Add pre-commit CI actions (#4982)

* define pre-commit

* add CI code

* configure

* apply pre-commit

* fstring

* apply MD

* pre-commit

* Update torch_utils.py

* Update print strings

* notes

* Cleanup code-format.yml

* Update setup.cfg

* Update .pre-commit-config.yaml

Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

.github/workflows/code-format.yml

@@ -0,0 +1,47 @@
+# Run code formatting GitHub Action, can be replaced by this bot: https://github.com/marketplace/pre-commit-ci
+
+name: Code formatting
+
+on: # https://help.github.com/en/actions/reference/events-that-trigger-workflows
+  push:
+    branches: [master]
+  pull_request: {}
+
+jobs:
+  pep8-check-flake8:
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@master
+      - uses: actions/setup-python@v2
+        with:
+          python-version: 3.7
+      - name: Install dependencies
+        run: |
+          pip install flake8
+          pip list
+        shell: bash
+      - name: PEP8
+        run: |
+          flake8 .
+
+  pre-commit-check:
+    runs-on: ubuntu-20.04
+    steps:
+      - uses: actions/checkout@v2
+        # for private repo - first is the checkout step, which needs to use unlimited fetch depth for pushing
+        with:
+          fetch-depth: 0
+      - uses: actions/setup-python@v2
+
+      - name: set PY
+        run: echo "PY=$(python -VV | sha256sum | cut -d' ' -f1)" >> $GITHUB_ENV
+      - uses: actions/cache@v2
+        with:
+          path: ~/.cache/pre-commit
+          key: pre-commit|${{ env.PY }}|${{ hashFiles('.pre-commit-config.yaml') }}
+
+      - uses: pre-commit/action@v2.0.3
+        # this action also provides an additional behaviour when used in private repositories
+        # when configured with a github token, the action will push back fixes to the pull request branch
+        with:
+          token: ${{ secrets.GITHUB_TOKEN }}

.github/workflows/greetings.yml

@@ -57,4 +57,3 @@ jobs:
             <a href="https://github.com/ultralytics/yolov5/actions"><img src="https://github.com/ultralytics/yolov5/workflows/CI%20CPU%20testing/badge.svg" alt="CI CPU testing"></a>
 
             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)), validation ([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.
-            

.gitignore

@@ -20,6 +20,7 @@
 *.data
 *.json
 *.cfg
+!setup.cfg
 !cfg/yolov3*.cfg
 
 storage.googleapis.com

.pre-commit-config.yaml

@@ -0,0 +1,67 @@
+# Define hooks for code formations
+# Will be applied on any updated commit files if a user has installed and linked commit hook
+
+default_language_version:
+  python: python3.8
+
+# Define bot property if installed via https://github.com/marketplace/pre-commit-ci
+ci:
+  autofix_prs: true
+  autoupdate_commit_msg: '[pre-commit.ci] pre-commit suggestions'
+  autoupdate_schedule: quarterly
+  # submodules: true
+
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.0.1
+    hooks:
+      - id: end-of-file-fixer
+      - id: trailing-whitespace
+      - id: check-case-conflict
+      - id: check-yaml
+      - id: check-toml
+      - id: pretty-format-json
+      - id: check-docstring-first
+
+  - repo: https://github.com/asottile/pyupgrade
+    rev: v2.23.1
+    hooks:
+      - id: pyupgrade
+        args: [--py36-plus]
+        name: Upgrade code
+
+  # TODO
+  #- repo: https://github.com/PyCQA/isort
+  #  rev: 5.9.3
+  #  hooks:
+  #    - id: isort
+  #      name: imports
+
+  # TODO
+  #- repo: https://github.com/pre-commit/mirrors-yapf
+  #  rev: v0.31.0
+  #  hooks:
+  #    - id: yapf
+  #      name: formatting
+
+  # TODO
+  #- repo: https://github.com/executablebooks/mdformat
+  #  rev: 0.7.7
+  #  hooks:
+  #    - id: mdformat
+  #      additional_dependencies:
+  #        - mdformat-gfm
+  #        - mdformat-black
+  #        - mdformat_frontmatter
+
+  # TODO
+  #- repo: https://github.com/asottile/yesqa
+  #  rev: v1.2.3
+  #  hooks:
+  #    - id: yesqa
+
+  - repo: https://github.com/PyCQA/flake8
+    rev: 3.9.2
+    hooks:
+      - id: flake8
+        name: PEP8

