Update emotion.py

emotion.py

@@ -9,23 +9,22 @@ from PIL import Image, ImageDraw
 from deepface import DeepFace
 
 # =========================
-# 參數優化（平衡效能與準度）
+# 1. 核心參數優化
 # =========================
-ANALYZE_EVERY_SEC = 1.0     # 辨識頻率：1秒一次
-DOWNSAMPLE_W = 320          # 再次降解析度，大幅提升速度
-EMA_ALPHA = 0.45
-CONF_TH = 35.0              # 稍微調低門檻，增加反應靈敏度
-SWITCH_CONFIRM_SEC = 2.0    # 縮短確認時間，體感變快
-ZOOM_FACTOR = 1.2
-
-DETECTOR_BACKEND = "opencv" # 最速模式
-ALIGN_FACE = False          # 關閉對齊以節省運算
-
-# 全域狀態：防止運算堆積
+ANALYZE_EVERY_SEC = 1.0     # 辨識頻率：1秒1次 (降低 CPU 負荷)
+DOWNSAMPLE_W = 320          # 解析度降至 320px (大幅提升速度)
+EMA_ALPHA = 0.40            # 平滑係數
+CONF_TH = 35.0              # 信心值門檻
+SWITCH_CONFIRM_SEC = 2.0    # 情緒穩定多久才算最終結果
+ZOOM_FACTOR = 1.25          # 稍微放大臉部區域
+DETECTOR_BACKEND = "opencv" # 最速辨識器
+ALIGN_FACE = False          # 關閉對齊以節省資源
+
+# 全域狀態：防止 DeepFace 重疊執行導致阻塞
 _is_processing = False
 
 # =========================
-# 狀態與工具
+# 2. 狀態管理
 # =========================
 @dataclass
 class AppState:
@@ -43,6 +42,38 @@ class AppState:
     last_face_t: float = 0.0
     face_in_box: bool = False
 
+# =========================
+# 3. UI 輔助函數 (修正 AttributeError)
+# =========================
+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:
+    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"}
+    zh = EMO_ZH.get(emo_key, "分析中...")
+    score_map = {"angry": 1, "disgust": 1, "fear": 1, "sad": 2, "neutral": 3, "surprise": 4, "happy": 5, "unknown": 3}
+    score = score_map.get(emo_key, 3)
+    conf_txt = f"{conf:.1f}%" if conf else "--"
+    return f"""
+    <div style="border-radius:16px;padding:20px;border:1px solid #E6E6E6;background:#FFFFFF;color:#000000;">
+      <div style="font-size:14px;color:#666;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}</div>
+      <div style="font-size:14px;color:#999;">信心值：{conf_txt}</div>
+    </div>
+    """
+
+def _score_to_label(score_int: int) -> str:
+    labels = {1: "1（心情差）", 2: "2（不太好）", 3: "3（普通）", 4: "4（不錯）", 5: "5（超棒）"}
+    return labels.get(score_int, "3（普通）")
+
+# =========================
+# 4. 影像處理工具
+# =========================
 def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
     if frame is None: return None
     h, w = frame.shape[:2]
@@ -59,121 +90,140 @@ def _zoom_center(frame: np.ndarray, zoom: float) -> np.ndarray:
     return frame[sy:sy + nh, sx:sx + nw]
 
 # =========================
-# UI 組件 (情緒映射)
-# =========================
-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）"}
-
-def _result_card_html(emo_key: str, conf: Optional[float]) -> str:
-    zh = EMO_ZH.get(emo_key, "分析中...")
-    score = EMO_TO_SCORE.get(emo_key, 3)
-    conf_txt = f"{conf:.1f}%" if conf else "--"
-    return f"""
-    <div style="border-radius:12px;padding:15px;border:1px solid #EEE;background:#FFF;color:#333;">
-      <div style="font-size:32px;font-weight:bold;">{zh}</div>
-      <div style="font-size:16px;">心情分數：{score} | 信心值：{conf_txt}</div>
-    </div>
-    """
-
-# =========================
-# 核心 Stream 邏輯
+# 5. 核心串流邏輯 (防止阻塞)
 # =========================
 def on_stream(frame_rgb: np.ndarray, st: AppState):
     global _is_processing
     now = time.time()
 
