Spaces:
Running
on
Zero
Running
on
Zero
Update app.py
Browse files
app.py
CHANGED
@@ -15,34 +15,34 @@ import asyncio
|
|
15 |
import traceback
|
16 |
|
17 |
|
18 |
-
model_yolo = YOLO('yolov8l.pt')
|
19 |
-
|
20 |
-
|
21 |
-
dog_breeds = ["Afghan_Hound", "African_Hunting_Dog", "Airedale", "American_Staffordshire_Terrier",
|
22 |
-
"Appenzeller", "Australian_Terrier", "Bedlington_Terrier", "Bernese_Mountain_Dog",
|
23 |
-
"Blenheim_Spaniel", "Border_Collie", "Border_Terrier", "Boston_Bull", "Bouvier_Des_Flandres",
|
24 |
-
"Brabancon_Griffon", "Brittany_Spaniel", "Cardigan", "Chesapeake_Bay_Retriever",
|
25 |
-
"Chihuahua", "Dandie_Dinmont", "Doberman", "English_Foxhound", "English_Setter",
|
26 |
-
"English_Springer", "EntleBucher", "Eskimo_Dog", "French_Bulldog", "German_Shepherd",
|
27 |
-
"German_Short-Haired_Pointer", "Gordon_Setter", "Great_Dane", "Great_Pyrenees",
|
28 |
-
"Greater_Swiss_Mountain_Dog", "Ibizan_Hound", "Irish_Setter", "Irish_Terrier",
|
29 |
-
"Irish_Water_Spaniel", "Irish_Wolfhound", "Italian_Greyhound", "Japanese_Spaniel",
|
30 |
-
"Kerry_Blue_Terrier", "Labrador_Retriever", "Lakeland_Terrier", "Leonberg", "Lhasa",
|
31 |
-
"Maltese_Dog", "Mexican_Hairless", "Newfoundland", "Norfolk_Terrier", "Norwegian_Elkhound",
|
32 |
-
"Norwich_Terrier", "Old_English_Sheepdog", "Pekinese", "Pembroke", "Pomeranian",
|
33 |
-
"Rhodesian_Ridgeback", "Rottweiler", "Saint_Bernard", "Saluki", "Samoyed",
|
34 |
-
"Scotch_Terrier", "Scottish_Deerhound", "Sealyham_Terrier", "Shetland_Sheepdog",
|
35 |
-
"Shih-Tzu", "Siberian_Husky", "Staffordshire_Bullterrier", "Sussex_Spaniel",
|
36 |
-
"Tibetan_Mastiff", "Tibetan_Terrier", "Walker_Hound", "Weimaraner",
|
37 |
-
"Welsh_Springer_Spaniel", "West_Highland_White_Terrier", "Yorkshire_Terrier",
|
38 |
-
"Affenpinscher", "Basenji", "Basset", "Beagle", "Black-and-Tan_Coonhound", "Bloodhound",
|
39 |
-
"Bluetick", "Borzoi", "Boxer", "Briard", "Bull_Mastiff", "Cairn", "Chow", "Clumber",
|
40 |
-
"Cocker_Spaniel", "Collie", "Curly-Coated_Retriever", "Dhole", "Dingo",
|
41 |
-
"Flat-Coated_Retriever", "Giant_Schnauzer", "Golden_Retriever", "Groenendael", "Keeshond",
|
42 |
-
"Kelpie", "Komondor", "Kuvasz", "Malamute", "Malinois", "Miniature_Pinscher",
|
43 |
-
"Miniature_Poodle", "Miniature_Schnauzer", "Otterhound", "Papillon", "Pug", "Redbone",
|
44 |
-
"Schipperke", "Silky_Terrier", "Soft-Coated_Wheaten_Terrier", "Standard_Poodle",
|
45 |
-
"Standard_Schnauzer", "Toy_Poodle", "Toy_Terrier", "Vizsla", "Whippet",
|
46 |
"Wire-Haired_Fox_Terrier"]
|
47 |
|
48 |
class MultiHeadAttention(nn.Module):
|
@@ -141,30 +141,30 @@ async def predict_single_dog(image):
|
|
141 |
topk_probs, topk_indices = torch.topk(probabilities, k=3)
|
142 |
top1_prob = topk_probs[0][0].item()
|
143 |
topk_breeds = [dog_breeds[idx.item()] for idx in topk_indices[0]]
|
144 |
-
|
145 |
# Calculate relative probabilities for display
|
146 |
raw_probs = [prob.item() for prob in topk_probs[0]]
|
147 |
sum_probs = sum(raw_probs)