models/common.py

@@ -79,7 +79,7 @@ class TransformerBlock(nn.Module):
         if c1 != c2:
             self.conv = Conv(c1, c2)
         self.linear = nn.Linear(c2, c2)  # learnable position embedding
-        self.tr = nn.Sequential(*[TransformerLayer(c2, num_heads) for _ in range(num_layers)])
+        self.tr = nn.Sequential(*(TransformerLayer(c2, num_heads) for _ in range(num_layers)))
         self.c2 = c2
 
     def forward(self, x):
@@ -114,7 +114,7 @@ class BottleneckCSP(nn.Module):
         self.cv4 = Conv(2 * c_, c2, 1, 1)
         self.bn = nn.BatchNorm2d(2 * c_)  # applied to cat(cv2, cv3)
         self.act = nn.LeakyReLU(0.1, inplace=True)
-        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
 
     def forward(self, x):
         y1 = self.cv3(self.m(self.cv1(x)))
@@ -130,7 +130,7 @@ class C3(nn.Module):
         self.cv1 = Conv(c1, c_, 1, 1)
         self.cv2 = Conv(c1, c_, 1, 1)
         self.cv3 = Conv(2 * c_, c2, 1)  # act=FReLU(c2)
-        self.m = nn.Sequential(*[Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)])
+        self.m = nn.Sequential(*(Bottleneck(c_, c_, shortcut, g, e=1.0) for _ in range(n)))
         # self.m = nn.Sequential(*[CrossConv(c_, c_, 3, 1, g, 1.0, shortcut) for _ in range(n)])
 
     def forward(self, x):
@@ -158,7 +158,7 @@ class C3Ghost(C3):
     def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5):
         super().__init__(c1, c2, n, shortcut, g, e)
         c_ = int(c2 * e)  # hidden channels
-        self.m = nn.Sequential(*[GhostBottleneck(c_, c_) for _ in range(n)])
+        self.m = nn.Sequential(*(GhostBottleneck(c_, c_) for _ in range(n)))
 
 
 class SPP(nn.Module):
@@ -362,7 +362,7 @@ class Detections:
     def __init__(self, imgs, pred, files, times=None, names=None, shape=None):
         super().__init__()
         d = pred[0].device  # device
-        gn = [torch.tensor([*[im.shape[i] for i in [1, 0, 1, 0]], 1., 1.], device=d) for im in imgs]  # normalizations
+        gn = [torch.tensor([*(im.shape[i] for i in [1, 0, 1, 0]), 1., 1.], device=d) for im in imgs]  # normalizations
         self.imgs = imgs  # list of images as numpy arrays
         self.pred = pred  # list of tensors pred[0] = (xyxy, conf, cls)
         self.names = names  # class names

models/experimental.py

@@ -97,7 +97,6 @@ def attempt_load(weights, map_location=None, inplace=True, fuse=True):
         else:
             model.append(ckpt['ema' if ckpt.get('ema') else 'model'].float().eval())  # without layer fuse
 
-
     # Compatibility updates
     for m in model.modules():
         if type(m) in [nn.Hardswish, nn.LeakyReLU, nn.ReLU, nn.ReLU6, nn.SiLU, Detect, Model]:

models/hub/yolov5-bifpn.yaml

@@ -18,7 +18,7 @@ backbone:
    [-1, 1, Conv, [256, 3, 2]],  # 3-P3/8
    [-1, 9, C3, [256]],
    [-1, 1, Conv, [512, 3, 2]],  # 5-P4/16
-   [-1, 9, C3, [512]]
+   [-1, 9, C3, [512]],
    [-1, 1, Conv, [1024, 3, 2]],  # 7-P5/32
    [-1, 1, SPP, [1024, [5, 9, 13]]],
    [-1, 3, C3, [1024, False]],  # 9

models/tf.py

@@ -40,7 +40,7 @@ LOGGER = logging.getLogger(__name__)
 class TFBN(keras.layers.Layer):
     # TensorFlow BatchNormalization wrapper
     def __init__(self, w=None):
-        super(TFBN, self).__init__()
+        super().__init__()
         self.bn = keras.layers.BatchNormalization(
             beta_initializer=keras.initializers.Constant(w.bias.numpy()),
             gamma_initializer=keras.initializers.Constant(w.weight.numpy()),
@@ -54,7 +54,7 @@ class TFBN(keras.layers.Layer):
 
 class TFPad(keras.layers.Layer):
     def __init__(self, pad):
-        super(TFPad, self).__init__()
+        super().__init__()
         self.pad = tf.constant([[0, 0], [pad, pad], [pad, pad], [0, 0]])
 
