Update

.pre-commit-config.yaml

@@ -1,35 +1,60 @@
 repos:
-- repo: https://github.com/pre-commit/pre-commit-hooks
-  rev: v4.2.0
-  hooks:
-  - id: check-executables-have-shebangs
-  - id: check-json
-  - id: check-merge-conflict
-  - id: check-shebang-scripts-are-executable
-  - id: check-toml
-  - id: check-yaml
-  - id: double-quote-string-fixer
-  - id: end-of-file-fixer
-  - id: mixed-line-ending
-    args: ['--fix=lf']
-  - id: requirements-txt-fixer
-  - id: trailing-whitespace
-- repo: https://github.com/myint/docformatter
-  rev: v1.4
-  hooks:
-  - id: docformatter
-    args: ['--in-place']
-- repo: https://github.com/pycqa/isort
-  rev: 5.12.0
-  hooks:
-    - id: isort
-- repo: https://github.com/pre-commit/mirrors-mypy
-  rev: v0.991
-  hooks:
-    - id: mypy
-      args: ['--ignore-missing-imports']
-- repo: https://github.com/google/yapf
-  rev: v0.32.0
-  hooks:
-  - id: yapf
-    args: ['--parallel', '--in-place']
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: check-executables-have-shebangs
+      - id: check-json
+      - id: check-merge-conflict
+      - id: check-shebang-scripts-are-executable
+      - id: check-toml
+      - id: check-yaml
+      - id: end-of-file-fixer
+      - id: mixed-line-ending
+        args: ["--fix=lf"]
+      - id: requirements-txt-fixer
+      - id: trailing-whitespace
+  - repo: https://github.com/myint/docformatter
+    rev: v1.7.5
+    hooks:
+      - id: docformatter
+        args: ["--in-place"]
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+        args: ["--profile", "black"]
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.8.0
+    hooks:
+      - id: mypy
+        args: ["--ignore-missing-imports"]
+        additional_dependencies:
+          [
+            "types-python-slugify",
+            "types-requests",
+            "types-PyYAML",
+            "types-pytz",
+          ]
+  - repo: https://github.com/psf/black
+    rev: 24.2.0
+    hooks:
+      - id: black
+        language_version: python3.10
+        args: ["--line-length", "119"]
+  - repo: https://github.com/kynan/nbstripout
+    rev: 0.7.1
+    hooks:
+      - id: nbstripout
+        args:
+          [
+            "--extra-keys",
+            "metadata.interpreter metadata.kernelspec cell.metadata.pycharm",
+          ]
+  - repo: https://github.com/nbQA-dev/nbQA
+    rev: 1.7.1
+    hooks:
+      - id: nbqa-black
+      - id: nbqa-pyupgrade
+        args: ["--py37-plus"]
+      - id: nbqa-isort
+        args: ["--float-to-top"]

.style.yapf

@@ -1,5 +0,0 @@
-[style]
-based_on_style = pep8
-blank_line_before_nested_class_or_def = false
-spaces_before_comment = 2
-split_before_logical_operator = true

.vscode/settings.json

@@ -0,0 +1,30 @@
+{
+    "editor.formatOnSave": true,
+    "files.insertFinalNewline": false,
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.black-formatter",
+        "editor.formatOnType": true,
+        "editor.codeActionsOnSave": {
+            "source.organizeImports": "explicit"
+        }
+    },
+    "[jupyter]": {
+        "files.insertFinalNewline": false
+    },
+    "black-formatter.args": [
+        "--line-length=119"
+    ],
+    "isort.args": ["--profile", "black"],
+    "flake8.args": [
+        "--max-line-length=119"
+    ],
+    "ruff.lint.args": [
+        "--line-length=119"
+    ],
+    "notebook.output.scrolling": true,
+    "notebook.formatOnCellExecution": true,
+    "notebook.formatOnSave.enabled": true,
+        "notebook.codeActionsOnSave": {
+            "source.organizeImports": "explicit"
+        }
+}

README.md

@@ -4,9 +4,10 @@ emoji: 📚
 colorFrom: purple
 colorTo: yellow
 sdk: gradio
-sdk_version: 3.36.1
+sdk_version: 4.19.2
 app_file: app.py
 pinned: false
+short_description: head pose estimation
 ---
 
 Check out the configuration reference at https://huggingface.co/docs/hub/spaces#reference

app.py

@@ -19,19 +19,18 @@ import torchvision
 import torchvision.transforms as T
 from scipy.spatial.transform import Rotation
 
-sys.path.insert(0, 'face_detection')
-sys.path.insert(0, 'deep-head-pose/code')
+sys.path.insert(0, "face_detection")
+sys.path.insert(0, "deep-head-pose/code")
 
 from hopenet import Hopenet
 from ibug.face_detection import RetinaFacePredictor
 
-DESCRIPTION = '# [Hopenet](https://github.com/natanielruiz/deep-head-pose)'
+DESCRIPTION = "# [Hopenet](https://github.com/natanielruiz/deep-head-pose)"
 
 
 def load_model(model_name: str, device: torch.device) -> nn.Module:
-    path = huggingface_hub.hf_hub_download('public-data/Hopenet',
-                                           f'models/{model_name}.pkl')
-    state_dict = torch.load(path, map_location='cpu')
+    path = huggingface_hub.hf_hub_download("public-data/Hopenet", f"models/{model_name}.pkl")
+    state_dict = torch.load(path, map_location="cpu")
     model = Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66)
     model.load_state_dict(state_dict)
     model.to(device)
@@ -40,12 +39,14 @@ def load_model(model_name: str, device: torch.device) -> nn.Module:
 
 
 def create_transform() -> Callable:
-    transform = T.Compose([
-        T.Resize(224),
-        T.CenterCrop(224),
-        T.ToTensor(),
-        T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
-    ])
+    transform = T.Compose(
+        [
+            T.Resize(224),
+            T.CenterCrop(224),
+            T.ToTensor(),
+            T.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
+        ]
+    )
     return transform
 