|
148 |
relative_probs = [f"{(prob/sum_probs * 100):.2f}%" for prob in raw_probs]
|
149 |
-
|
150 |
return top1_prob, topk_breeds, relative_probs
|
151 |
-
|
152 |
|
153 |
async def detect_multiple_dogs(image, conf_threshold=0.3, iou_threshold=0.45):
|
154 |
results = model_yolo(image, conf=conf_threshold, iou=iou_threshold)[0]
|
155 |
dogs = []
|
156 |
boxes = []
|
157 |
for box in results.boxes:
|
158 |
-
if box.cls == 16: # COCO dataset class for dog is 16
|
159 |
xyxy = box.xyxy[0].tolist()
|
160 |
confidence = box.conf.item()
|
161 |
boxes.append((xyxy, confidence))
|
162 |
-
|
163 |
if not boxes:
|
164 |
dogs.append((image, 1.0, [0, 0, image.width, image.height]))
|
165 |
else:
|
166 |
nms_boxes = non_max_suppression(boxes, iou_threshold)
|
167 |
-
|
168 |
for box, confidence in nms_boxes:
|
169 |
x1, y1, x2, y2 = box
|
170 |
w, h = x2 - x1, y2 - y1
|
@@ -174,7 +174,7 @@ async def detect_multiple_dogs(image, conf_threshold=0.3, iou_threshold=0.45):
|
|
174 |
y2 = min(image.height, y2 + h * 0.05)
|
175 |
cropped_image = image.crop((x1, y1, x2, y2))
|
176 |
dogs.append((cropped_image, confidence, [x1, y1, x2, y2]))
|
177 |
-
|
178 |
return dogs
|
179 |
|
180 |
|
@@ -187,24 +187,24 @@ def non_max_suppression(boxes, iou_threshold):
|
|
187 |
boxes = [box for box in boxes if calculate_iou(current[0], box[0]) < iou_threshold]
|
188 |
return keep
|
189 |
|
190 |
-
|
191 |
def calculate_iou(box1, box2):
|
192 |
x1 = max(box1[0], box2[0])
|
193 |
y1 = max(box1[1], box2[1])
|
194 |
x2 = min(box1[2], box2[2])
|
195 |
y2 = min(box1[3], box2[3])
|
196 |
-
|
197 |
intersection = max(0, x2 - x1) * max(0, y2 - y1)
|
198 |
area1 = (box1[2] - box1[0]) * (box1[3] - box1[1])
|
199 |
area2 = (box2[2] - box2[0]) * (box2[3] - box2[1])
|
200 |
-
|
201 |
iou = intersection / float(area1 + area2 - intersection)
|
202 |
return iou
|
203 |
|
204 |
|
205 |
async def process_single_dog(image):
|
206 |
top1_prob, topk_breeds, relative_probs = await predict_single_dog(image)
|
207 |
-
|
208 |
# Case 1: Low confidence - unclear image or breed not in dataset
|
209 |
if top1_prob < 0.2:
|
210 |
error_message = '''
|
@@ -225,7 +225,7 @@ async def process_single_dog(image):
|
|
225 |
return error_message, None, initial_state
|
226 |
|
227 |
breed = topk_breeds[0]
|
228 |
-
|
229 |
# Case 2: High confidence - single breed result
|
230 |
if top1_prob >= 0.45:
|
231 |
description = get_dog_description(breed)
|
@@ -243,7 +243,7 @@ async def process_single_dog(image):
|
|
243 |
"is_multi_dog": False
|
244 |
}
|
245 |
return html_content, image, initial_state
|
246 |
-
|
247 |
# Case 3: Medium confidence - show top 3 breeds with relative probabilities
|
248 |
else:
|
249 |
breeds_html = ""
|
@@ -269,7 +269,38 @@ async def process_single_dog(image):
|
|
269 |
}
|
270 |
return breeds_html, image, initial_state
|
271 |
|
272 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
273 |
async def predict(image):
|
274 |
if image is None:
|
275 |
