Download emotion.py from YuAnTsai/MachineVision_DeepLearning_FinalProject: direct link, hf CLI and curl.
- Browser
- Download file 9.38 kB
-
https://huggingface.co/spaces/YuAnTsai/MachineVision_DeepLearning_FinalProject/resolve/698dff79fdcd8f0100a8b4a982e4256409fe46b9/emotion.py
- Command line
-
hf download hf://spaces/YuAnTsai/MachineVision_DeepLearning_FinalProject@698dff79fdcd8f0100a8b4a982e4256409fe46b9/emotion.py
-
curl -L -o emotion.py https://huggingface.co/spaces/YuAnTsai/MachineVision_DeepLearning_FinalProject/resolve/698dff79fdcd8f0100a8b4a982e4256409fe46b9/emotion.py
9.38 kB
| import time | |
| from dataclasses import dataclass, field | |
| from typing import Optional, Dict, Tuple, List | |
| import gradio as gr | |
| import numpy as np | |
| import cv2 | |
| from PIL import Image | |
| import mediapipe as mp | |
| from mediapipe.tasks import python | |
| from mediapipe.tasks.vision import FaceDetector, FaceDetectorOptions, RunningMode | |
| from deepface import DeepFace | |
| # ========================= | |
| # 參數與 MediaPipe 初始化 | |
| # ========================= | |
| ANALYZE_EVERY_SEC = 0.6 # MediaPipe 很快,可以稍微縮短間隔 | |
| DOWNSAMPLE_W = 720 | |
| EMA_ALPHA = 0.45 | |
| CONF_TH = 40.0 | |
| SWITCH_CONFIRM_SEC = 2.0 | |
| IOU_TH = 0.25 | |
| ZOOM_FACTOR = 1.3 | |
| # MediaPipe 設定 | |
| MODEL_PATH = 'model/blaze_face_short_range.tflite' | |
| base_options = python.BaseOptions(model_asset_path=MODEL_PATH) | |
| options = FaceDetectorOptions( | |
| base_options=base_options, | |
| running_mode=RunningMode.IMAGE | |
| ) | |
| # 建立全域偵測器 | |
| mp_detector = FaceDetector.create_from_options(options) | |
| # ========================= | |
| # 情緒映射與標籤 | |
| # ========================= | |
| EMO_ZH = { | |
| "angry": "生氣", "disgust": "厭惡", "fear": "害怕", | |
| "happy": "開心", "sad": "難過", "surprise": "驚訝", | |
| "neutral": "平靜", "unknown": "未知", | |
| } | |
| EMO_TO_SCORE = { | |
| "angry": 1, "disgust": 1, "fear": 1, | |
| "sad": 2, "neutral": 3, "surprise": 4, | |
| "happy": 5, "unknown": 3, | |
| } | |
| SCORE_LABELS = { | |
| 1: "1(心情差)", 2: "2(不太好)", 3: "3(普通)", | |
| 4: "4(不錯)", 5: "5(超棒)", | |
| } | |
| SCORE_CHOICES = [SCORE_LABELS[i] for i in [1, 2, 3, 4, 5]] | |
| class AppState: | |
| running: bool = True | |
| finished: bool = False | |
| last_analyze_t: float = 0.0 | |
| track_bbox: Optional[Tuple[int, int, int, int]] = None | |
| ema_scores: Optional[np.ndarray] = None | |
| emo_keys: List[str] = field(default_factory=list) | |
| stable_emo: str = "unknown" | |
| candidate_emo: Optional[str] = None | |
| candidate_since: Optional[float] = None | |
| final_emo: Optional[str] = None | |
| final_conf: Optional[float] = None | |
| final_score: int = 3 | |
| # ========================= | |
| # UI 工具與輔助函式 | |
| # ========================= | |
| def _hint_html(msg: str) -> str: | |
| return f'<div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#000000;">{msg}</div>' | |
| def _result_card_html(emo_key: str, conf: Optional[float]) -> str: | |
| zh = EMO_ZH.get(emo_key, emo_key) | |
| score = EMO_TO_SCORE.get(emo_key, 3) | |
| conf_txt = "" if conf is None else f"{conf:.1f}%" | |
| score_desc = SCORE_LABELS[score].split("(")[1].rstrip(")") | |
| return f""" | |
