Update emotion.py

emotion.py

@@ -1,73 +1,35 @@
 import time
-import threading
 from dataclasses import dataclass, field
 from typing import Optional, Dict, Tuple, List
 
 import gradio as gr
 import numpy as np
-from PIL import Image, ImageDraw
+from PIL import Image
 
 from deepface import DeepFace
 
 
+# ✅ 避免 css 未定義造成 NameError（不影響功能）
+css = ""
+
+
 # =========================
-# 參數（優先順：快）
+# 參數（可微調）
 # =========================
-ANALYZE_EVERY_SEC = 1.2     # ✅ 降頻率（原 0.8）
-DOWNSAMPLE_W = 480          # ✅ 降解析（原 720）
+ANALYZE_EVERY_SEC = 0.8
+DOWNSAMPLE_W = 720
 EMA_ALPHA = 0.45
 CONF_TH = 40.0
 SWITCH_CONFIRM_SEC = 2.5
 IOU_TH = 0.25
-ZOOM_FACTOR = 1.25          # ✅ 稍微降 zoom（減少失真與負擔）
+ZOOM_FACTOR = 1.5
 
-DETECTOR_BACKEND = "opencv" # ✅ 改快（原 mtcnn）
+DETECTOR_BACKEND = "mtcnn"     # 想快一點可改 "opencv"
 ALIGN_FACE = True
 
-# 防誤判（保留）
-MIN_FACE_AREA_RATIO = 0.05
-MIN_DET_CONF = 0.90
-
 
 # =========================
-# Warm-up（優先順：按 Record 不要等）
-# =========================
-_WARMED = False
-
-def _warmup_models():
-    global _WARMED
-    if _WARMED:
-        return
-    _WARMED = True
-    try:
-        dummy = np.zeros((224, 224, 3), dtype=np.uint8)
-        # detector warmup
-        try:
-            DeepFace.extract_faces(
-                img_path=dummy,
-                detector_backend=DETECTOR_BACKEND,
-                enforce_detection=False,
-                align=ALIGN_FACE,
-            )
-        except Exception:
-            pass
-        # emotion model warmup
-        try:
-            DeepFace.analyze(
-                img_path=dummy,
-                actions=["emotion"],
-                enforce_detection=False,
-            )
-        except Exception:
-            pass
-    except Exception:
-        pass
-
-threading.Thread(target=_warmup_models, daemon=True).start()
-
-
-# =========================
-# 情緒中文 + 分數映射
+# 情緒中文 + 分數映射（7 -> 5）
 # =========================
 EMO_ZH = {
     "angry": "生氣",
@@ -80,6 +42,7 @@ EMO_ZH = {
     "unknown": "未知",
 }
 
+# 你要的：把 7 種情緒塞進 5 分心情分數
 EMO_TO_SCORE = {
     "angry": 1,
     "disgust": 1,
@@ -91,6 +54,9 @@ EMO_TO_SCORE = {
     "unknown": 3,
 }
 
+def get_emotion_score(emo: str) -> int:
+    return EMO_TO_SCORE.get(emo, 3)
+
 SCORE_LABELS = {
     1: "1（心情差）",
     2: "2（不太好）",
@@ -106,72 +72,101 @@ SCORE_CHOICES = [SCORE_LABELS[i] for i in [1, 2, 3, 4, 5]]
 # =========================
 @dataclass
 class AppState:
+    mode: str = "攝影機辨識" 
+
     running: bool = True
     finished: bool = False
     last_analyze_t: float = 0.0
 
+    # tracking
     track_bbox: Optional[Tuple[int, int, int, int]] = None
 
+    # smoothing
     ema_scores: Optional[np.ndarray] = None
     emo_keys: List[str] = field(default_factory=list)
 
+    # stable/candidate
     stable_emo: str = "unknown"
     candidate_emo: Optional[str] = None
     candidate_since: Optional[float] = None
 
+    # final
     final_emo: Optional[str] = None
     final_conf: Optional[float] = None
-    final_score: int = 3
 
-    last_face_t: float = 0.0
-    face_in_box: bool = False
+    final_score: int = 3  
 
 
 # =========================
-# UI HTML
+# UI HTML (強制黑色文字)
 # =========================
 def _hint_html(msg: str) -> str:
+    # 加入 color:#000000 強制黑色
     return f"""
     <div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#000000;">
       {msg}
     </div>
     """
 