return "Please upload an image to start.", None, None
|
@@ -291,7 +322,7 @@ async def predict(image):
|
|
291 |
'#A233FF', # ็ดซ่ฒ
|
292 |
'#FF3333', # ็ด
่ฒ
|
293 |
'#33FFB7', # ้็ถ ่ฒ
|
294 |
-
'#FFE033' # ้้ป่ฒ
|
295 |
]
|
296 |
annotated_image = image.copy()
|
297 |
draw = ImageDraw.Draw(annotated_image)
|
@@ -305,14 +336,14 @@ async def predict(image):
|
|
305 |
|
306 |
for i, (cropped_image, detection_confidence, box) in enumerate(dogs):
|
307 |
color = single_dog_color if len(dogs) == 1 else color_list[i % len(color_list)]
|
308 |
-
|
309 |
# ๅชๅๅ็ไธ็ๆจ่จ
|
310 |
draw.rectangle(box, outline=color, width=4)
|
311 |
label = f"Dog {i+1}"
|
312 |
label_bbox = draw.textbbox((0, 0), label, font=font)
|
313 |
label_width = label_bbox[2] - label_bbox[0]
|
314 |
label_height = label_bbox[3] - label_bbox[1]
|
315 |
-
|
316 |
label_x = box[0] + 5
|
317 |
label_y = box[1] + 5
|
318 |
draw.rectangle(
|
@@ -322,13 +353,13 @@ async def predict(image):
|
|
322 |
width=2
|
323 |
)
|
324 |
draw.text((label_x, label_y), label, fill=color, font=font)
|
325 |
-
|
326 |
top1_prob, topk_breeds, relative_probs = await predict_single_dog(cropped_image)
|
327 |
combined_confidence = detection_confidence * top1_prob
|
328 |
-
|
329 |
# ้ๅง่ณ่จๅก็
|
330 |
dogs_info += f'<div class="dog-info-card" style="border-left: 6px solid {color};">'
|
331 |
-
|
332 |
if combined_confidence < 0.2:
|
333 |
dogs_info += f'''
|
334 |
<div class="dog-info-header" style="background-color: {color}10;">
|
@@ -387,7 +418,7 @@ async def predict(image):
|
|
387 |
<span class="value">{description['Lifespan']}</span>
|
388 |
</div>
|
389 |
</div>
|
390 |
-
|
391 |
<h2 class="section-title">
|
392 |
<span class="icon">๐</span> TEMPERAMENT & PERSONALITY
|
393 |
</h2>
|
@@ -403,7 +434,7 @@ async def predict(image):
|
|
403 |
</span>
|
404 |
</span>
|
405 |
</div>
|
406 |
-
|
407 |
<h2 class="section-title">
|
408 |
<span class="icon">๐ช</span> CARE REQUIREMENTS
|
409 |
</h2>
|
@@ -454,7 +485,7 @@ async def predict(image):
|
|
454 |
<span class="value">{description['Care Level']}</span>
|
455 |
</div>
|
456 |
</div>
|
457 |
-
|
458 |
<h2 class="section-title">
|
459 |
<span class="icon">๐จโ๐ฉโ๐งโ๐ฆ</span> FAMILY COMPATIBILITY
|
460 |
</h2>
|
@@ -474,14 +505,14 @@ async def predict(image):
|
|
474 |
<span class="value">{description['Good with Children']}</span>
|
475 |
</div>
|
476 |
</div>
|
477 |
-
|
478 |
<h2 class="section-title">
|
479 |
<span class="icon">๐</span> DESCRIPTION
|
480 |
</h2>
|
481 |
<div class="description-section">
|
482 |
<p>{description.get('Description', '')}</p>
|
483 |
</div>
|
484 |
-
|
485 |
<div class="action-section">
|
486 |
<a href="{get_akc_breeds_link(breed)}" target="_blank" class="akc-button">
|
487 |
<span class="icon">๐</span>
|
@@ -498,16 +529,16 @@ async def predict(image):
|
|
498 |
<div class="breed-info">
|
499 |
<div class="model-uncertainty-note">
|
500 |
<span class="icon">โน๏ธ</span>
|
501 |
-
Note: The model is showing some uncertainty in its predictions.
