Update emotion.py

emotion.py

@@ -19,13 +19,13 @@ CONF_TH = 40.0
 SWITCH_CONFIRM_SEC = 2.5
 IOU_TH = 0.25
 
-# 建議改為 "opencv" 穩定性較高
+# 建議改為 "opencv" 穩定性較高，若想維持原狀可改回 "mtcnn"
 DETECTOR_BACKEND = "opencv" 
 ALIGN_FACE = True
 
 
 # =========================
-# 情緒中文 + 分數映射
+# 情緒中文 + 分數映射（7 -> 5）
 # =========================
 EMO_ZH = {
     "angry": "生氣",
@@ -38,6 +38,7 @@ 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,
@@ -49,10 +50,11 @@ EMO_TO_SCORE = {
     "unknown": 3,
 }
 
-# 供外部主程式呼叫的介面
+# ### [整合需求 新增] ###
+# 為了讓主程式 (app.py) 可以呼叫這個轉換邏輯，將其包裝成函式
 def get_emotion_score(emo: str) -> int:
     return EMO_TO_SCORE.get(emo, 3)
-
+# ######################
 
 SCORE_LABELS = {
     1: "1（心情差）",
@@ -65,10 +67,12 @@ SCORE_CHOICES = [SCORE_LABELS[i] for i in [1, 2, 3, 4, 5]]
 
 
 # =========================
-# 狀態 (已移除 mode 欄位)
+# 狀態
 # =========================
 @dataclass
 class AppState:
+    mode: str = "攝影機辨識"  # Default mode
+
     running: bool = True
     finished: bool = False
     last_analyze_t: float = 0.0
@@ -89,92 +93,165 @@ class AppState:
     final_emo: Optional[str] = None
     final_conf: Optional[float] = None
 
-    # 儲存整數分數
+    # ### [整合需求 新增] ###
+    # 用來儲存最後計算出的整數分數 (1~5)，讓外部程式容易讀取
     final_score: int = 3  
+    # ######################
 
 
 # =========================
 # UI HTML
 # =========================
 def _hint_html(msg: str) -> str:
-    return f"""<div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#111;">{msg}</div>"""
+    return f"""
+    <div style="border-radius:14px;padding:14px;border:1px dashed #DADADA;background:#FAFAFA;color:#111;">
+      {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。")
+    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("）")
 
+    # ✅ 結果字體用黑色，避免你說的灰字看不清楚
     return f"""
-    <div style="border-radius:16px;padding:20px;border:1px solid #E6E6E6;background:#FFFFFF;color:#111;">
-      <div style="font-size:14px;color:#444;margin-bottom:8px;">辨識結果</div>
-      <div style="font-size:42px;font-weight:800;line-height:1.1;margin-bottom:14px;color:#000;">{zh}</div>
-      <div style="font-size:16px;color:#111;margin-bottom:6px;">心情分數：<b>{score}</b>（{score_desc}）</div>
-      <div style="font-size:14px;color:#111;">信心值：{conf_txt}</div>
+    <div style="
+        border-radius:16px;
+        padding:20px;
+        border:1px solid #E6E6E6;
+        background:#FFFFFF;
+        color:#111;
+    ">
+      <div style="font-size:14px;color:#444;margin-bottom:8px;">
+        辨識結果
+      </div>
+
+      <div style="
+        font-size:42px;
+        font-weight:800;
+        line-height:1.1;
+        margin-bottom:14px;
+        color:#000;
+      ">
+        {zh}
+      </div>
+
+      <div style="font-size:16px;color:#111;margin-bottom:6px;">
+        心情分數：<b>{score}</b>（{score_desc}）
+      </div>
+
+      <div style="font-size:14px;color:#111;">
+        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]
 
+
 def _downsample_rgb(frame: np.ndarray, target_w: int) -> np.ndarray:
-    if frame is None: return None
+    if frame is None:
+        return None
     h, w = frame.shape[:2]
-    if w <= target_w: return frame
+    if w <= target_w:
+        return frame
     scale = target_w / w
     new_h = max(1, int(h * scale))
     img = Image.fromarray(frame)
     img = img.resize((target_w, new_h))
     return np.array(img)
 
-def _iou(a, b) -> float:
+
+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
     ax2, ay2 = ax + aw, ay + ah
     bx2, by2 = bx + bw, by + bh
+
     ix1, iy1 = max(ax, bx), max(ay, by)
     ix2, iy2 = min(ax2, bx2), min(ay2, by2)
     iw, ih = max(0, ix2 - ix1), max(0, iy2 - iy1)
     inter = iw * ih
-    if inter <= 0: return 0.0
+    if inter <= 0:
+        return 0.0
     union = aw * ah + bw * bh - inter
     return inter / max(1e-6, union)
 