+
 def _camera_hint_before_start() -> str:
     return _hint_html(
         "請先按「Click to access webcam / 允許」開啟攝影機；"
         "接著，請按「錄製（Record）」開始。"
     )
 
+
 def _camera_hint_done() -> str:
     return _hint_html("已完成辨識，可按「重新攝影機辨識」再次進行辨識。")
 
+
 def _camera_hint_stopped() -> str:
     return _hint_html("已停止辨識。可按「重新攝影機辨識」再試一次。")
 
+
 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("）")
+
+    # ✅ 強制設定 color: #000000
     return f"""
-    <div style="border-radius:16px;padding:20px;border:1px solid #E6E6E6;background:#FFFFFF;color:#000000;">
-      <div style="font-size:14px;color:#000000;margin-bottom:8px;">辨識結果</div>
-      <div style="font-size:42px;font-weight:800;line-height:1.1;margin-bottom:14px;color:#000000;">{zh}</div>
-      <div style="font-size:16px;color:#000000;margin-bottom:6px;">心情分數：{score}（{score_desc}）</div>
-      <div style="font-size:14px;color:#000000;">信心值：{conf_txt}</div>
+    <div style="
+        border-radius:16px;
+        padding:20px;
+        border:1px solid #E6E6E6;
+        background:#FFFFFF;
+        color:#000000; 
+    ">
+      <div style="font-size:14px;color:#000000;margin-bottom:8px;">
+        辨識結果
+      </div>
+      <div style="
+        font-size:42px;
+        font-weight:800;
+        line-height:1.1;
+        margin-bottom:14px;
+        color:#000000;
+      ">
+        {zh}
+      </div>
+      <div style="font-size:16px;color:#000000;margin-bottom:6px;">
+        心情分數：{score}（{score_desc}）
+      </div>
+      <div style="font-size:14px;color:#000000;">
+        信心值：{conf_txt}
+      </div>
     </div>
     """
 
+
 def _score_radio_value(score: int) -> str:
     score = int(score)
     score = min(5, max(1, score))
     return SCORE_LABELS[score]
 
 
-# =========================
-# 影像工具
-# =========================
 def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
     if frame is None:
         return None
@@ -185,66 +180,28 @@ def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
     return np.array(img)
 
 def _zoom_center(frame: np.ndarray, zoom: float) -> np.ndarray:
+    """
+    裁切畫面中心以模擬數位變焦。
+    zoom: 放大倍率 (例如 1.5)
+    """
     if frame is None or zoom <= 1.0:
         return frame
+        
     h, w = frame.shape[:2]
+    
+    # 計算新的寬高
     new_w = int(w / zoom)
     new_h = int(h / zoom)
+    
+    # 計算起始點 (讓裁切框置中)
     start_x = (w - new_w) // 2
     start_y = (h - new_h) // 2
-    return frame[start_y:start_y + new_h, start_x:start_x + new_w]
-
-
-# =========================
-# 引導框（永遠畫）
-# =========================
-GUIDE_W_RATIO = 0.55
-GUIDE_H_RATIO = 0.70
-GUIDE_Y_OFFSET = 0.00
-
-def _guide_box(frame: np.ndarray) -> Tuple[int, int, int, int]:
-    h, w = frame.shape[:2]
-    gw = int(w * GUIDE_W_RATIO)
-    gh = int(h * GUIDE_H_RATIO)
-    cx = w // 2
-    cy = int(h * (0.5 + GUIDE_Y_OFFSET))
-    x1 = max(0, cx - gw // 2)
-    y1 = max(0, cy - gh // 2)
-    x2 = min(w - 1, cx + gw // 2)
-    y2 = min(h - 1, cy + gh // 2)
-    return x1, y1, x2, y2
-
-def _bbox_center_in_box(bbox_xywh: Tuple[float, float, float, float], box_xyxy: Tuple[int, int, int, int]) -> bool:
-    x, y, w, h = bbox_xywh
-    cx = x + w / 2.0
-    cy = y + h / 2.0
-    x1, y1, x2, y2 = box_xyxy
-    return (x1 <= cx <= x2) and (y1 <= cy <= y2)
-
-def _draw_guide_overlay(frame_rgb: np.ndarray, detected_in_box: bool) -> np.ndarray:
-    img = Image.fromarray(frame_rgb)
-    draw = ImageDraw.Draw(img)
-
-    x1, y1, x2, y2 = _guide_box(frame_rgb)
-    color = (0, 200, 0) if detected_in_box else (220, 0, 0)
-
-    h, w = frame_rgb.shape[:2]
-    thickness = max(3, int(min(w, h) * 0.008))
-    for t in range(thickness):
-        draw.rectangle([x1 - t, y1 - t, x2 + t, y2 + t], outline=color)
-
-    msg = "已偵測到人臉，開始辨識情緒中…" if detected_in_box else "未偵測到人臉，請把臉放進框內"
-    tx = x1
-    ty = max(0, y1 - int(thickness * 6))
-    draw.rectangle([tx, ty, tx + 360, ty + 32], fill=(255, 255, 255))
-    draw.text((tx + 6, ty + 6), msg, fill=(0, 0, 0))
-
-    return np.array(img)
+    
+    # 進行裁切
+    cropped = frame[start_y : start_y + new_h, start_x : start_x + new_w]
+    return cropped
 