-    if not st.running or st.finished or frame_rgb is None:
-        return (gr.update(), gr.update(), gr.update(), gr.update(), st, gr.update())
+    # 如果已經完成或沒影像，直接結束
+    if st.finished or not st.running or frame_rgb is None:
+        return (gr.update(), gr.update(), gr.update(), gr.update(), st)
 
-    # 1. 基礎處理 (輕量)
-    frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR)
-    
-    # 2. 判斷是否要跳過重度運算 (防止阻塞關鍵)
-    # 如果正在處理中，或距離上次處理不到時間，只回傳畫框影像
+    # A. 基礎���像處理 (輕量級，每影格都做)
+    processed_frame = _zoom_center(frame_rgb, ZOOM_FACTOR)
+
+    # B. 判斷是否要進行 DeepFace 分析 (防止堆積)
     if _is_processing or (now - st.last_analyze_t < ANALYZE_EVERY_SEC):
-        # 即使不運算，也回傳當前畫面讓 UI 不會卡死
-        is_detected = (now - st.last_face_t) < 1.0
-        # 此處省略畫框 draw 邏輯以極大化流暢度，或可沿用你的 _draw_guide_overlay
-        return (frame_rgb, gr.update(), gr.update(), gr.update(), st, gr.update())
+        # 忙碌中或時間未到，只回傳影像，確保 UI 不會卡死
+        return (processed_frame, gr.update(), gr.update(), gr.update(), st)
 
-    # 3. 開始重度運算
+    # C. 開始分析 (加鎖)
     _is_processing = True
     try:
         st.last_analyze_t = now
-        small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
+        small_img = _downsample_rgb(processed_frame, DOWNSAMPLE_W)
         
-        # 快速臉部偵測
+        # 使用 DeepFace 分析 (enforce_detection=False 避免沒臉時噴 Error)
         results = DeepFace.analyze(
-            img_path=small,
+            img_path=small_img,
             actions=['emotion'],
             detector_backend=DETECTOR_BACKEND,
             enforce_detection=False,
             align=ALIGN_FACE
         )
         
-        if results and results[0].get('face_confidence', 0) > 0.4:
+        if results and len(results) > 0:
             res = results[0]
-            st.last_face_t = now
-            emo_dict = res['emotion']
-            top_key = max(emo_dict, key=emo_dict.get)
-            top_conf = emo_dict[top_key]
-
-            # EMA 平滑處理
-            keys = list(emo_dict.keys())
-            vec = np.array([emo_dict[k] for k in keys])
-            if st.ema_scores is None:
-                st.ema_scores = vec
-                st.emo_keys = keys
-            else:
-                st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores
-            
-            stable_key = st.emo_keys[np.argmax(st.ema_scores)]
-            st.stable_emo = stable_key
-
-            # 確認邏輯
-            if st.candidate_emo != stable_key:
-                st.candidate_emo = stable_key
-                st.candidate_since = now
-            elif st.candidate_since and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC:
-                st.final_emo = stable_key
-                st.final_conf = top_conf
-                st.finished = True
-                st.running = False
-
-            return (
-                frame_rgb, 
-                _result_card_html(stable_key, top_conf), 
-                SCORE_LABELS[EMO_TO_SCORE.get(stable_key, 3)],
-                "偵測中...",
-                st,
-                gr.update()
-            )
-            
+            # 只有在真的偵測到臉的情況下才更新 (OpenCV 信心值較低)
+            if res.get('face_confidence', 0) > 0.3:
+                st.last_face_t = now
+                emo_dict = res['emotion']
+                top_key = max(emo_dict, key=emo_dict.get)
+                
+                # EMA 平滑
+                keys = list(emo_dict.keys())
+                vec = np.array([float(emo_dict[k]) for k in keys])
+                if st.ema_scores is None:
+                    st.ema_scores, st.emo_keys = vec, keys
+                else:
+                    st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores
+                
+                stable_key = st.emo_keys[np.argmax(st.ema_scores)]
+                st.stable_emo = stable_key
+
+                # 確認邏輯
+                if st.candidate_emo != stable_key:
+                    st.candidate_emo, st.candidate_since = stable_key, now
+                elif st.candidate_since and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC:
+                    st.final_emo, st.final_conf = stable_key, float(emo_dict[stable_key])
+                    st.finished = True
+                
+                score_val = {"angry": 1, "disgust": 1, "fear": 1, "sad": 2, "neutral": 3, "surprise": 4, "happy": 5, "unknown": 3}.get(stable_key, 3)
+                
+                return (
+                    processed_frame, 
+                    _result_card_html(stable_key, float(emo_dict[top_key])),
+                    _score_to_label(score_val),
+                    _hint_html("正在辨識情緒，請保持表情穩定..."),
+                    st
+                )
+
     except Exception as e:
-        print(f"Analysis Error: {e}")
+        print(f"DeepFace 分析異常: {e}")
     finally:
-        _is_processing = False # 釋放鎖定，允許下一波分析
+        _is_processing = False
 