     def call(self, inputs):
@@ -65,7 +65,7 @@ class TFConv(keras.layers.Layer):
     # Standard convolution
     def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
         # ch_in, ch_out, weights, kernel, stride, padding, groups
-        super(TFConv, self).__init__()
+        super().__init__()
         assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
         assert isinstance(k, int), "Convolution with multiple kernels are not allowed."
         # TensorFlow convolution padding is inconsistent with PyTorch (e.g. k=3 s=2 'SAME' padding)
@@ -96,7 +96,7 @@ class TFFocus(keras.layers.Layer):
     # Focus wh information into c-space
     def __init__(self, c1, c2, k=1, s=1, p=None, g=1, act=True, w=None):
         # ch_in, ch_out, kernel, stride, padding, groups
-        super(TFFocus, self).__init__()
+        super().__init__()
         self.conv = TFConv(c1 * 4, c2, k, s, p, g, act, w.conv)
 
     def call(self, inputs):  # x(b,w,h,c) -> y(b,w/2,h/2,4c)
@@ -110,7 +110,7 @@ class TFFocus(keras.layers.Layer):
 class TFBottleneck(keras.layers.Layer):
     # Standard bottleneck
     def __init__(self, c1, c2, shortcut=True, g=1, e=0.5, w=None):  # ch_in, ch_out, shortcut, groups, expansion
-        super(TFBottleneck, self).__init__()
+        super().__init__()
         c_ = int(c2 * e)  # hidden channels
         self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
         self.cv2 = TFConv(c_, c2, 3, 1, g=g, w=w.cv2)
@@ -123,7 +123,7 @@ class TFBottleneck(keras.layers.Layer):
 class TFConv2d(keras.layers.Layer):
     # Substitution for PyTorch nn.Conv2D
     def __init__(self, c1, c2, k, s=1, g=1, bias=True, w=None):
-        super(TFConv2d, self).__init__()
+        super().__init__()
         assert g == 1, "TF v2.2 Conv2D does not support 'groups' argument"
         self.conv = keras.layers.Conv2D(
             c2, k, s, 'VALID', use_bias=bias,
@@ -138,7 +138,7 @@ class TFBottleneckCSP(keras.layers.Layer):
     # CSP Bottleneck https://github.com/WongKinYiu/CrossStagePartialNetworks
     def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
         # ch_in, ch_out, number, shortcut, groups, expansion
-        super(TFBottleneckCSP, self).__init__()
+        super().__init__()
         c_ = int(c2 * e)  # hidden channels
         self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
         self.cv2 = TFConv2d(c1, c_, 1, 1, bias=False, w=w.cv2)
@@ -158,7 +158,7 @@ class TFC3(keras.layers.Layer):
     # CSP Bottleneck with 3 convolutions
     def __init__(self, c1, c2, n=1, shortcut=True, g=1, e=0.5, w=None):
         # ch_in, ch_out, number, shortcut, groups, expansion
-        super(TFC3, self).__init__()
+        super().__init__()
         c_ = int(c2 * e)  # hidden channels
         self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
         self.cv2 = TFConv(c1, c_, 1, 1, w=w.cv2)
@@ -172,7 +172,7 @@ class TFC3(keras.layers.Layer):
 class TFSPP(keras.layers.Layer):
     # Spatial pyramid pooling layer used in YOLOv3-SPP
     def __init__(self, c1, c2, k=(5, 9, 13), w=None):
-        super(TFSPP, self).__init__()
+        super().__init__()
         c_ = c1 // 2  # hidden channels
         self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
         self.cv2 = TFConv(c_ * (len(k) + 1), c2, 1, 1, w=w.cv2)
@@ -186,7 +186,7 @@ class TFSPP(keras.layers.Layer):
 class TFSPPF(keras.layers.Layer):
     # Spatial pyramid pooling-Fast layer
     def __init__(self, c1, c2, k=5, w=None):
-        super(TFSPPF, self).__init__()
+        super().__init__()
         c_ = c1 // 2  # hidden channels
         self.cv1 = TFConv(c1, c_, 1, 1, w=w.cv1)
         self.cv2 = TFConv(c_ * 4, c2, 1, 1, w=w.cv2)
@@ -201,7 +201,7 @@ class TFSPPF(keras.layers.Layer):
 