 
-# =========================
-# Tracking / IoU
-# =========================
 def _iou(a: Tuple[int, int, int, int], b: Tuple[int, int, int, int]) -> float:
     ax, ay, aw, ah = a
     bx, by, bw, bh = b
@@ -260,9 +217,14 @@ def _iou(a: Tuple[int, int, int, int], b: Tuple[int, int, int, int]) -> float:
     union = aw * ah + bw * bh - inter
     return inter / max(1e-6, union)
 
-def _pick_face_by_tracking(faces: List[Dict], prev_bbox: Optional[Tuple[int, int, int, int]]):
+
+def _pick_face_by_tracking(
+    faces: List[Dict],
+    prev_bbox: Optional[Tuple[int, int, int, int]]
+) -> Tuple[Optional[Dict], Optional[Tuple[int, int, int, int]]]:
     if not faces:
         return None, None
+
     cand = []
     for f in faces:
         fa = f.get("facial_area", {}) or {}
@@ -304,47 +266,30 @@ def _reset_state_for_camera(st: AppState) -> AppState:
     st.final_emo = None
     st.final_conf = None
     st.final_score = 3
-    st.last_face_t = 0.0
-    st.face_in_box = False
     return st
 
 
-def _is_real_face(pick: Dict, bbox_full_xywh: Tuple[float, float, float, float], frame_hw: Tuple[int, int]) -> bool:
-    fh, fw = frame_hw
-    x, y, w, h = bbox_full_xywh
-    area_ratio = (w * h) / max(1.0, float(fw * fh))
-    if area_ratio < MIN_FACE_AREA_RATIO:
-        return False
-    det_conf = pick.get("confidence", None)
-    if det_conf is not None:
-        try:
-            if float(det_conf) < MIN_DET_CONF:
-                return False
-        except Exception:
-            pass
-    return True
-
-
 # =========================
-# Stream（優先順）
+# Camera streaming
 # =========================
 def on_stream(frame_rgb: np.ndarray, st: AppState):
     if st.finished or (not st.running):
         cam_visible = False
+
         if st.final_emo:
-            return (
-                gr.update(visible=cam_visible),
-                gr.update(value=_result_card_html(st.final_emo, st.final_conf)),
-                gr.update(value=_score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))),
-                gr.update(value=_camera_hint_done()),
-                st,
-                gr.update(value="重新攝影機辨識"),
-            )
+            result_html = _result_card_html(st.final_emo, st.final_conf)
+            mood_val = _score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))
+            hint_html = _camera_hint_done()
+        else:
+            result_html = _hint_html("尚未完成辨識。")
+            mood_val = _score_radio_value(3)
+            hint_html = _camera_hint_stopped()
+
         return (
             gr.update(visible=cam_visible),
-            gr.update(value=_hint_html("尚未完成辨識。")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_stopped()),
+            gr.update(value=result_html),
+            gr.update(value=mood_val),
+            gr.update(value=hint_html),
             st,
             gr.update(value="重新攝影機辨識"),
         )
@@ -358,128 +303,65 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
             st,
             gr.update(value="重新攝影機辨識"),
         )
-
+    
     frame_rgb = _zoom_center(frame_rgb, ZOOM_FACTOR)
-    now = time.time()
 