-    return (frame_rgb, gr.update(), gr.update(), gr.update(), st, gr.update())
+    return (processed_frame, gr.update(), gr.update(), gr.update(), st)
 
 # =========================
-# Gradio 介面省略 (沿用原架構但簡化)
+# 6. Gradio 介面佈局
 # =========================
-with gr.Blocks(title="Fast Emotion Detector") as demo:
-    st = gr.State(AppState())
-    cam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="Live")
-    result_html = gr.HTML(_result_card_html("unknown", 0))
-    mood_radio = gr.Radio(choices=list(SCORE_LABELS.values()), label="心情分數")
+with gr.Blocks(title="Emotion AI Detector", css=".gradio-container {background-color: #f9f9f9}") as demo:
+    st_state = gr.State(AppState())
+    
+    gr.Markdown("# 🎭 AI 情緒即時偵測系統")
     
-    # 串流設定
-    cam.stream(
+    with gr.Row():
+        with gr.Column(scale=2):
+            # 串流組件
+            input_cam = gr.Image(sources=["webcam"], streaming=True, type="numpy", label="即時視訊")
+            
+            with gr.Row():
+                btn_reset = gr.Button("🔄 重新辨識", variant="secondary")
+                btn_stop = gr.Button("⏹ 停止", variant="stop")
+        
+        with gr.Column(scale=1):
+            # 結果顯示組件
+            hint_box = gr.HTML(_hint_html("請開啟攝影機，並按「Record」開始辨識。"))
+            result_box = gr.HTML(_result_card_html("unknown", None))
+            mood_radio = gr.Radio(
+                choices=["1（心情差）", "2（不太好）", "3（普通）", "4（不錯）", "5（超棒）"],
+                label="系統判定心情等級",
+                interactive=False,
+                value="3（普通）"
+            )
+
+    # --- 事件綁定 ---
+    
+    # 串流主邏輯: queue=False 與 show_progress="hidden" 是流暢關鍵
+    input_cam.stream(
         fn=on_stream,
-        inputs=[cam, st],
-        outputs=[cam, result_html, mood_radio, gr.HTML(), st, gr.Button()],
-        show_progress="hidden", # 隱藏進度條可以減少 UI 負擔
-        queue=False # 關鍵：不進入隊列，直接拋棄過期請求
+        inputs=[input_cam, st_state],
+        outputs=[input_cam, result_box, mood_radio, hint_box, st_state],
+        show_progress="hidden",
+        queue=False
     )
 
+    # 重新辨識按鈕
+    def restart_app():
+        return (None, _result_card_html("unknown", None), "3（普通）", _hint_html("系統已重置，請重新開始。"), AppState())
+    
+    btn_reset.click(
+        fn=restart_app,
+        outputs=[input_cam, result_box, mood_radio, hint_box, st_state]
+    )
+
+    # 停止按鈕
+    def stop_app(curr_st: AppState):
+        curr_st.running = False
+        return _hint_html("偵測已停止。"), curr_st
+    
+    btn_stop.click(fn=stop_app, inputs=[st_state], outputs=[hint_box, st_state])
+
+# =========================
+# 7. 啟動伺服器
+# =========================
 if __name__ == "__main__":
-    demo.launch(server_name="0.0.0.0", server_port=7860)
+    # 使用 share=False 減少網路延遲造成的卡頓
+    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)