 class TFDetect(keras.layers.Layer):
     def __init__(self, nc=80, anchors=(), ch=(), imgsz=(640, 640), w=None):  # detection layer
-        super(TFDetect, self).__init__()
+        super().__init__()
         self.stride = tf.convert_to_tensor(w.stride.numpy(), dtype=tf.float32)
         self.nc = nc  # number of classes
         self.no = nc + 5  # number of outputs per anchor
@@ -249,7 +249,7 @@ class TFDetect(keras.layers.Layer):
 
 class TFUpsample(keras.layers.Layer):
     def __init__(self, size, scale_factor, mode, w=None):  # warning: all arguments needed including 'w'
-        super(TFUpsample, self).__init__()
+        super().__init__()
         assert scale_factor == 2, "scale_factor must be 2"
         self.upsample = lambda x: tf.image.resize(x, (x.shape[1] * 2, x.shape[2] * 2), method=mode)
         # self.upsample = keras.layers.UpSampling2D(size=scale_factor, interpolation=mode)
@@ -263,7 +263,7 @@ class TFUpsample(keras.layers.Layer):
 
 class TFConcat(keras.layers.Layer):
     def __init__(self, dimension=1, w=None):
-        super(TFConcat, self).__init__()
+        super().__init__()
         assert dimension == 1, "convert only NCHW to NHWC concat"
         self.d = 3
 
@@ -272,7 +272,7 @@ class TFConcat(keras.layers.Layer):
 
 
 def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
-    LOGGER.info('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
+    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
     anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
     na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
     no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
@@ -299,7 +299,7 @@ def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
         elif m is nn.BatchNorm2d:
             args = [ch[f]]
         elif m is Concat:
-            c2 = sum([ch[-1 if x == -1 else x + 1] for x in f])
+            c2 = sum(ch[-1 if x == -1 else x + 1] for x in f)
         elif m is Detect:
             args.append([ch[x + 1] for x in f])
             if isinstance(args[1], int):  # number of anchors
@@ -312,11 +312,11 @@ def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
         m_ = keras.Sequential([tf_m(*args, w=model.model[i][j]) for j in range(n)]) if n > 1 \
             else tf_m(*args, w=model.model[i])  # module
 
-        torch_m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)  # module
+        torch_m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
         t = str(m)[8:-2].replace('__main__.', '')  # module type
-        np = sum([x.numel() for x in torch_m_.parameters()])  # number params
+        np = sum(x.numel() for x in torch_m_.parameters())  # number params
         m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
-        LOGGER.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n, np, t, args))  # print
+        LOGGER.info(f'{i:>3}{str(f):>18}{str(n):>3}{np:>10}  {t:<40}{str(args):<30}')  # print
         save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
         layers.append(m_)
         ch.append(c2)
@@ -325,7 +325,7 @@ def parse_model(d, ch, model, imgsz):  # model_dict, input_channels(3)
 
 class TFModel:
     def __init__(self, cfg='yolov5s.yaml', ch=3, nc=None, model=None, imgsz=(640, 640)):  # model, channels, classes
-        super(TFModel, self).__init__()
+        super().__init__()
         if isinstance(cfg, dict):
             self.yaml = cfg  # model dict
         else:  # is *.yaml
@@ -336,7 +336,7 @@ class TFModel:
 
         # Define model
         if nc and nc != self.yaml['nc']:
-            print('Overriding %s nc=%g with nc=%g' % (cfg, self.yaml['nc'], nc))
+            print(f"Overriding {cfg} nc={self.yaml['nc']} with nc={nc}")
             self.yaml['nc'] = nc  # override yaml value
         self.model, self.savelist = parse_model(deepcopy(self.yaml), ch=[ch], model=model, imgsz=imgsz)
 

models/yolo.py

@@ -247,7 +247,7 @@ class Model(nn.Module):
 
 
 def parse_model(d, ch):  # model_dict, input_channels(3)
-    LOGGER.info('\n%3s%18s%3s%10s  %-40s%-30s' % ('', 'from', 'n', 'params', 'module', 'arguments'))
+    LOGGER.info(f"\n{'':>3}{'from':>18}{'n':>3}{'params':>10}  {'module':<40}{'arguments':<30}")
     anchors, nc, gd, gw = d['anchors'], d['nc'], d['depth_multiple'], d['width_multiple']
     na = (len(anchors[0]) // 2) if isinstance(anchors, list) else anchors  # number of anchors
     no = na * (nc + 5)  # number of outputs = anchors * (classes + 5)
@@ -275,7 +275,7 @@ def parse_model(d, ch):  # model_dict, input_channels(3)
         elif m is nn.BatchNorm2d:
             args = [ch[f]]
         elif m is Concat:
-            c2 = sum([ch[x] for x in f])
+            c2 = sum(ch[x] for x in f)
         elif m is Detect:
             args.append([ch[x] for x in f])
             if isinstance(args[1], int):  # number of anchors
@@ -287,11 +287,11 @@ def parse_model(d, ch):  # model_dict, input_channels(3)
         else:
             c2 = ch[f]
 
