre-process, 4.3ms inference, 1.5ms NMS per image at shape (1, 3, 224, 224)\n",
             "Results saved to \u001b[1mruns/predict-cls/exp\u001b[0m\n"
           ]
         }
@@ -149,29 +149,29 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 3,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "WQPtK1QYVaD_",
-        "outputId": "92de5f34-cf41-49e7-b679-41db94e995ac"
+        "outputId": "20fc0630-141e-4a90-ea06-342cbd7ce496"
       },
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
-            "--2022-11-18 21:48:38--  https://image-net.org/data/ILSVRC/2012/ILSVRC2012_img_val.tar\n",
+            "--2022-11-22 19:53:40--  https://image-net.org/data/ILSVRC/2012/ILSVRC2012_img_val.tar\n",
             "Resolving image-net.org (image-net.org)... 171.64.68.16\n",
             "Connecting to image-net.org (image-net.org)|171.64.68.16|:443... connected.\n",
             "HTTP request sent, awaiting response... 200 OK\n",
             "Length: 6744924160 (6.3G) [application/x-tar]\n",
             "Saving to: ‘ILSVRC2012_img_val.tar’\n",
             "\n",
-            "ILSVRC2012_img_val. 100%[===================>]   6.28G  7.15MB/s    in 11m 13s \n",
+            "ILSVRC2012_img_val. 100%[===================>]   6.28G  16.1MB/s    in 10m 52s \n",
             "\n",
-            "2022-11-18 21:59:52 (9.55 MB/s) - ‘ILSVRC2012_img_val.tar’ saved [6744924160/6744924160]\n",
+            "2022-11-22 20:04:32 (9.87 MB/s) - ‘ILSVRC2012_img_val.tar’ saved [6744924160/6744924160]\n",
             "\n"
           ]
         }
@@ -183,25 +183,25 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 4,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "X58w8JLpMnjH",
-        "outputId": "9961ad87-d639-4489-b578-0a0578fefaab"
+        "outputId": "41843132-98e2-4c25-d474-4cd7b246fb8e"
       },
       "outputs": [
         {
           "output_type": "stream",
           "name": "stdout",
           "text": [
             "\u001b[34m\u001b[1mclassify/val: \u001b[0mdata=../datasets/imagenet, weights=['yolov5s-cls.pt'], batch_size=128, imgsz=224, device=, workers=8, verbose=True, project=runs/val-cls, name=exp, exist_ok=False, half=True, dnn=False\n",
-            "YOLOv5 🚀 v6.2-258-g7fc7ed7 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
+            "YOLOv5 🚀 v7.0-3-g61ebf5e Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
             "\n",
             "Fusing layers... \n",
             "Model summary: 117 layers, 5447688 parameters, 0 gradients, 11.4 GFLOPs\n",
-            "validating: 100% 391/391 [04:48<00:00,  1.35it/s]\n",
+            "validating: 100% 391/391 [04:57<00:00,  1.31it/s]\n",
             "                   Class      Images    top1_acc    top5_acc\n",
             "                     all       50000       0.715       0.902\n",
             "                   tench          50        0.94        0.98\n",
@@ -1269,45 +1269,47 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 5,
+      "execution_count": null,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/"
         },
         "id": "1NcFxRcFdJ_O",
-        "outputId": "638c55b1-dc45-4eee-cabc-4921dc61faf5"
+        "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=3, batch_size=16, 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[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 ✅\n",
-            "YOLOv5 🚀 v6.2-258-g7fc7ed7 Python-3.7.15 torch-1.12.1+cu113 CUDA:0 (Tesla T4, 15110MiB)\n",
+            "YOLOv5 🚀 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 ⚠️, 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 [00:09<00:00, 11.1MB/s]\n",
+            "100% 103M/103M [00:00<00:00, 347MB/s] \n",
             "Unzipping /content/datasets/imagenette160.zip...\n",
-            "Dataset download success ✅ (13.2s), saved to \u001b[1m/content/datasets/imagenette160\u001b[0m\n",
+            "Dataset download success ✅ (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 3 epochs...\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",
-            "       1/3    0.348G        1.31        1.09       0.794       0.979: 100% 592/592 [01:02<00:00,  9.47it/s]\n",
-            "       2/3    0.415G        1.09       0.852       0.883        0.99: 100% 592/592 [00:59<00:00, 10.00it/s]\n",
-            "       3/3    0.415G       0.954       0.776       0.907       0.994: 100% 592/592 [00:59<00:00,  9.89it/s]\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 (0.051 hours)\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",
@@ -1320,7 +1322,7 @@
       ],
       "source": [
         "# Train YOLOv5s Classification on Imagenette160 for 3 epochs\n",
-        "!python classify/train.py --img 224 --batch 16 --epochs 3 --data imagenette160 --model yolov5s-cls.pt --cache"
+        "!python classify/train.py --model yolov5s-cls.pt --data imagenette160 --epochs 5 --img 224 --cache"
       ]
     },
     {
@@ -1339,19 +1341,20 @@
       },
       "source": [
         "## Comet Logging and Visualization 🌟 NEW\n",
-        "[Comet](https://bit.ly/yolov5-readme-comet) 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://bit.ly/yolov5-colab-comet-panels)! 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",
+        "[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=<Your API Key>  # 2. paste API key\n",
         "python train.py --img 640 --epochs 3 --data coco128.yaml --weights yolov5s.pt  # 3. train\n",
         "```\n",
-        "\n",
-        "To learn more about all of the supported Comet features for this integration, check out the [Comet Tutorial](https://github.com/ultralytics/yolov5/tree/master/utils/loggers/comet). If you'd like to learn more about Comet, head over to our [documentation](https://bit.ly/yolov5-colab-comet-docs). Get started by trying out the Comet Colab Notebook:\n",
+        "To learn more about all of the supported Comet features for this integration, check out the [Comet Tutorial](https://github.com/ultralytics/yolov5/tree/master/utils/loggers/comet). 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",
-        "<img width=\"1920\" alt=\"yolo-ui\" src=\"https://user-images.githubusercontent.com/26833433/202851203-164e94e1-2238-46dd-91f8-de020e9d6b41.png\">"
+        "<a href=\"https://bit.ly/yolov5-readme-comet2\">\n",
+        "<img alt=\"Comet Dashboard\" src=\"https://user-images.githubusercontent.com/26833433/202851203-164e94e1-2238-46dd-91f8-de020e9d6b41.png\" width=\"1280\"/></a>"
       ]
     },
     {
@@ -1474,4 +1477,4 @@
   },
   "nbformat": 4,
   "nbformat_minor": 0
-}
+}