-def _pick_face_by_tracking(faces, prev_bbox):
-    if not faces: return None, None
+
+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 {}
-        x, y, w, h = int(fa.get("x",0)), int(fa.get("y",0)), int(fa.get("w",0)), int(fa.get("h",0))
+        x = int(fa.get("x", 0) or 0)
+        y = int(fa.get("y", 0) or 0)
+        w = int(fa.get("w", 0) or 0)
+        h = int(fa.get("h", 0) or 0)
         if w > 0 and h > 0 and f.get("face") is not None:
             cand.append((f, (x, y, w, h), w * h))
-    if not cand: return None, None
+
+    if not cand:
+        return None, None
+
     if prev_bbox is not None:
-        best, best_i = None, 0.0
+        best = None
+        best_i = 0.0
         for f, bb, area in cand:
             i = _iou(prev_bbox, bb)
-            if i > best_i: best_i = i; best = (f, bb)
-        if best is not None and best_i >= IOU_TH: return best[0], best[1]
+            if i > best_i:
+                best_i = i
+                best = (f, bb)
+        if best is not None and best_i >= IOU_TH:
+            return best[0], best[1]
+
     cand.sort(key=lambda x: x[2], reverse=True)
     return cand[0][0], cand[0][1]
 
+
 def _reset_state_for_camera(st: AppState) -> AppState:
-    st.running = True; st.finished = False; st.last_analyze_t = 0.0
-    st.track_bbox = None; st.ema_scores = None; st.emo_keys = []
-    st.stable_emo = "unknown"; st.candidate_emo = None; st.candidate_since = None
-    st.final_emo = None; st.final_conf = None
+    st.running = True
+    st.finished = False
+    st.last_analyze_t = 0.0
+    st.track_bbox = None
+    st.ema_scores = None
+    st.emo_keys = []
+    st.stable_emo = "unknown"
+    st.candidate_emo = None
+    st.candidate_since = None
+    st.final_emo = None
+    st.final_conf = None
+    
+    # ### [整合需求 新增] ###
     st.final_score = 3
+    # ######################
+    
     return st
 
 
@@ -182,10 +259,10 @@ def _reset_state_for_camera(st: AppState) -> AppState:
 # Camera streaming
 # =========================
 def on_stream(frame_rgb: np.ndarray, st: AppState):
-    # 移除模式檢查，直接執行
-
+    # ✅ 完成/停止狀態：不要再顯示「Click to access…/Record…」
     if st.finished or (not st.running):
         cam_visible = False
+
         if st.final_emo:
             result_html = _result_card_html(st.final_emo, st.final_conf)
             mood_val = _score_radio_value(EMO_TO_SCORE.get(st.final_emo, 3))
@@ -194,49 +271,106 @@ def on_stream(frame_rgb: np.ndarray, st: AppState):
             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=result_html), gr.update(value=mood_val), gr.update(value=hint_html), st, gr.update(value="重新攝影機辨識")
 
+        return (
+            gr.update(visible=cam_visible),
+            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"),
+        )
+
+    # ✅ 還沒拿到 frame：提示使用者按允許/Record（而不是亂寫已開啟）
     if frame_rgb is None:
-        return 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")
+        return (
+            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"),
+        )
 
     now = time.time()
     if now - st.last_analyze_t < ANALYZE_EVERY_SEC:
         show = st.stable_emo or "unknown"
-        return 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")
+        return (
+            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"),
+        )
 
     st.last_analyze_t = now
+
     small = _downsample_rgb(frame_rgb, DOWNSAMPLE_W)
-    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)
 
+    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:
         show = st.stable_emo or "unknown"
-        return 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")
+        return (
+            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"),
+        )
 
     st.track_bbox = bbox
     face = pick["face"]
-    if face.dtype != np.uint8: face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
-
-    result = DeepFace.analyze(img_path=face, actions=["emotion"], enforce_detection=False)
-    if isinstance(result, list): result = result[0]
+    if face.dtype != np.uint8:
+        face = np.clip(face * 255.0, 0, 255).astype(np.uint8)
+
+    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:
         show = st.stable_emo or "unknown"
-        return 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")
+        return (
+            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"),
+        )
 
     top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
     top_conf = float(emo_dict[top_key])
 
     if top_conf < CONF_TH:
         show = st.stable_emo or "unknown"
-        return 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")
+        return (
+            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"),
+        )
 
     keys = list(emo_dict.keys())
     vec = np.array([float(emo_dict[k]) for k in keys], dtype=np.float32)
 
     if st.ema_scores is None or st.emo_keys != keys:
-        st.ema_scores = vec; st.emo_keys = keys
+        st.ema_scores = vec
+        st.emo_keys = keys
     else:
         st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores
 