-        m_ = nn.Sequential(*[m(*args) for _ in range(n)]) if n > 1 else m(*args)  # module
+        m_ = nn.Sequential(*(m(*args) for _ in range(n))) if n > 1 else m(*args)  # module
         t = str(m)[8:-2].replace('__main__.', '')  # module type
-        np = sum([x.numel() for x in m_.parameters()])  # number params
+        np = sum(x.numel() for x in m_.parameters())  # number params
         m_.i, m_.f, m_.type, m_.np = i, f, t, np  # attach index, 'from' index, type, number params
-        LOGGER.info('%3s%18s%3s%10.0f  %-40s%-30s' % (i, f, n_, np, t, args))  # print
+        LOGGER.info(f'{i:>3}{str(f):>18}{n_:>3}{np:10.0f}  {t:<40}{str(args):<30}')  # print
         save.extend(x % i for x in ([f] if isinstance(f, int) else f) if x != -1)  # append to savelist
         layers.append(m_)
         if i == 0:

setup.cfg

@@ -0,0 +1,45 @@
+# Project-wide configuration file, can be used for package metadata and other toll configurations
+# Example usage: global configuration for PEP8 (via flake8) setting or default pytest arguments
+
+[metadata]
+license_file = LICENSE
+description-file = README.md
+
+
+[tool:pytest]
+norecursedirs =
+    .git
+    dist
+    build
+addopts =
+    --doctest-modules
+    --durations=25
+    --color=yes
+
+
+[flake8]
+max-line-length = 120
+exclude = .tox,*.egg,build,temp
+select = E,W,F
+doctests = True
+verbose = 2
+# https://pep8.readthedocs.io/en/latest/intro.html#error-codes
+format = pylint
+# see: https://www.flake8rules.com/
+ignore =
+    E731  # Do not assign a lambda expression, use a def
+    F405
+    E402
+    F841
+    E741
+    F821
+    E722
+    F401
+    W504
+    E127
+    W504
+    E231
+    E501
+    F403
+    E302
+    F541

utils/datasets.py

@@ -140,7 +140,7 @@ class InfiniteDataLoader(torch.utils.data.dataloader.DataLoader):
             yield next(self.iterator)
 
 
-class _RepeatSampler(object):
+class _RepeatSampler:
     """ Sampler that repeats forever
 
     Args:
@@ -287,7 +287,7 @@ class LoadStreams:
         self.stride = stride
 
         if os.path.isfile(sources):
-            with open(sources, 'r') as f:
+            with open(sources) as f:
                 sources = [x.strip() for x in f.read().strip().splitlines() if len(x.strip())]
         else:
             sources = [sources]
@@ -398,14 +398,14 @@ class LoadImagesAndLabels(Dataset):
                     f += glob.glob(str(p / '**' / '*.*'), recursive=True)
                     # f = list(p.rglob('*.*'))  # pathlib
                 elif p.is_file():  # file
-                    with open(p, 'r') as t:
+                    with open(p) as t:
                         t = t.read().strip().splitlines()
                         parent = str(p.parent) + os.sep
                         f += [x.replace('./', parent) if x.startswith('./') else x for x in t]  # local to global path
                         # f += [p.parent / x.lstrip(os.sep) for x in t]  # local to global path (pathlib)
                 else:
                     raise Exception(f'{prefix}{p} does not exist')
-            self.img_files = sorted([x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS])
+            self.img_files = sorted(x.replace('/', os.sep) for x in f if x.split('.')[-1].lower() in IMG_FORMATS)
             # self.img_files = sorted([x for x in f if x.suffix[1:].lower() in IMG_FORMATS])  # pathlib
             assert self.img_files, f'{prefix}No images found'
         except Exception as e:
@@ -681,7 +681,7 @@ def load_mosaic(self, index):
     # YOLOv5 4-mosaic loader. Loads 1 image + 3 random images into a 4-image mosaic
     labels4, segments4 = [], []
     s = self.img_size
-    yc, xc = [int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border]  # mosaic center x, y
+    yc, xc = (int(random.uniform(-x, 2 * s + x)) for x in self.mosaic_border)  # mosaic center x, y
     indices = [index] + random.choices(self.indices, k=3)  # 3 additional image indices
     random.shuffle(indices)
     for i, index in enumerate(indices):
@@ -767,7 +767,7 @@ def load_mosaic9(self, index):
             c = s - w, s + h0 - hp - h, s, s + h0 - hp
 
