Merge branch 'ultralytics:master' into master

.github/workflows/ci-testing.yml

@@ -68,11 +68,11 @@ jobs:
  - name: Install requirements
  run: |
  python -m pip install --upgrade pip wheel
+ torch=""
  if [ "${{ matrix.torch }}" == "1.8.0" ]; then
- pip install -r requirements.txt torch==1.8.0 torchvision==0.9.0 --extra-index-url https://download.pytorch.org/whl/cpu
- else
- pip install -r requirements.txt --extra-index-url https://download.pytorch.org/whl/cpu
+ torch="torch==1.8.0 torchvision==0.9.0"
  fi
+ pip install -r requirements.txt $torch --extra-index-url https://download.pytorch.org/whl/cpu
  shell: bash # for Windows compatibility
  - name: Check environment
  run: |

.github/workflows/cla.yml

@@ -20,7 +20,7 @@ jobs:
  steps:
  - name: CLA Assistant
  if: (github.event.comment.body == 'recheck' || github.event.comment.body == 'I have read the CLA Document and I sign the CLA') || github.event_name == 'pull_request_target'
- uses: contributor-assistant/github-action@v2.3.2
+ uses: contributor-assistant/github-action@v2.4.0
  env:
  GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
  # must be repository secret token

.github/workflows/format.yml

@@ -19,7 +19,8 @@ jobs:
  with:
  token: ${{ secrets.GITHUB_TOKEN }} # automatically generated, do not modify
  python: true # format Python code and docstrings
- markdown: true # format Markdown and YAML
+ markdown: true # format Markdown
+ prettier: true # format YAML
  spelling: true # check spelling
  links: false # check broken links
  summary: true # print PR summary with GPT4 (requires 'openai_api_key' or 'openai_azure_api_key' and 'openai_azure_endpoint')

README.md

@@ -108,7 +108,7 @@ To request an Enterprise License please complete the form at [Ultralytics Licens
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
  <a href="https://twitter.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width="2%" alt="Ultralytics Twitter"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
- <a href="https://youtube.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="2%" alt="Ultralytics YouTube"></a>
+ <a href="https://youtube.com/ultralytics?sub_confirmation=1"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="2%" alt="Ultralytics YouTube"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
  <a href="https://www.tiktok.com/@ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-tiktok.png" width="2%" alt="Ultralytics TikTok"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
@@ -468,9 +468,7 @@ python classify/predict.py --weights yolov5s-cls.pt --source data/images/bus.jpg
 ```
 
 ```python
-model = torch.hub.load(
- "ultralytics/yolov5", "custom", "yolov5s-cls.pt"
-) # load from PyTorch Hub
+model = torch.hub.load("ultralytics/yolov5", "custom", "yolov5s-cls.pt") # load from PyTorch Hub
 ```
 
 ### Export
@@ -535,7 +533,7 @@ For YOLOv5 bug reports and feature requests please visit [GitHub Issues](https:/
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
  <a href="https://twitter.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width="3%" alt="Ultralytics Twitter"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
- <a href="https://youtube.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="3%" alt="Ultralytics YouTube"></a>
+ <a href="https://youtube.com/ultralytics?sub_confirmation=1"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="3%" alt="Ultralytics YouTube"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
  <a href="https://www.tiktok.com/@ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-tiktok.png" width="3%" alt="Ultralytics TikTok"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">

README.zh-CN.md

@@ -34,7 +34,7 @@ YOLOv5 🚀 是世界上最受欢迎的视觉 AI，代表<a href="https://ultral
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
  <a href="https://twitter.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width="2%" alt="Ultralytics Twitter"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
- <a href="https://youtube.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="2%" alt="Ultralytics YouTube"></a>
+ <a href="https://youtube.com/ultralytics?sub_confirmation=1"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="2%" alt="Ultralytics YouTube"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
  <a href="https://www.tiktok.com/@ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-tiktok.png" width="2%" alt="Ultralytics TikTok"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="2%">
@@ -394,9 +394,7 @@ python classify/predict.py --weights yolov5s-cls.pt --source data/images/bus.jpg
 ```
 
 ```python
-model = torch.hub.load(
- "ultralytics/yolov5", "custom", "yolov5s-cls.pt"
-) # load from PyTorch Hub
+model = torch.hub.load("ultralytics/yolov5", "custom", "yolov5s-cls.pt") # load from PyTorch Hub
 ```
 