|
502 |
Here are the most likely breeds based on the available visual features.
|
503 |
</div>
|
504 |
<div class="breeds-list">
|
505 |
'''
|
506 |
-
|
507 |
for j, (breed, prob) in enumerate(zip(topk_breeds, relative_probs)):
|
508 |
description = get_dog_description(breed)
|
509 |
dogs_info += f'''
|
510 |
-
<div class="breed-option uncertainty-mode">
|
511 |
<div class="breed-header">
|
512 |
<span class="option-number">Option {j+1}</span>
|
513 |
<span class="breed-name">{breed}</span>
|
@@ -521,46 +552,220 @@ async def predict(image):
|
|
521 |
</div>
|
522 |
'''
|
523 |
dogs_info += '</div></div>'
|
524 |
-
|
525 |
dogs_info += '</div>'
|
526 |
|
527 |
|
528 |
html_output = f"""
|
529 |
-
|
530 |
-
|
531 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
532 |
margin: 40px 0; /* ๅขๅ ๅก็้่ท */
|
533 |
-
padding: 0;
|
534 |
-
border-radius: 12px;
|
535 |
box-shadow: 0 2px 12px rgba(0,0,0,0.08);
|
536 |
overflow: hidden;
|
537 |
transition: all 0.3s ease;
|
538 |
background: white;
|
539 |
-
}
|
540 |
-
|
541 |
-
.dog-info-card:hover {
|
542 |
box-shadow: 0 4px 16px rgba(0,0,0,0.12);
|
543 |
-
}
|
544 |
-
|
545 |
-
.dog-info-header {
|
546 |
padding: 24px 28px; /* ๅขๅ ๅ
ง่ท */
|
547 |
margin: 0;
|
548 |
font-size: 22px;
|
549 |
font-weight: bold;
|
550 |
border-bottom: 1px solid #e1e4e8;
|
551 |
-
}
|
552 |
-
|
553 |
-
.breed-info {
|
554 |
padding: 28px; /* ๅขๅ ๆด้ซๅ
ง่ท */
|
555 |
line-height: 1.6;
|
556 |
-
}
|
557 |
-
|
558 |
-
.section-title {
|
559 |
font-size: 1.3em;
|
560 |
font-weight: 700;
|
561 |
color: #2c3e50;
|
562 |
margin: 32px 0 20px 0;
|
563 |
-
padding: 12px 0;
|
564 |
border-bottom: 2px solid #e1e4e8;
|
565 |
text-transform: uppercase;
|
566 |
letter-spacing: 0.5px;
|
@@ -568,16 +773,16 @@ async def predict(image):
|
|
568 |
align-items: center;
|
569 |
gap: 8px;
|
570 |
position: relative;
|
571 |
-
}
|
572 |
-
|
573 |
-
.icon {
|
574 |
font-size: 1.2em;
|
575 |
display: inline-flex;
|
576 |
align-items: center;
|
577 |
justify-content: center;
|
578 |
-
}
|
579 |
-
|
580 |
-
.info-section, .care-section, .family-section {
|
581 |
display: flex;
|
582 |
flex-wrap: wrap;
|
583 |
gap: 16px;
|
@@ -586,9 +791,9 @@ async def predict(image):
|
|
586 |
background: #f8f9fa;
|
587 |
border-radius: 12px;
|
588 |
border: 1px solid #e1e4e8; /* ๆทปๅ ้ๆก */
|
589 |
-
}
|
590 |
-
|
591 |
-
.info-item {
|
592 |
background: white; /* ๆน็บ็ฝ่ฒ่ๆฏ */
|
593 |