         padx, pady = c[:2]
-        x1, y1, x2, y2 = [max(x, 0) for x in c]  # allocate coords
+        x1, y1, x2, y2 = (max(x, 0) for x in c)  # allocate coords
 
         # Labels
         labels, segments = self.labels[index].copy(), self.segments[index].copy()
@@ -782,7 +782,7 @@ def load_mosaic9(self, index):
         hp, wp = h, w  # height, width previous
 
     # Offset
-    yc, xc = [int(random.uniform(0, s)) for _ in self.mosaic_border]  # mosaic center x, y
+    yc, xc = (int(random.uniform(0, s)) for _ in self.mosaic_border)  # mosaic center x, y
     img9 = img9[yc:yc + 2 * s, xc:xc + 2 * s]
 
     # Concat/clip labels
@@ -838,7 +838,7 @@ def extract_boxes(path='../datasets/coco128'):  # from utils.datasets import *;
             # labels
             lb_file = Path(img2label_paths([str(im_file)])[0])
             if Path(lb_file).exists():
-                with open(lb_file, 'r') as f:
+                with open(lb_file) as f:
                     lb = np.array([x.split() for x in f.read().strip().splitlines()], dtype=np.float32)  # labels
 
                 for j, x in enumerate(lb):
@@ -866,7 +866,7 @@ def autosplit(path='../datasets/coco128/images', weights=(0.9, 0.1, 0.0), annota
         annotated_only:  Only use images with an annotated txt file
     """
     path = Path(path)  # images dir
-    files = sorted([x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS])  # image files only
+    files = sorted(x for x in path.rglob('*.*') if x.suffix[1:].lower() in IMG_FORMATS)  # image files only
     n = len(files)  # number of files
     random.seed(0)  # for reproducibility
     indices = random.choices([0, 1, 2], weights=weights, k=n)  # assign each image to a split
@@ -902,7 +902,7 @@ def verify_image_label(args):
         # verify labels
         if os.path.isfile(lb_file):
             nf = 1  # label found
-            with open(lb_file, 'r') as f:
+            with open(lb_file) as f:
                 l = [x.split() for x in f.read().strip().splitlines() if len(x)]
                 if any([len(x) > 8 for x in l]):  # is segment
                     classes = np.array([x[0] for x in l], dtype=np.float32)
@@ -944,7 +944,7 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profil
 
     def round_labels(labels):
         # Update labels to integer class and 6 decimal place floats
-        return [[int(c), *[round(x, 4) for x in points]] for c, *points in labels]
+        return [[int(c), *(round(x, 4) for x in points)] for c, *points in labels]
 
     def unzip(path):
         # Unzip data.zip TODO: CONSTRAINT: path/to/abc.zip MUST unzip to 'path/to/abc/'
@@ -1019,7 +1019,7 @@ def dataset_stats(path='coco128.yaml', autodownload=False, verbose=False, profil
             with open(file, 'w') as f:
                 json.dump(stats, f)  # save stats *.json
             t2 = time.time()
-            with open(file, 'r') as f:
+            with open(file) as f:
                 x = json.load(f)  # load hyps dict
             print(f'stats.json times: {time.time() - t2:.3f}s read, {t2 - t1:.3f}s write')
 

utils/general.py

@@ -136,7 +136,7 @@ def is_writeable(dir, test=False):
                 pass
             file.unlink()  # remove file
             return True
-        except IOError:
+        except OSError:
             return False
     else:  # method 2
         return os.access(dir, os.R_OK)  # possible issues on Windows
@@ -355,7 +355,7 @@ def check_dataset(data, autodownload=True):
     assert 'nc' in data, "Dataset 'nc' key missing."
     if 'names' not in data:
         data['names'] = [f'class{i}' for i in range(data['nc'])]  # assign class names if missing
-    train, val, test, s = [data.get(x) for x in ('train', 'val', 'test', 'download')]
+    train, val, test, s = (data.get(x) for x in ('train', 'val', 'test', 'download'))
     if val:
         val = [Path(x).resolve() for x in (val if isinstance(val, list) else [val])]  # val path
         if not all(x.exists() for x in val):

