File size: 22,443 Bytes
25f60e9 | 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 | 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
DETECTOR_BACKEND = "mtcnn" # 想快一點可改 "opencv"
ALIGN_FACE = True
# =========================
# 情緒中文 + 分數映射(7 -> 5)
# =========================
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",
}
# 你要的:把 7 種情緒塞進 5 分心情分數
EMO_TO_SCORE = {
"angry": 1,
"disgust": 1,
"fear": 1,
"sad": 2,
"neutral": 3,
"surprise": 4,
"happy": 5,
"unknown": 3,
}
# ### [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)",
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
# =========================
@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
# ### [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>
"""
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 _upload_hint_before() -> str:
return _hint_html("請上傳一張清楚的臉部照片(臉越大越準)。")
def _upload_hint_done() -> str:
return _hint_html("已完成圖片辨識,可按「重新上傳圖片辨識」再次辨識。")
def _upload_hint_stopped() -> str:
return _hint_html("已停止圖片辨識。可按「重新上傳圖片辨識」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>
"""
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: 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
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]]
) -> 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 = 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 prev_bbox is not None:
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]
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
# ### [整合需求 新增] ###
st.final_score = 3
# ######################
return st
def _reset_state_for_upload(st: AppState) -> AppState:
st.running = False
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
# =========================
# Camera streaming
# =========================
def on_stream(frame_rgb: np.ndarray, st: AppState):
# 上傳模式不走攝影機流程
if st.mode != "攝影機辨識":
return (
gr.update(), # cam
gr.update(), # result
gr.update(), # mood
gr.update(value=_upload_hint_before()),
st,
gr.update(value="重新上傳圖片辨識"),
)
# ✅ 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))
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"),
)
# ✅ 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"),
)
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
# 延遲確認
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
# ### [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"),
)
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"),
)
# =========================
# Upload image
# =========================
def on_upload(img: np.ndarray, st: AppState):
if st.mode != "上傳圖片辨識":
return (
gr.update(), gr.update(), st,
gr.update(value=_camera_hint_before_start()),
gr.update(value="重新攝影機辨識")
)
st = _reset_state_for_upload(st)
if img is None:
return (
gr.update(value=_upload_hint_before()),
gr.update(value=_score_radio_value(3)),
st,
gr.update(value=_upload_hint_before()),
gr.update(value="重新上傳圖片辨識"),
)
small = _downsample_rgb(img, 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, None)
if pick is None or pick.get("face") is None:
return (
gr.update(value=_hint_html("沒有偵測到人臉,請換一張更清楚、臉更大的照片。")),
gr.update(value=_score_radio_value(3)),
st,
gr.update(value=_upload_hint_before()),
gr.update(value="重新上傳圖片辨識"),
)
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:
return (
gr.update(value=_hint_html("辨識失敗,請換一張照片再試一次。")),
gr.update(value=_score_radio_value(3)),
st,
gr.update(value=_upload_hint_before()),
gr.update(value="重新上傳圖片辨識"),
)
top_key = max(emo_dict, key=lambda k: float(emo_dict[k]))
top_conf = float(emo_dict[top_key])
st.final_emo = top_key
st.final_conf = top_conf
# ### [整合需求 新增] ###
# 圖片辨識完成,存入分數
st.final_score = EMO_TO_SCORE.get(top_key, 3)
# ######################
st.finished = True
return (
gr.update(value=_result_card_html(top_key, top_conf)),
gr.update(value=_score_radio_value(EMO_TO_SCORE.get(top_key, 3))),
st,
gr.update(value=_upload_hint_done()),
gr.update(value="重新上傳圖片辨識"),
)
# =========================
# Mode / Buttons
# =========================
def on_mode_change(mode: str, st: AppState):
st.mode = mode
if mode == "攝影機辨識":
st = _reset_state_for_camera(st)
return (
gr.update(visible=True), # cam
gr.update(visible=False, value=None), # upload
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()),
st,
gr.update(value="重新攝影機辨識"),
)
else:
st = _reset_state_for_upload(st)
return (
gr.update(visible=False), # cam
gr.update(visible=True, value=None), # upload
gr.update(value=_upload_hint_before()), # result
gr.update(value=_score_radio_value(3)), # mood
gr.update(value=_upload_hint_before()), # hint
st,
gr.update(value="重新上傳圖片辨識"),
)
def on_restart(st: AppState):
if st.mode == "攝影機辨識":
st = _reset_state_for_camera(st)
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
gr.update(), # upload
)
else:
st = _reset_state_for_upload(st)
return (
gr.update(), # cam
gr.update(value=_upload_hint_before()), # result
gr.update(value=_score_radio_value(3)), # mood
gr.update(value=_upload_hint_before()), # hint
st,
gr.update(value="重新上傳圖片辨識"),
gr.update(value=None), # upload clear
)
def on_stop(st: AppState):
if st.mode == "攝影機辨識":
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"),
gr.update(),
)
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"),
gr.update(),
)
# 上傳模式:停止 → 回到可重新上傳
st = _reset_state_for_upload(st)
return (
gr.update(),
gr.update(value=_hint_html("已停止圖片辨識。")),
gr.update(value=_score_radio_value(3)),
gr.update(value=_upload_hint_stopped()),
st,
gr.update(value="重新上傳圖片辨識"),
gr.update(value=None),
)
# =========================
# 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") as demo:
st = gr.State(AppState())
gr.Markdown("## 情緒辨識")
gr.Markdown("請先選擇辨識方式:**攝影機** 或 **上傳圖片**。")
mode = gr.Radio(
choices=["攝影機辨識", "上傳圖片辨識"],
value="攝影機辨識",
label="辨識方式",
)
hint = gr.HTML(_camera_hint_before_start())
cam = gr.Image(
sources=["webcam"],
streaming=True,
type="numpy",
label="攝影機",
visible=True,
)
upload = gr.Image(
sources=["upload"],
type="numpy",
label="上傳圖片",
visible=False,
)
with gr.Row():
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)"))
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,
)
mode.change(
fn=on_mode_change,
inputs=[mode, st],
outputs=[cam, upload, result, mood, hint, st, btn_restart],
show_progress="minimal",
)
cam.stream(
fn=on_stream,
inputs=[cam, st],
outputs=[cam, result, mood, hint, st, btn_restart],
show_progress="minimal",
)
upload.change(
fn=on_upload,
inputs=[upload, st],
outputs=[result, mood, st, hint, btn_restart],
show_progress="minimal",
)
btn_restart.click(
fn=on_restart,
inputs=[st],
outputs=[cam, result, mood, hint, st, btn_restart, upload],
show_progress="minimal",
)
btn_stop.click(
fn=on_stop,
inputs=[st],
outputs=[cam, result, mood, hint, st, btn_restart, upload],
show_progress="minimal",
)
demo.launch(server_name="0.0.0.0", server_port=7860, share=False) |