padding: 14px 18px; /* ๅขๅ ๅ
ง่ท */
|
594 |
border-radius: 8px;
|
@@ -599,30 +804,30 @@ async def predict(image):
|
|
599 |
border: 1px solid #e1e4e8;
|
600 |
flex: 1 1 auto;
|
601 |
min-width: 200px;
|
602 |
-
}
|
603 |
-
|
604 |
-
.label {
|
605 |
color: #666;
|
606 |
font-weight: 600;
|
607 |
font-size: 1.1rem;
|
608 |
-
}
|
609 |
-
|
610 |
-
.value {
|
611 |
color: #2c3e50;
|
612 |
font-weight: 500;
|
613 |
font-size: 1.1rem;
|
614 |
-
}
|
615 |
-
|
616 |
-
.temperament-section {
|
617 |
background: #f8f9fa;
|
618 |
padding: 20px; /* ๅขๅ ๅ
ง่ท */
|
619 |
border-radius: 12px;
|
620 |
margin-bottom: 28px; /* ๅขๅ ้่ท */
|
621 |
color: #444;
|
622 |
border: 1px solid #e1e4e8; /* ๆทปๅ ้ๆก */
|
623 |
-
}
|
624 |
-
|
625 |
-
.description-section {
|
626 |
background: #f8f9fa;
|
627 |
padding: 24px; /* ๅขๅ ๅ
ง่ท */
|
628 |
border-radius: 12px;
|
@@ -631,28 +836,27 @@ async def predict(image):
|
|
631 |
color: #444;
|
632 |
border: 1px solid #e1e4e8; /* ๆทปๅ ้ๆก */
|
633 |
fontsize: 1.1rem;
|
634 |
-
}
|
635 |
-
|
636 |
-
.description-section p {{
|
637 |
margin: 0;
|
638 |
padding: 0;
|
639 |
text-align: justify; /* ๆๅญๅ
ฉ็ซฏๅฐ้ฝ */
|
640 |
word-wrap: break-word; /* ็ขบไฟ้ทๅฎๅญๆๆ่ก */
|
641 |
white-space: pre-line; /* ไฟ็ๆ่กไฝๅไฝต็ฉบ็ฝ */
|
642 |
max-width: 100%; /* ็ขบไฟไธๆ่ถ
ๅบๅฎนๅจ */
|
643 |
-
}
|
644 |
-
|
645 |
-
.action-section {
|
646 |
margin-top: 24px;
|
647 |
text-align: center;
|
648 |
-
}
|
649 |
-
|
650 |
.akc-button,
|
651 |
.breed-section .akc-link,
|
652 |
-
.breed-option .akc-link {
|
653 |
display: inline-flex;
|
654 |
align-items: center;
|
655 |
-
padding: 14px 28px;
|
656 |
background: linear-gradient(145deg, #00509E, #003F7F);
|
657 |
color: white;
|
658 |
border-radius: 12px; /* ๅขๅ ๅ่ง */
|
@@ -661,30 +865,29 @@ async def predict(image):
|
|
661 |
transition: all 0.3s ease;
|
662 |
font-weight: 600;
|
663 |
font-size: 1.1em;
|
664 |
-
box-shadow:
|
665 |
0 2px 4px rgba(0,0,0,0.1),
|
666 |
inset 0 1px 1px rgba(255,255,255,0.1);
|
667 |
-
border: 1px solid rgba(255,255,255,0.1);
|
668 |
-
}
|
669 |
-
|
670 |
.akc-button:hover,
|
671 |
.breed-section .akc-link:hover,
|
672 |
-
.breed-option .akc-link:hover {
|
673 |
background: linear-gradient(145deg, #003F7F, #00509E);
|
674 |
-
transform: translateY(-2px);
|
675 |
color: white;
|
676 |
-
box-shadow:
|
677 |
-
0 6px 12px rgba(0,0,0,0.2),
|
678 |
inset 0 1px 1px rgba(255,255,255,0.2);
|
679 |
-
