Merge branch 'ultralytics:master' into master

.github/workflows/ci-testing.yml

@@ -155,11 +155,11 @@ jobs:
         run: |
           m=${{ matrix.model }}-cls.pt  # official weights
           b=runs/train-cls/exp/weights/best.pt  # best.pt checkpoint
-          python classify/train.py --imgsz 32 --model $m --data mnist2560 --epochs 1  # train
-          python classify/val.py --imgsz 32 --weights $b --data ../datasets/mnist2560  # val
-          python classify/predict.py --imgsz 32 --weights $b --source ../datasets/mnist2560/test/7/60.png  # predict
+          python classify/train.py --imgsz 32 --model $m --data mnist160 --epochs 1  # train
+          python classify/val.py --imgsz 32 --weights $b --data ../datasets/mnist160  # val
+          python classify/predict.py --imgsz 32 --weights $b --source ../datasets/mnist160/test/7/60.png  # predict
           python classify/predict.py --imgsz 32 --weights $m --source data/images/bus.jpg  # predict
-          python export.py --weights $b --img 64 --imgsz 224 --include torchscript  # export
+          python export.py --weights $b --img 64 --include torchscript  # export
           python - <<EOF
           import torch
           for path in '$m', '$b':

.github/workflows/stale.yml

@@ -9,7 +9,7 @@ jobs:
   stale:
     runs-on: ubuntu-latest
     steps:
-      - uses: actions/stale@v6
+      - uses: actions/stale@v7
         with:
           repo-token: ${{ secrets.GITHUB_TOKEN }}
           stale-issue-message: |

.github/workflows/translate-readme.yml

@@ -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

.pre-commit-config.yaml

@@ -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: v2.37.3
+    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

CITATION.cff

@@ -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"

benchmarks.py

@@ -22,7 +22,7 @@
     $ pip install -U nvidia-tensorrt --index-url https://pypi.ngc.nvidia.com  # TensorRT
 
 Usage:
-    $ python utils/benchmarks.py --weights yolov5s.pt --img 640
+    $ python benchmarks.py --weights yolov5s.pt --img 640
 """
 
 import argparse
@@ -81,10 +81,10 @@ def run(
 
             # Validate
             if model_type == SegmentationModel:
-                result = val_seg(data, w, batch_size, imgsz, plots=False, device=device, task='benchmark', half=half)
+                result = val_seg(data, w, batch_size, imgsz, plots=False, device=device, task='speed', half=half)
                 metric = result[0][7]  # (box(p, r, map50, map), mask(p, r, map50, map), *loss(box, obj, cls))
             else:  # DetectionModel:
-                result = val_det(data, w, batch_size, imgsz, plots=False, device=device, task='benchmark', half=half)
+                result = val_det(data, w, batch_size, imgsz, plots=False, device=device, task='speed', half=half)
                 metric = result[0][3]  # (p, r, map50, map, *loss(box, obj, cls))
             speed = result[2][1]  # times (preprocess, inference, postprocess)
             y.append([name, round(file_size(w), 1), round(metric, 4), round(speed, 2)])  # MB, mAP, t_inference

classify/predict.py

@@ -6,7 +6,10 @@
     $ python classify/predict.py --weights yolov5s-cls.pt --source 0                               # webcam
                                                                    img.jpg                         # image
                                                                    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
@@ -15,7 +18,7 @@
     $ python classify/predict.py --weights yolov5s-cls.pt                 # PyTorch
                                            yolov5s-cls.torchscript        # TorchScript
                                            yolov5s-cls.onnx               # ONNX Runtime or OpenCV DNN with --dnn
-                                           yolov5s-cls.xml                # OpenVINO
+                                           yolov5s-cls_openvino_model     # OpenVINO
                                            yolov5s-cls.engine             # TensorRT
                                            yolov5s-cls.mlmodel            # CoreML (macOS-only)
                                            yolov5s-cls_saved_model        # TensorFlow SavedModel
@@ -73,7 +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
@@ -91,7 +94,7 @@ def run(
     # Dataloader
     bs = 1  # batch_size
     if webcam:
-        view_img = check_imshow()
+        view_img = check_imshow(warn=True)
         dataset = LoadStreams(source, img_size=imgsz, transforms=classify_transforms(imgsz[0]), vid_stride=vid_stride)
         bs = len(dataset)
     elif screenshot:
@@ -196,7 +199,7 @@ def parse_opt():
     parser.add_argument('--imgsz', '--img', '--img-size', nargs='+', type=int, default=[224], help='inference size h,w')
     parser.add_argument('--device', default='', help='cuda device, i.e. 0 or 0,1,2,3 or cpu')
     parser.add_argument('--view-img', action='store_true', help='show results')
-    parser.add_argument('--save-txt', action='store_false', help='save results to *.txt')
+    parser.add_argument('--save-txt', action='store_true', help='save results to *.txt')
     parser.add_argument('--nosave', action='store_true', help='do not save images/videos')
     parser.add_argument('--augment', action='store_true', help='augmented inference')
     parser.add_argument('--visualize', action='store_true', help='visualize features')

classify/train.py

@@ -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
@@ -40,8 +40,8 @@
 from models.experimental import attempt_load
 from models.yolo import ClassificationModel, DetectionModel
 from utils.dataloaders import create_classification_dataloader
-from utils.general import (DATASETS_DIR, LOGGER, WorkingDirectory, check_git_status, check_requirements, colorstr,
-                           download, increment_path, init_seeds, print_args, yaml_save)
+from utils.general import (DATASETS_DIR, LOGGER, TQDM_BAR_FORMAT, WorkingDirectory, check_git_info, check_git_status,
+                           check_requirements, colorstr, download, increment_path, init_seeds, print_args, yaml_save)
 from utils.loggers import GenericLogger
 from utils.plots import imshow_cls
 from utils.torch_utils import (ModelEMA, model_info, reshape_classifier_output, select_device, smart_DDP,
@@ -50,6 +50,7 @@
 LOCAL_RANK = int(os.getenv('LOCAL_RANK', -1))  # https://pytorch.org/docs/stable/elastic/run.html
 RANK = int(os.getenv('RANK', -1))
 WORLD_SIZE = int(os.getenv('WORLD_SIZE', 1))
+GIT_INFO = check_git_info()
 
 
 def train(opt, device):
@@ -174,7 +175,7 @@ def train(opt, device):
             trainloader.sampler.set_epoch(epoch)
         pbar = enumerate(trainloader)
         if RANK in {-1, 0}:
-            pbar = tqdm(enumerate(trainloader), total=len(trainloader), bar_format='{l_bar}{bar:10}{r_bar}{bar:-10b}')
+            pbar = tqdm(enumerate(trainloader), total=len(trainloader), bar_format=TQDM_BAR_FORMAT)
         for i, (images, labels) in pbar:  # progress bar
             images, labels = images.to(device, non_blocking=True), labels.to(device)
 
@@ -237,6 +238,7 @@ def train(opt, device):
                     'updates': ema.updates,
                     'optimizer': None,  # optimizer.state_dict(),
                     'opt': vars(opt),
+                    'git': GIT_INFO,  # {remote, branch, commit} if a git repo
                     'date': datetime.now().isoformat()}
 
                 # Save last, best and delete