| <div style="border-radius:16px;padding:20px;border:1px solid #E6E6E6;background:#FFFFFF;color:#000000;"> | |
| <div style="font-size:14px;margin-bottom:8px;">即時辨識結果</div> | |
| <div style="font-size:42px;font-weight:800;line-height:1.1;margin-bottom:14px;">{zh}</div> | |
| <div style="font-size:16px;margin-bottom:6px;">心情分數:{score}({score_desc})</div> | |
| <div style="font-size:14px;">信心值:{conf_txt}</div> | |
| </div> | |
| """ | |
| def _score_radio_value(score: int) -> str: | |
| return SCORE_LABELS[min(5, max(1, int(score)))] | |
| def _iou(a, b) -> float: | |
| ax, ay, aw, ah = a | |
| bx, by, bw, bh = b | |
| ix, iy = max(ax, bx), max(ay, by) | |
| iw, ih = max(0, min(ax+aw, bx+bw)-ix), max(0, min(ay+ah, by+bh)-iy) | |
| area_i = iw * ih | |
| if area_i <= 0: return 0.0 | |
| return area_i / (aw*ah + bw*bh - area_i) | |
| def _zoom_center(frame: np.ndarray, zoom: float) -> np.ndarray: | |
| if frame is None or zoom <= 1.0: return frame | |
| h, w = frame.shape[:2] | |
| nw, nh = int(w / zoom), int(h / zoom) | |
| sx, sy = (w - nw) // 2, (h - nh) // 2 | |
| return frame[sy:sy+nh, sx:sx+nw] | |
| # ========================= | |
| # MediaPipe 偵測邏輯 | |
| # ========================= | |
| def get_face_mediapipe(frame: np.ndarray, prev_bbox: Optional[Tuple[int, int, int, int]]): | |
| h, w = frame.shape[:2] | |
| mp_image = mp.Image(image_format=mp.ImageFormat.SRGB, data=frame) | |
| res = mp_detector.detect(mp_image) | |
| if not res.detections: | |
| return None, None | |
| candidates = [] | |
| for det in res.detections: | |
| b = det.bounding_box | |
| # 數值校正,避免超出邊界導致 DeepFace 報錯 | |
| nx, ny = max(0, b.origin_x), max(0, b.origin_y) | |
| nw, nh = min(b.width, w - nx), min(b.height, h - ny) | |
| if nw > 10 and nh > 10: | |
| candidates.append(((nx, ny, nw, nh), frame[ny:ny+nh, nx:nx+nw])) | |
| if not candidates: | |
| return None, None | |
| # 優先匹配上一幀的位置 | |
| if prev_bbox: | |
| best_match = max(candidates, key=lambda c: _iou(prev_bbox, c[0]), default=(None, None)) | |
| if best_match[0] and _iou(prev_bbox, best_match[0]) > IOU_TH: | |
| return best_match | |
| # 否則回傳面積最大者 | |
| return max(candidates, key=lambda c: c[0][2] * c[0][3]) | |
| # ========================= | |
| # Gradio 事件處理 | |
| # ========================= | |
| def on_stream(frame_rgb: np.ndarray, st: AppState): | |
| if not st.running or st.finished: | |
| res_html = _result_card_html(st.final_emo, st.final_conf) if st.final_emo else _hint_html("辨識停止") | |
| return gr.update(visible=False), res_html, _score_radio_value(st.final_score), _hint_html("已完成"), st, gr.update() | |
| if frame_rgb is None: | |
| return gr.update(), gr.update(), gr.update(), _hint_html("等待攝影機..."), st, gr.update() | |
| frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR) | |
| now = time.time() | |
| # 頻率控制 | |
| if now - st.last_analyze_t < ANALYZE_EVERY_SEC: | |
| return gr.update(), gr.update(), gr.update(), gr.update(), st, gr.update() | |
| st.last_analyze_t = now | |
| # 使用 MediaPipe 找臉 | |
| bbox, face_crop = get_face_mediapipe(frame_rgb, st.track_bbox) | |
| if face_crop is None: | |
| return gr.update(), gr.update(), gr.update(), _hint_html("未偵測到人臉"), st, gr.update() | |
| st.track_bbox = bbox | |