-    # ✅ 先畫框（永遠立即有框），不等 detector
-    detected_recent = st.face_in_box and (now - st.last_face_t) < 1.0
-    annotated_fast = _draw_guide_overlay(frame_rgb, detected_recent)
-
-    # ✅ 如果還沒到分析時間，直接回傳畫框（超順）
+    now = time.time()
     if now - st.last_analyze_t < ANALYZE_EVERY_SEC:
+        show = st.stable_emo or "unknown"
         return (
-            gr.update(visible=True, value=annotated_fast),
-            gr.update(value=_hint_html("已偵測到人臉，開始辨識情緒中…" if detected_recent else "未偵測到人臉，請把臉放進框內")),
-            gr.update(value=_score_radio_value(3)),
+            gr.update(visible=True),
+            gr.update(value=_result_card_html(show, st.final_conf)),
+            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
             gr.update(value=_camera_hint_before_start()),
             st,
             gr.update(value="重新攝影機辨識"),
         )
 
-    # 到時間才做一次重工作（低頻）
     st.last_analyze_t = now
-    small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
 
-    try:
-        faces = DeepFace.extract_faces(
-            img_path=small,
-            detector_backend=DETECTOR_BACKEND,
-            enforce_detection=True,
-            align=ALIGN_FACE,
-        )
-    except Exception:
-        faces = []
+    small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
 
+    # ✅ 這裡固定 enforce_detection=False（避免沒臉就丟例外，造成卡頓/誤判）
+    faces = DeepFace.extract_faces(
+        img_path=small,
+        detector_backend=DETECTOR_BACKEND,
+        enforce_detection=False,
+        align=ALIGN_FACE,
+    )
     pick, bbox = _pick_face_by_tracking(faces, st.track_bbox)
-
     if pick is None or bbox is None or pick.get("face") is None:
-        st.track_bbox = None
-        st.face_in_box = False
-        st.last_face_t = now
-        st.stable_emo = "unknown"
-        annotated = _draw_guide_overlay(frame_rgb, False)
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("未偵測到人臉，請把臉放進框內")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    sh, sw = small.shape[:2]
-    fh, fw = frame_rgb.shape[:2]
-    sx = fw / max(1, sw)
-    sy = fh / max(1, sh)
-    x, y, w, h = bbox
-    bbox_full = (x * sx, y * sy, w * sx, h * sy)
-
-    if not _is_real_face(pick, bbox_full, (fh, fw)):
-        st.track_bbox = None
-        st.face_in_box = False
-        st.last_face_t = now
-        annotated = _draw_guide_overlay(frame_rgb, False)
+        show = st.stable_emo or "unknown"
         return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("未偵測到人臉，請把臉放進框內")),
-            gr.update(value=_score_radio_value(3)),
+            gr.update(visible=True),
+            gr.update(value=_result_card_html(show, st.final_conf)),
+            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
             gr.update(value=_camera_hint_before_start()),
             st,
             gr.update(value="重新攝影機辨識"),
         )
 
-    guide = _guide_box(frame_rgb)
-    in_box = _bbox_center_in_box(bbox_full, guide)
-
-    st.last_face_t = now
-    st.face_in_box = in_box
     st.track_bbox = bbox
-
-    if not in_box:
-        annotated = _draw_guide_overlay(frame_rgb, False)
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("已偵測到人臉，但請把臉放進框內")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
-    # 只有臉在框內才分析情緒
     face = pick["face"]
     if face.dtype != np.uint8:
         face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
 