utils/loggers/__init__.py

@@ -135,7 +135,7 @@ class Loggers():
         # Callback runs on training end
         if plots:
             plot_results(file=self.save_dir / 'results.csv')  # save results.png
-        files = ['results.png', 'confusion_matrix.png', *[f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R')]]
+        files = ['results.png', 'confusion_matrix.png', *(f'{x}_curve.png' for x in ('F1', 'PR', 'P', 'R'))]
         files = [(self.save_dir / f) for f in files if (self.save_dir / f).exists()]  # filter
 
         if self.tb:

utils/loggers/wandb/wandb_utils.py

@@ -5,6 +5,7 @@ import os
 import sys
 from contextlib import contextmanager
 from pathlib import Path
+from typing import Dict
 
 import pkg_resources as pkg
 import yaml
@@ -142,7 +143,8 @@ class WandbLogger():
         self.max_imgs_to_log = 16
         self.wandb_artifact_data_dict = None
         self.data_dict = None
-        # It's more elegant to stick to 1 wandb.init call, but useful config data is overwritten in the WandbLogger's wandb.init call
+        # It's more elegant to stick to 1 wandb.init call,
+        #  but useful config data is overwritten in the WandbLogger's wandb.init call
         if isinstance(opt.resume, str):  # checks resume from artifact
             if opt.resume.startswith(WANDB_ARTIFACT_PREFIX):
                 entity, project, run_id, model_artifact_name = get_run_info(opt.resume)
@@ -371,14 +373,14 @@ class WandbLogger():
         for i, data in enumerate(tqdm(self.val_table.data)):
             self.val_table_path_map[data[3]] = data[0]
 
-    def create_dataset_table(self, dataset, class_to_id, name='dataset'):
+    def create_dataset_table(self, dataset: LoadImagesAndLabels, class_to_id: Dict[int,str], name: str = 'dataset'):
         """
         Create and return W&B artifact containing W&B Table of the dataset.
 
         arguments:
-        dataset (LoadImagesAndLabels) -- instance of LoadImagesAndLabels class used to iterate over the data to build Table
-        class_to_id (dict(int, str)) -- hash map that maps class ids to labels
-        name (str) -- name of the artifact
+        dataset -- instance of LoadImagesAndLabels class used to iterate over the data to build Table
+        class_to_id -- hash map that maps class ids to labels
+        name -- name of the artifact
 
         returns:
         dataset artifact to be logged or used
@@ -430,7 +432,7 @@ class WandbLogger():
                 box_data.append(
                     {"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
                      "class_id": int(cls),
-                     "box_caption": "%s %.3f" % (names[cls], conf),
+                     "box_caption": f"{names[cls]} {conf:.3f}",
                      "scores": {"class_score": conf},
                      "domain": "pixel"})
                 total_conf += conf
@@ -459,7 +461,7 @@ class WandbLogger():
             if self.current_epoch % self.bbox_interval == 0:
                 box_data = [{"position": {"minX": xyxy[0], "minY": xyxy[1], "maxX": xyxy[2], "maxY": xyxy[3]},
                              "class_id": int(cls),
-                             "box_caption": "%s %.3f" % (names[cls], conf),
+                             "box_caption": f"{names[cls]} {conf:.3f}",
                              "scores": {"class_score": conf},
                              "domain": "pixel"} for *xyxy, conf, cls in pred.tolist()]
                 boxes = {"predictions": {"box_data": box_data, "class_labels": names}}  # inference-space

utils/loss.py

@@ -18,7 +18,7 @@ def smooth_BCE(eps=0.1):  # https://github.com/ultralytics/yolov3/issues/238#iss
 class BCEBlurWithLogitsLoss(nn.Module):
     # BCEwithLogitLoss() with reduced missing label effects.
     def __init__(self, alpha=0.05):
-        super(BCEBlurWithLogitsLoss, self).__init__()
+        super().__init__()
         self.loss_fcn = nn.BCEWithLogitsLoss(reduction='none')  # must be nn.BCEWithLogitsLoss()
         self.alpha = alpha
 