@@ -244,47 +378,110 @@ 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
+        st.candidate_emo = stable_key
+        st.candidate_since = now
     else:
-        if st.candidate_since is None: st.candidate_since = now
+        if st.candidate_since is None:
+            st.candidate_since = now
 
-    confirmed = (st.candidate_since is not None and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC)
+    confirmed = (
+        st.candidate_since is not None
+        and (now - st.candidate_since) >= SWITCH_CONFIRM_SEC
+    )
 
     if confirmed and st.final_emo is None:
-        st.final_emo = stable_key; st.final_conf = top_conf
+        st.final_emo = stable_key
+        st.final_conf = top_conf
+        
+        # ### [整合需求 新增] ###
+        # 在辨識完成的瞬間，順便存入整數分數
         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)), gr.update(value=_score_radio_value(EMO_TO_SCORE.get(stable_key, 3))), gr.update(value=_camera_hint_done()), st, gr.update(value="重新攝影機辨識")
+        # ######################
+
+        st.running = False
+        st.finished = True
+
+        return (
+            gr.update(visible=False),
+            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_done()),
+            st,
+            gr.update(value="重新攝影機辨識"),
+        )
 
-    return 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()), st, gr.update(value="重新攝影機辨識")
+    return (
+        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()),
+        st,
+        gr.update(value="重新攝影機辨識"),
+    )
 
 
 # =========================
-# Buttons Logic (Removed Upload)
+# Mode / Buttons
 # =========================
-
 def on_restart(st: AppState):
     st = _reset_state_for_camera(st)
-    # 回傳值已減少 (移除最後一個 upload update)
-    return 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")
+    return (
+        gr.update(visible=True),                               # cam
+        gr.update(value=_hint_html("等待影像…（尚未開始串流）")),  # result
+        gr.update(value=_score_radio_value(3)),                # mood
+        gr.update(value=_camera_hint_before_start()),          # hint
+        st,
+        gr.update(value="重新攝影機辨識"),                      # btn label
+    )
+
 
 def on_stop(st: AppState):
-    st.running = False; st.finished = True
+    st.running = False
+    st.finished = True
+    # ✅ 停止後也不要再顯示 Click/Record 提示，改成「已停止/可重新」
     if st.final_emo is None:
-        return 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), 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")
+        return (
+            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"),
+        )
 
-css = """#app_container { max-width: 960px; margin: 0 auto; } .gradio-container { background: #f1f5f9 !important; }"""
+    return (
+        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()),
+        st,
+        gr.update(value="重新攝影機辨識"),
+    )
+
+
+# =========================
+# Gradio UI
+# =========================
+# ### [整合需求] 下方的 UI Block 可以保留，
+# 之後整合進 app.py 時，app.py 會只 import 上面的函式，不會執行這裡。
+# 這樣隊友還是可以單獨執行這個檔案來測試。
+css = """
+#app_container { max-width: 960px; margin: 0 auto; }
+.gradio-container { background: #f1f5f9 !important; }
+"""
+
+# 為了方便 app.py 整合，我們把 UI 宣告包成一個函式 render_ui (或是 create_demo)
+# 但為了不改動隊友原本的結構，我們保留下面的寫法，但加上 if __name__ == "__main__"
+# 這樣 app.py import 時不會自動跑出介面
 
 if __name__ == "__main__":
-    with gr.Blocks(title="Emotion Detector", css=css) as demo:
+    with gr.Blocks(title="Emotion Detector") as demo:
         st = gr.State(AppState())
 
         gr.Markdown("## 情緒辨識")
         
-        # 移除了模式選擇 Radio
-        
         hint = gr.HTML(_camera_hint_before_start())
 
         cam = gr.Image(
@@ -299,6 +496,7 @@ if __name__ == "__main__":
             btn_restart = gr.Button("重新攝影機辨識", variant="primary")
             btn_stop = gr.Button("停止", variant="secondary")
 
+        # ✅ 你要的排序：結果在上、分數在下
         gr.Markdown("### 辨識結果")
         result = gr.HTML(_hint_html("等待影像…（尚未開始串流）"))