 
@@ -66,8 +67,7 @@ def crop_face(image: np.ndarray, box: tuple[int, int, int, int]) -> np.ndarray:
 
 
 @torch.inference_mode()
-def predict(image: np.ndarray, transform: Callable, model: nn.Module,
-            device: torch.device) -> np.ndarray:
+def predict(image: np.ndarray, transform: Callable, model: nn.Module, device: torch.device) -> np.ndarray:
     indices = torch.arange(66).float().to(device)
 
     image = PIL.Image.fromarray(image)
@@ -84,12 +84,11 @@ def predict(image: np.ndarray, transform: Callable, model: nn.Module,
     return out
 
 
-def draw_axis(image: np.ndarray, pose: np.ndarray, origin: np.ndarray,
-              length: int) -> None:
+def draw_axis(image: np.ndarray, pose: np.ndarray, origin: np.ndarray, length: int) -> None:
     # (yaw, pitch, roll) -> (roll, yaw, pitch)
     pose = pose[[2, 0, 1]]
     pose *= np.array([1, -1, 1])
-    rot = Rotation.from_euler('zyx', pose, degrees=True)
+    rot = Rotation.from_euler("zyx", pose, degrees=True)
 
     vectors = rot.as_matrix().T[:, :2]  # shape: (3, 2)
     pts = np.round(vectors * length + origin).astype(int)
@@ -99,9 +98,14 @@ def draw_axis(image: np.ndarray, pose: np.ndarray, origin: np.ndarray,
     cv2.line(image, tuple(origin), tuple(pts[2]), (255, 0, 0), 2)
 
 
-def run(image: np.ndarray, model_name: str, face_detector: RetinaFacePredictor,
-        models: dict[str, nn.Module], transform: Callable,
-        device: torch.device) -> np.ndarray:
+def run(
+    image: np.ndarray,
+    model_name: str,
+    face_detector: RetinaFacePredictor,
+    models: dict[str, nn.Module],
+    transform: Callable,
+    device: torch.device,
+) -> np.ndarray:
     model = models[model_name]
 
     # RGB -> BGR
@@ -124,47 +128,36 @@ def run(image: np.ndarray, model_name: str, face_detector: RetinaFacePredictor,
     return res[:, :, ::-1]
 
 
-device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
-face_detector = RetinaFacePredictor(
-    threshold=0.8,
-    device=device,
-    model=RetinaFacePredictor.get_model('mobilenet0.25'))
+device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
+face_detector = RetinaFacePredictor(threshold=0.8, device=device, model=RetinaFacePredictor.get_model("mobilenet0.25"))
 
 model_names = [
-    'hopenet_alpha1',
-    'hopenet_alpha2',
-    'hopenet_robust_alpha1',
+    "hopenet_alpha1",
+    "hopenet_alpha2",
+    "hopenet_robust_alpha1",
 ]
 models = {name: load_model(name, device) for name in model_names}
 transform = create_transform()
 
-fn = functools.partial(run,
-                       face_detector=face_detector,
-                       models=models,
-                       transform=transform,
-                       device=device)
+fn = functools.partial(run, face_detector=face_detector, models=models, transform=transform, device=device)
 
-examples = [['images/pexels-ksenia-chernaya-8535230.jpg', 'hopenet_alpha1']]
+examples = [["images/pexels-ksenia-chernaya-8535230.jpg", "hopenet_alpha1"]]
 
-with gr.Blocks(css='style.css') as demo:
+with gr.Blocks(css="style.css") as demo:
     gr.Markdown(DESCRIPTION)
     with gr.Row():
         with gr.Column():
-            image = gr.Image(label='Input', type='numpy')
-            model_name = gr.Radio(label='Model',
-                                  choices=model_names,
-                                  type='value',
-                                  value=model_names[0])
-            run_button = gr.Button('Run')
+            image = gr.Image(label="Input", type="numpy")
+            model_name = gr.Radio(label="Model", choices=model_names, type="value", value=model_names[0])
+            run_button = gr.Button("Run")
         with gr.Column():
-            result = gr.Image(label='Output')
-    gr.Examples(examples=examples,
-                inputs=[image, model_name],
-                outputs=result,
-                fn=fn,
-                cache_examples=os.getenv('CACHE_EXAMPLES') == '1')
-    run_button.click(fn=fn,
-                     inputs=[image, model_name],
-                     outputs=result,
-                     api_name='run')
+            result = gr.Image(label="Output")
+    gr.Examples(
+        examples=examples,
+        inputs=[image, model_name],
+        outputs=result,
+        fn=fn,
+        cache_examples=os.getenv("CACHE_EXAMPLES") == "1",
+    )
+    run_button.click(fn=fn, inputs=[image, model_name], outputs=result, api_name="run")
 demo.queue().launch()

requirements.txt

@@ -1,6 +1,6 @@
-numpy==1.23.5
-opencv-python-headless==4.8.0.74
-Pillow==10.0.0
-scipy==1.11.1
+numpy==1.26.4
+opencv-python-headless==4.9.0.80
+Pillow==10.2.0
+scipy==1.12.0
 torch==2.0.1
 torchvision==0.15.2

style.css

@@ -1,7 +1,11 @@
 h1 {
   text-align: center;
+  display: block;
 }
 
 #duplicate-button {
   margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
 }