Update

.gitattributes

@@ -26,3 +26,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zstandard filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

.gitignore

@@ -1 +0,0 @@
-images

.pre-commit-config.yaml

@@ -0,0 +1,60 @@
+repos:
+  - 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"]

.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

@@ -4,7 +4,7 @@ emoji: 🔥
 colorFrom: blue
 colorTo: gray
 sdk: gradio
-sdk_version: 3.0.5
+sdk_version: 4.19.2
 app_file: app.py
 pinned: false
 ---

app.py

@@ -2,90 +2,50 @@
 
 from __future__ import annotations
 
-import argparse
-import functools
 import os
 import pathlib
 import sys
-import tarfile
 
 import cv2
 import gradio as gr
-import huggingface_hub
 import numpy as np
 import torch
 
-sys.path.insert(0, 'face_detection')
-sys.path.insert(0, 'face_alignment')
-sys.path.insert(0, 'emotion_recognition')
+sys.path.insert(0, "face_detection")
+sys.path.insert(0, "face_alignment")
+sys.path.insert(0, "emotion_recognition")
 
 from ibug.emotion_recognition import EmoNetPredictor
 from ibug.face_alignment import FANPredictor
 from ibug.face_detection import RetinaFacePredictor
 
-TITLE = 'ibug-group/emotion_recognition'
-DESCRIPTION = 'This is an unofficial demo for https://github.com/ibug-group/emotion_recognition.'
-ARTICLE = '<center><img src="https://visitor-badge.glitch.me/badge?page_id=hysts.ibug-emotion_recognition" alt="visitor badge"/></center>'
-
-TOKEN = os.environ['TOKEN']
-
-
-def parse_args() -> argparse.Namespace:
-    parser = argparse.ArgumentParser()
-    parser.add_argument('--device', type=str, default='cpu')
-    parser.add_argument('--theme', type=str)
-    parser.add_argument('--live', action='store_true')
-    parser.add_argument('--share', action='store_true')
-    parser.add_argument('--port', type=int)
-    parser.add_argument('--disable-queue',
-                        dest='enable_queue',
-                        action='store_false')
-    parser.add_argument('--allow-flagging', type=str, default='never')
-    return parser.parse_args()
-
-
-def load_sample_images() -> list[pathlib.Path]:
-    image_dir = pathlib.Path('images')
-    if not image_dir.exists():
-        image_dir.mkdir()
-        dataset_repo = 'hysts/input-images'
-        filenames = ['004.tar']
-        for name in filenames:
-            path = huggingface_hub.hf_hub_download(dataset_repo,
-                                                   name,
-                                                   repo_type='dataset',
-                                                   use_auth_token=TOKEN)
-            with tarfile.open(path) as f:
-                f.extractall(image_dir.as_posix())
-    return sorted(image_dir.rglob('*.jpg'))
-
-
-def load_face_detector(device: torch.device) -> RetinaFacePredictor:
-    model = RetinaFacePredictor(
-        threshold=0.8,
-        device=device,
-        model=RetinaFacePredictor.get_model('mobilenet0.25'))
-    return model
+DESCRIPTION = "# [ibug-group/emotion_recognition](https://github.com/ibug-group/emotion_recognition)"
 
 
-def load_landmark_detector(device: torch.device) -> FANPredictor:
-    model = FANPredictor(device=device, model=FANPredictor.get_model('2dfan2'))
-    return model
+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"))
+landmark_detector = FANPredictor(device=device, model=FANPredictor.get_model("2dfan2"))
 
 
 def load_model(model_name: str, device: torch.device) -> EmoNetPredictor:
-    model = EmoNetPredictor(device=device,
-                            model=EmoNetPredictor.get_model(model_name))
+    model = EmoNetPredictor(device=device, model=EmoNetPredictor.get_model(model_name))
     return model
 
 
-def predict(image: np.ndarray, model_name: str, max_num_faces: int,
-            face_detector: RetinaFacePredictor,
-            landmark_detector: FANPredictor,
-            models: dict[str, EmoNetPredictor]) -> np.ndarray:
+model_names = [
+    "emonet248",
+    "emonet245",
+    "emonet248_alt",
+    "emonet245_alt",
+]
+models = {name: load_model(name, device=device) for name in model_names}
+
+
+def predict(image: np.ndarray, model_name: str, max_num_faces: int) -> np.ndarray:
     model = models[model_name]
     if len(model.config.emotion_labels) == 8:
-        colors = (
+        colors: tuple[tuple[int, int, int], ...] = (
             (192, 192, 192),
             (0, 255, 0),
             (255, 0, 0),
@@ -109,13 +69,10 @@ def predict(image: np.ndarray, model_name: str, max_num_faces: int,
 
     faces = face_detector(image, rgb=False)
     if len(faces) == 0:
-        raise RuntimeError('No face was found.')
+        raise gr.Error("No face was found.")
     faces = sorted(list(faces), key=lambda x: -x[4])[:max_num_faces]
     faces = np.asarray(faces)
-    _, _, features = landmark_detector(image,
-                                       faces,
-                                       rgb=False,
-                                       return_features=True)
+    _, _, features = landmark_detector(image, faces, rgb=False, return_features=True)
     emotions = model(features)
 
     res = image.copy()
@@ -123,71 +80,54 @@ def predict(image: np.ndarray, model_name: str, max_num_faces: int,
         box = np.round(face[:4]).astype(int)
         cv2.rectangle(res, tuple(box[:2]), tuple(box[2:]), (0, 255, 0), 2)
 
