File size: 12,680 Bytes
25f60e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
324b70f
 
25f60e9
 
 
 
324b70f
25f60e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
324b70f
25f60e9
 
324b70f
25f60e9
 
 
 
 
 
 
 
 
 
 
 
324b70f
25f60e9
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
324b70f
25f60e9
 
 
 
 
 
 
324b70f
25f60e9
 
324b70f
25f60e9
 
 
 
 
 
 
 
 
 
 
 
 
 
324b70f
 
 
 
 
25f60e9
 
 
 
 
 
 
 
 
324b70f
25f60e9
324b70f
25f60e9
 
 
 
 
 
324b70f
25f60e9
 
 
 
 
 
 
 
324b70f
25f60e9
 
 
324b70f
 
25f60e9
 
 
324b70f
25f60e9
 
324b70f
25f60e9
324b70f
25f60e9
 
324b70f
 
25f60e9
 
 
 
324b70f
 
 
 
25f60e9
 
 
 
 
 
 
 
324b70f
c2c53b0
25f60e9
 
 
 
 
 
 
 
 
 
324b70f
25f60e9
 
324b70f
25f60e9
 
 
 
324b70f
25f60e9
 
 
324b70f
c2c53b0
324b70f
25f60e9
 
324b70f
25f60e9
 
 
324b70f
 
 
 
25f60e9
 
 
 
324b70f
25f60e9
 
 
 
 
 
324b70f
25f60e9
 
 
 
 
324b70f
25f60e9
 
 
 
 
 
 
 
324b70f
25f60e9
324b70f
25f60e9
324b70f
25f60e9
 
324b70f
25f60e9
324b70f
 
c2c53b0
324b70f
25f60e9
 
 
324b70f
25f60e9
 
 
324b70f
 
 
25f60e9
 
324b70f
 
 
 
c2c53b0
324b70f
25f60e9
 
324b70f
c2c53b0
 
 
324b70f
 
 
c2c53b0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
324b70f
c2c53b0
 
 
 
 
 
324b70f
c2c53b0
 
 
 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
import time
from dataclasses import dataclass, field
from typing import Optional, Dict, Tuple, List

import gradio as gr
import numpy as np
from PIL import Image

from deepface import DeepFace


# =========================
# 參數(可微調)
# =========================
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

# 建議改為 "opencv" 穩定性較高
DETECTOR_BACKEND = "opencv" 
ALIGN_FACE = True


# =========================
# 情緒中文 + 分數映射
# =========================
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,
}

# 供外部主程式呼叫的介面
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)",
    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]]


# =========================
# 狀態 (已移除 mode 欄位)
# =========================
@dataclass
class AppState:
    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

    # 儲存整數分數
    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>"""

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(")")

    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>
    """

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
    h, w = frame.shape[:2]
    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:
    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
    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
    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))
        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 prev_bbox is not None:
        best, best_i = None, 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]
    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.final_score = 3
    return st


# =========================
# Camera streaming
# =========================
def on_stream(frame_rgb: np.ndarray, st: AppState):
    # 移除模式檢查,直接執行

    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))
            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=result_html), gr.update(value=mood_val), gr.update(value=hint_html), st, gr.update(value="重新攝影機辨識")

    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")

    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")

    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)

    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")

    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]
    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")

    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")

    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
    else:
        st.ema_scores = EMA_ALPHA * vec + (1.0 - EMA_ALPHA) * st.ema_scores

    stable_idx = int(np.argmax(st.ema_scores))
    stable_key = st.emo_keys[stable_idx]
    st.stable_emo = stable_key

    if st.candidate_emo != stable_key:
        st.candidate_emo = stable_key; st.candidate_since = now
    else:
        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)

    if confirmed and st.final_emo is None:
        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)), 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")


# =========================
# Buttons Logic (Removed Upload)
# =========================

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")

def on_stop(st: AppState):
    st.running = False; st.finished = True
    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")

css = """#app_container { max-width: 960px; margin: 0 auto; } .gradio-container { background: #f1f5f9 !important; }"""

if __name__ == "__main__":
    with gr.Blocks(title="Emotion Detector", css=css) 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(
            sources=["webcam"],
            streaming=True,
            type="numpy",
            label="攝影機",
            visible=True,
        )

        with gr.Row():
            btn_restart = gr.Button("重新攝影機辨識", variant="primary")
            btn_stop = gr.Button("停止", variant="secondary")

        gr.Markdown("### 辨識結果")
        result = gr.HTML(_hint_html("等待影像…(尚未開始串流)"))

        gr.Markdown("### 心情分數(系統判定)")
        mood = gr.Radio(
            choices=SCORE_CHOICES,
            value=_score_radio_value(3),
            label="心情分數",
            interactive=False,
        )

        cam.stream(
            fn=on_stream,
            inputs=[cam, st],
            outputs=[cam, result, mood, hint, st, btn_restart],
            show_progress="minimal",
        )

        btn_restart.click(
            fn=on_restart,
            inputs=[st],
            outputs=[cam, result, mood, hint, st, btn_restart],
            show_progress="minimal",
        )

        btn_stop.click(
            fn=on_stop,
            inputs=[st],
            outputs=[cam, result, mood, hint, st, btn_restart],
            show_progress="minimal",
        )

    demo.launch(server_name="0.0.0.0", server_port=7860, share=False)