| # DeepFace 情緒分析 (傳入已裁切的人臉) | |
| try: | |
| res = DeepFace.analyze(face_crop, actions=['emotion'], enforce_detection=False, silent=True) | |
| emo_dict = res[0]['emotion'] if isinstance(res, list) else res['emotion'] | |
| except: | |
| return gr.update(), gr.update(), gr.update(), gr.update(), st, gr.update() | |
| top_key = max(emo_dict, key=lambda k: float(emo_dict[k])) | |
| top_conf = float(emo_dict[top_key]) | |
| # 平滑處理 (EMA) | |
| if top_conf >= CONF_TH: | |
| keys = list(emo_dict.keys()) | |
| vals = np.array([float(emo_dict[k]) for k in keys]) | |
| if st.ema_scores is None or st.emo_keys != keys: | |
| st.ema_scores, st.emo_keys = vals, keys | |
| else: | |
| st.ema_scores = EMA_ALPHA * vals + (1.0 - EMA_ALPHA) * st.ema_scores | |
| st.stable_emo = st.emo_keys[int(np.argmax(st.ema_scores))] | |
| # 穩定切換邏輯 | |
| if st.candidate_emo != st.stable_emo: | |
| st.candidate_emo, st.candidate_since = st.stable_emo, now | |
| elif st.candidate_since and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC: | |
| st.final_emo, st.final_conf = st.stable_emo, top_conf | |
| st.final_score = EMO_TO_SCORE.get(st.stable_emo, 3) | |
| st.finished, st.running = True, False | |
| return ( | |
| gr.update(visible=not st.finished), | |
| gr.update(value=_result_card_html(st.stable_emo, top_conf)), | |
| gr.update(value=_score_radio_value(EMO_TO_SCORE.get(st.stable_emo, 3))), | |
| gr.update(value=_hint_html("正在辨識中,請保持表情穩定...")), | |
| st, | |
| gr.update() | |
| ) | |
| def on_restart(st: AppState): | |
| new_st = AppState() | |
| return ( | |
| gr.update(visible=True), | |
| _hint_html("等待影像..."), | |
| _score_radio_value(3), | |
| _hint_html("請點擊 Record 開始"), | |
| new_st, | |
| gr.update() | |
| ) | |
| def on_stop(st: AppState): | |
| st.running, st.finished = False, True | |
| return gr.update(visible=False), gr.update(), gr.update(), _hint_html("已手動停止"), st, gr.update() | |
| # ========================= | |
| # Gradio UI 介面 | |
| # ========================= | |
| css = ".gradio-container { background-color: #f7f9fc; }" | |
| with gr.Blocks(title="AI 情緒偵測系統", css=css) as demo: | |
| state = gr.State(AppState()) | |
| gr.Markdown("# 🎭 AI 情緒辨識評分系統") | |
| status_hint = gr.HTML(_hint_html("請開啟攝影機並點擊錄製")) | |
| with gr.Row(): | |
| with gr.Column(scale=1): | |
| webcam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="攝影機畫面") | |
| with gr.Row(): | |
| btn_re = gr.Button("🔄 重新辨識", variant="primary") | |
| btn_stop = gr.Button("🛑 停止", variant="secondary") | |
| with gr.Column(scale=1): | |
| res_display = gr.HTML(_result_card_html("unknown", 0)) | |
| gr.Markdown("### 系統判定心情分數") | |
| mood_radio = gr.Radio(choices=SCORE_CHOICES, value=SCORE_LABELS[3], interactive=False, label="") | |
| # 事件綁定 | |
| webcam.stream( | |
| fn=on_stream, | |
| inputs=[webcam, state], | |
| outputs=[webcam, res_display, mood_radio, status_hint, state, btn_re] | |
| ) | |
| btn_re.click(fn=on_restart, inputs=[state], outputs=[webcam, res_display, mood_radio, status_hint, state, btn_re]) | |
| btn_stop.click(fn=on_stop, inputs=[state], outputs=[webcam, res_display, mood_radio, status_hint, state, btn_re]) | |
| if __name__ == "__main__": | |
| demo.launch(server_name="0.0.0.0", server_port=7860) |