@@ -35,7 +35,7 @@ class BCEBlurWithLogitsLoss(nn.Module):
 class FocalLoss(nn.Module):
     # Wraps focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
     def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
-        super(FocalLoss, self).__init__()
+        super().__init__()
         self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
         self.gamma = gamma
         self.alpha = alpha
@@ -65,7 +65,7 @@ class FocalLoss(nn.Module):
 class QFocalLoss(nn.Module):
     # Wraps Quality focal loss around existing loss_fcn(), i.e. criteria = FocalLoss(nn.BCEWithLogitsLoss(), gamma=1.5)
     def __init__(self, loss_fcn, gamma=1.5, alpha=0.25):
-        super(QFocalLoss, self).__init__()
+        super().__init__()
         self.loss_fcn = loss_fcn  # must be nn.BCEWithLogitsLoss()
         self.gamma = gamma
         self.alpha = alpha

utils/plots.py

@@ -250,7 +250,7 @@ def plot_targets_txt():  # from utils.plots import *; plot_targets_txt()
     fig, ax = plt.subplots(2, 2, figsize=(8, 8), tight_layout=True)
     ax = ax.ravel()
     for i in range(4):
-        ax[i].hist(x[i], bins=100, label='%.3g +/- %.3g' % (x[i].mean(), x[i].std()))
+        ax[i].hist(x[i], bins=100, label=f'{x[i].mean():.3g} +/- {x[i].std():.3g}')
         ax[i].legend()
         ax[i].set_title(s[i])
     plt.savefig('targets.jpg', dpi=200)
@@ -363,7 +363,7 @@ def profile_idetection(start=0, stop=0, labels=(), save_dir=''):
                 else:
                     a.remove()
         except Exception as e:
-            print('Warning: Plotting error for %s; %s' % (f, e))
+            print(f'Warning: Plotting error for {f}; {e}')
     ax[1].legend()
     plt.savefig(Path(save_dir) / 'idetection_profile.png', dpi=200)
 
@@ -384,10 +384,10 @@ def plot_evolve(evolve_csv='path/to/evolve.csv'):  # from utils.plots import *;
         plt.subplot(6, 5, i + 1)
         plt.scatter(v, f, c=hist2d(v, f, 20), cmap='viridis', alpha=.8, edgecolors='none')
         plt.plot(mu, f.max(), 'k+', markersize=15)
-        plt.title('%s = %.3g' % (k, mu), fontdict={'size': 9})  # limit to 40 characters
+        plt.title(f'{k} = {mu:.3g}', fontdict={'size': 9})  # limit to 40 characters
         if i % 5 != 0:
             plt.yticks([])
-        print('%15s: %.3g' % (k, mu))
+        print(f'{k:>15}: {mu:.3g}')
     f = evolve_csv.with_suffix('.png')  # filename
     plt.savefig(f, dpi=200)
     plt.close()

utils/torch_utils.py

@@ -123,7 +123,7 @@ def profile(input, ops, n=10, device=None):
                     y = m(x)
                     t[1] = time_sync()
                     try:
-                        _ = (sum([yi.sum() for yi in y]) if isinstance(y, list) else y).sum().backward()
+                        _ = (sum(yi.sum() for yi in y) if isinstance(y, list) else y).sum().backward()
                         t[2] = time_sync()
                     except Exception as e:  # no backward method
                         # print(e)  # for debug
@@ -223,7 +223,7 @@ def model_info(model, verbose=False, img_size=640):
     n_p = sum(x.numel() for x in model.parameters())  # number parameters
     n_g = sum(x.numel() for x in model.parameters() if x.requires_grad)  # number gradients
     if verbose:
-        print('%5s %40s %9s %12s %20s %10s %10s' % ('layer', 'name', 'gradient', 'parameters', 'shape', 'mu', 'sigma'))
+        print(f"{'layer':>5} {'name':>40} {'gradient':>9} {'parameters':>12} {'shape':>20} {'mu':>10} {'sigma':>10}")
         for i, (name, p) in enumerate(model.named_parameters()):
             name = name.replace('module_list.', '')
             print('%5g %40s %9s %12g %20s %10.3g %10.3g' %
@@ -270,7 +270,7 @@ def scale_img(img, ratio=1.0, same_shape=False, gs=32):  # img(16,3,256,416)
         s = (int(h * ratio), int(w * ratio))  # new size
         img = F.interpolate(img, size=s, mode='bilinear', align_corners=False)  # resize
         if not same_shape:  # pad/crop img
-            h, w = [math.ceil(x * ratio / gs) * gs for x in (h, w)]
+            h, w = (math.ceil(x * ratio / gs) * gs for x in (h, w))
         return F.pad(img, [0, w - s[1], 0, h - s[0]], value=0.447)  # value = imagenet mean