 ### 模型导出
@@ -461,7 +459,7 @@ Ultralytics 提供两种许可证选项以适应各种使用场景：
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
  <a href="https://twitter.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-twitter.png" width="3%" alt="Ultralytics Twitter"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
- <a href="https://youtube.com/ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="3%" alt="Ultralytics YouTube"></a>
+ <a href="https://youtube.com/ultralytics?sub_confirmation=1"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-youtube.png" width="3%" alt="Ultralytics YouTube"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">
  <a href="https://www.tiktok.com/@ultralytics"><img src="https://github.com/ultralytics/assets/raw/main/social/logo-social-tiktok.png" width="3%" alt="Ultralytics TikTok"></a>
  <img src="https://github.com/ultralytics/assets/raw/main/social/logo-transparent.png" width="3%">

requirements.txt

@@ -9,7 +9,7 @@ opencv-python>=4.1.1
 pillow>=10.3.0
 psutil # system resources
 PyYAML>=5.3.1
-requests>=2.23.0
+requests>=2.32.0
 scipy>=1.4.1
 thop>=0.1.1 # FLOPs computation
 torch>=1.8.0 # see https://pytorch.org/get-started/locally (recommended)

segment/train.py

@@ -746,7 +746,7 @@ def run(**kwargs):
  """
  Executes YOLOv5 training with given parameters, altering options programmatically; returns updated options.
 
- Example: mport train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
+ Example: import train; train.run(data='coco128.yaml', imgsz=320, weights='yolov5m.pt')
  """
  opt = parse_opt(True)
  for k, v in kwargs.items():

utils/augmentations.py

@@ -455,7 +455,7 @@ def classify_albumentations(
  if vflip > 0:
  T += [A.VerticalFlip(p=vflip)]
  if jitter > 0:
- color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, satuaration, 0 hue
+ color_jitter = (float(jitter),) * 3 # repeat value for brightness, contrast, saturation, 0 hue
  T += [A.ColorJitter(*color_jitter, 0)]
  else: # Use fixed crop for eval set (reproducibility)
  T = [A.SmallestMaxSize(max_size=size), A.CenterCrop(height=size, width=size)]

utils/dataloaders.py

@@ -137,7 +137,7 @@ def __iter__(self):
  g = torch.Generator()
  g.manual_seed(self.seed + self.epoch)
 
- # determine the the eventual size (n) of self.indices (DDP indices)
+ # determine the eventual size (n) of self.indices (DDP indices)
  n = int((len(self.dataset) - self.rank - 1) / self.num_replicas) + 1 # num_replicas == WORLD_SIZE
  idx = torch.randperm(n, generator=g)
  if not self.shuffle:

utils/general.py

@@ -68,6 +68,8 @@
 os.environ["NUMEXPR_MAX_THREADS"] = str(NUM_THREADS) # NumExpr max threads
 os.environ["OMP_NUM_THREADS"] = "1" if platform.system() == "darwin" else str(NUM_THREADS) # OpenMP (PyTorch and SciPy)
 os.environ["TF_CPP_MIN_LOG_LEVEL"] = "2" # suppress verbose TF compiler warnings in Colab
+os.environ["TORCH_CPP_LOG_LEVEL"] = "ERROR" # suppress "NNPACK.cpp could not initialize NNPACK" warnings
+os.environ["KINETO_LOG_LEVEL"] = "5" # suppress verbose PyTorch profiler output when computing FLOPs
 
 
 def is_ascii(s=""):

utils/loggers/clearml/hpo.py

@@ -58,7 +58,7 @@
  # now we decide if we want to maximize it or minimize it (accuracy we maximize)
  objective_metric_sign="max",
  # let us limit the number of concurrent experiments,
- # this in turn will make sure we do dont bombard the scheduler with experiments.
+ # this in turn will make sure we don't bombard the scheduler with experiments.
  # if we have an auto-scaler connected, this, by proxy, will limit the number of machine
  max_number_of_concurrent_tasks=1,
  # this is the optimizer class (actually doing the optimization)

utils/torch_utils.py

@@ -79,11 +79,11 @@ def reshape_classifier_output(model, n=1000):
  elif isinstance(m, nn.Sequential):
  types = [type(x) for x in m]
  if nn.Linear in types:
- i = types.index(nn.Linear) # nn.Linear index
+ i = len(types) - 1 - types[::-1].index(nn.Linear) # last nn.Linear index
  if m[i].out_features != n:
  m[i] = nn.Linear(m[i].in_features, n)
  elif nn.Conv2d in types:
- i = types.index(nn.Conv2d) # nn.Conv2d index
+ i = len(types) - 1 - types[::-1].index(nn.Conv2d) # last nn.Conv2d index
  if m[i].out_channels != n:
  m[i] = nn.Conv2d(m[i].in_channels, n, m[i].kernel_size, m[i].stride, bias=m[i].bias is not None)