-        emotion = emotions['emotion'][index]
-        valence = emotions['valence'][index]
-        arousal = emotions['arousal'][index]
+        emotion = emotions["emotion"][index]
+        valence = emotions["valence"][index]
+        arousal = emotions["arousal"][index]
         emotion_label = model.config.emotion_labels[emotion].title()
 
-        text_content = f'{emotion_label} ({valence: .01f}, {arousal: .01f})'
-        cv2.putText(res,
-                    text_content, (box[0], box[1] - 10),
-                    cv2.FONT_HERSHEY_DUPLEX,
-                    1,
-                    colors[emotion],
-                    lineType=cv2.LINE_AA)
+        text_content = f"{emotion_label} ({valence: .01f}, {arousal: .01f})"
+        cv2.putText(
+            res, text_content, (box[0], box[1] - 10), cv2.FONT_HERSHEY_DUPLEX, 1, colors[emotion], lineType=cv2.LINE_AA
+        )
 
     return res[:, :, ::-1]
 
 
-def main():
-    args = parse_args()
-    device = torch.device(args.device)
-
-    face_detector = load_face_detector(device)
-    landmark_detector = load_landmark_detector(device)
-
-    model_names = [
-        'emonet248',
-        'emonet245',
-        'emonet248_alt',
-        'emonet245_alt',
-    ]
-    models = {name: load_model(name, device=device) for name in model_names}
-
-    func = functools.partial(predict,
-                             face_detector=face_detector,
-                             landmark_detector=landmark_detector,
-                             models=models)
-    func = functools.update_wrapper(func, predict)
-
-    image_paths = load_sample_images()
-    examples = [[path.as_posix(), model_names[0], 30] for path in image_paths]
-
-    gr.Interface(
-        func,
-        [
-            gr.inputs.Image(type='numpy', label='Input'),
-            gr.inputs.Radio(model_names,
-                            type='value',
-                            default=model_names[0],
-                            label='Model'),
-            gr.inputs.Slider(
-                1, 30, step=1, default=30, label='Max Number of Faces'),
-        ],
-        gr.outputs.Image(type='numpy', label='Output'),
-        examples=examples,
-        title=TITLE,
-        description=DESCRIPTION,
-        article=ARTICLE,
-        theme=args.theme,
-        allow_flagging=args.allow_flagging,
-        live=args.live,
-    ).launch(
-        enable_queue=args.enable_queue,
-        server_port=args.port,
-        share=args.share,
+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,
+                value=model_names[0],
+                type="value",
+            )
+            max_num_of_faces = gr.Slider(
+                label="Max Number of Faces",
+                minimum=1,
+                maximum=30,
+                step=1,
+                value=30,
+            )
+            run_button = gr.Button()
+        with gr.Column():
+            result = gr.Image(label="Output")
+    gr.Examples(
+        examples=[[path.as_posix(), model_names[0], 30] for path in sorted(pathlib.Path("images").rglob("*.jpg"))],
+        inputs=[image, model_name, max_num_of_faces],
+        outputs=result,
+        fn=predict,
+        cache_examples=os.getenv("CACHE_EXAMPLES") == "1",
+    )
+    run_button.click(
+        fn=predict,
+        inputs=[image, model_name, max_num_of_faces],
+        outputs=result,
+        api_name="predict",
     )
 
 
-if __name__ == '__main__':
-    main()
+if __name__ == "__main__":
+    demo.queue(max_size=20).launch()

images/README.md

@@ -0,0 +1,3 @@
+These images are from the following public domain:
+- https://www.pexels.com/photo/collage-photo-of-woman-3812743/
+- https://www.pexels.com/photo/collage-of-portraits-of-cheerful-woman-3807758/

requirements.txt

@@ -1,4 +1,4 @@
-numpy==1.22.3
-opencv-python-headless==4.5.5.64
-torch==1.11.0
-torchvision==0.12.0
+numpy==1.26.4
+opencv-python-headless==4.9.0.80
+torch==2.0.1
+torchvision==0.15.2

style.css

@@ -0,0 +1,11 @@
+h1 {
+  text-align: center;
+  display: block;
+}
+
+#duplicate-button {
+  margin: auto;
+  color: #fff;
+  background: #1565c0;
+  border-radius: 100vh;
+}