-    try:
-        result = DeepFace.analyze(
-            img_path=face,
-            actions=["emotion"],
-            enforce_detection=True,
-        )
-    except Exception:
-        annotated = _draw_guide_overlay(frame_rgb, False)
-        st.face_in_box = False
-        st.last_face_t = now
-        return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("未偵測到人臉，請把臉放進框內")),
-            gr.update(value=_score_radio_value(3)),
-            gr.update(value=_camera_hint_before_start()),
-            st,
-            gr.update(value="重新攝影機辨識"),
-        )
-
+    # ✅ 這裡也固定 enforce_detection=False（避免偶發抓不到臉時丟例外）
+    result = DeepFace.analyze(
+        img_path=face,
+        actions=["emotion"],
+        enforce_detection=False,
+    )
     if isinstance(result, list):
         result = result[0]
     emo_dict = result.get("emotion", None)
+
     if not isinstance(emo_dict, dict) or len(emo_dict) == 0:
-        annotated = _draw_guide_overlay(frame_rgb, True)
+        show = st.stable_emo or "unknown"
         return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("已偵測到人臉，開始辨識情緒中…")),
-            gr.update(value=_score_radio_value(3)),
+            gr.update(visible=True),
+            gr.update(value=_result_card_html(show, st.final_conf)),
+            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
             gr.update(value=_camera_hint_before_start()),
             st,
             gr.update(value="重新攝影機辨識"),
@@ -489,11 +371,11 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
     top_conf = float(emo_dict[top_key])
 
     if top_conf < CONF_TH:
-        annotated = _draw_guide_overlay(frame_rgb, True)
+        show = st.stable_emo or "unknown"
         return (
-            gr.update(visible=True, value=annotated),
-            gr.update(value=_hint_html("已偵測到人臉，開始辨識情緒中…")),
-            gr.update(value=_score_radio_value(3)),
+            gr.update(visible=True),
+            gr.update(value=_result_card_html(show, st.final_conf)),
+            gr.update(value=_score_radio_value(EMO_TO_SCORE.get(show, 3))),
             gr.update(value=_camera_hint_before_start()),
             st,
             gr.update(value="重新攝影機辨識"),
@@ -512,6 +394,7 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
     stable_key = st.emo_keys[stable_idx]
     st.stable_emo = stable_key
 
+    # 延遲確認
     if st.candidate_emo != stable_key:
         st.candidate_emo = stable_key
         st.candidate_since = now
@@ -528,8 +411,10 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
         st.final_emo = stable_key
         st.final_conf = top_conf
         st.final_score = EMO_TO_SCORE.get(stable_key, 3)
+
         st.running = False
         st.finished = True
+
         return (
             gr.update(visible=False),
             gr.update(value=_result_card_html(stable_key, top_conf)),
@@ -539,9 +424,8 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
             gr.update(value="重新攝影機辨識"),
         )
 
-    annotated = _draw_guide_overlay(frame_rgb, True)
     return (
-        gr.update(visible=True, value=annotated),
+        gr.update(visible=True),
         gr.update(value=_result_card_html(stable_key, top_conf)),
         gr.update(value=_score_radio_value(EMO_TO_SCORE.get(stable_key, 3))),
         gr.update(value=_camera_hint_before_start()),
@@ -551,33 +435,35 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
 
 
 # =========================
-# Buttons
+# Mode / Buttons
 # =========================
 def on_restart(st: AppState):
     st = _reset_state_for_camera(st)
     return (
-        gr.update(visible=True, value=None),  # ✅ 清掉上一張畫面
-        gr.update(value=_hint_html("等待影像…（尚未開始串流）")),
-        gr.update(value=_score_radio_value(3)),
-        gr.update(value=_camera_hint_before_start()),
+        gr.update(visible=True),                               
+        gr.update(value=_hint_html("等待影像…（尚未開始串流）")),  
+        gr.update(value=_score_radio_value(3)),                
+        gr.update(value=_camera_hint_before_start()),          
         st,
-        gr.update(value="重新攝影機辨識"),
+        gr.update(value="重新攝影機辨識"),                      
     )
 
+
 def on_stop(st: AppState):
     st.running = False
     st.finished = True
     if st.final_emo is None:
         return (
-            gr.update(visible=False, value=None),
+            gr.update(visible=False),
             gr.update(value=_hint_html("已停止辨識。")),
             gr.update(value=_score_radio_value(3)),
             gr.update(value=_camera_hint_stopped()),
             st,
             gr.update(value="重新攝影機辨識"),
         )
+
     return (
-        gr.update(visible=False, value=None),
+        gr.update(visible=False),
         gr.update(value=_result_card_html(st.final_emo, st.final_conf)),
         gr.update(value=_score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))),
         gr.update(value=_camera_hint_done()),
@@ -594,7 +480,7 @@ if __name__ == "__main__":
         st = gr.State(AppState())
 
         gr.Markdown("## 情緒辨識")
-
+        
         hint = gr.HTML(_camera_hint_before_start())
 
         cam = gr.Image(