border: 1px solid rgba(255,255,255,0.2);
|
680 |
-
}
|
681 |
-
|
682 |
-
|
683 |
-
|
684 |
-
|
685 |
-
|
686 |
-
|
687 |
-
.warning-message {{
|
688 |
display: flex;
|
689 |
align-items: center;
|
690 |
gap: 8px;
|
@@ -694,9 +897,9 @@ async def predict(image):
|
|
694 |
padding: 16px;
|
695 |
background: #fff5f5;
|
696 |
border-radius: 8px;
|
697 |
-
}
|
698 |
-
|
699 |
-
.model-uncertainty-note {
|
700 |
display: flex;
|
701 |
align-items: center;
|
702 |
gap: 12px;
|
@@ -706,108 +909,103 @@ async def predict(image):
|
|
706 |
margin-bottom: 20px;
|
707 |
color: #495057;
|
708 |
border-radius: 4px;
|
709 |
-
}
|
710 |
-
|
711 |
-
.breeds-list {
|
712 |
display: flex;
|
713 |
flex-direction: column;
|
714 |
gap: 20px;
|
715 |
-
}
|
716 |
-
|
717 |
-
.breed-option {
|
718 |
background: white;
|
719 |
border: 1px solid #e1e4e8;
|
720 |
border-radius: 8px;
|
721 |
overflow: hidden;
|
722 |
-
}
|
723 |
-
|
724 |
-
.breed-header {
|
725 |
display: flex;
|
726 |
align-items: center;
|
727 |
padding: 16px;
|
728 |
background: #f8f9fa;
|
729 |
gap: 12px;
|
730 |
border-bottom: 1px solid #e1e4e8;
|
731 |
-
}
|
732 |
-
|
733 |
-
.option-number {
|
734 |
font-weight: 600;
|
735 |
color: #666;
|
736 |
padding: 4px 8px;
|
737 |
background: #e1e4e8;
|
738 |
border-radius: 4px;
|
739 |
-
}
|
740 |
-
|
741 |
-
.breed-name {
|
742 |
font-size: 1.5em;
|
743 |
font-weight: bold;
|
744 |
color: #2c3e50;
|
745 |
flex-grow: 1;
|
746 |
-
}
|
747 |
-
|
748 |
-
.confidence-badge {
|
749 |
padding: 4px 12px;
|
750 |
border-radius: 20px;
|
751 |
font-size: 0.9em;
|
752 |
font-weight: 500;
|
753 |
-
}
|
754 |
-
|
755 |
-
.breed-content {
|
756 |
padding: 20px;
|
757 |
-
}
|
758 |
-
|
759 |
-
.breed-content li {{
|
760 |
margin-bottom: 8px;
|
761 |
display: flex;
|
762 |
align-items: flex-start; /* ๆน็บ้ ้จๅฐ้ฝ */
|
763 |
gap: 8px;
|
764 |
flex-wrap: wrap; /* ๅ
่จฑๅ
งๅฎนๆ่ก */
|
765 |
-
}
|
766 |
-
|
767 |
-
.breed-content li strong {{
|
768 |
flex: 0 0 auto; /* ไธ่ฎๆจ้ก็ธฎๆพ */
|
769 |
min-width: 100px; /* ็ตฆๆจ้กไธๅๅบๅฎๆๅฐๅฏฌๅบฆ */
|
770 |
-
}
|
771 |
-
|
772 |
-
ul {
|
773 |
padding-left: 0;
|
774 |
margin: 0;
|
775 |
list-style-type: none;
|
776 |
-
}
|
777 |
-
|
778 |
-
li {
|
779 |
margin-bottom: 8px;
|
780 |
display: flex;
|
781 |
align-items: center;
|
782 |
gap: 8px;
|
783 |
-
}
|
784 |
-
|
785 |
-
.akc-link {{
|
786 |
color: white;
|
787 |
text-decoration: none;
|
788 |
font-weight: 600;
|
789 |
font-size: 1.1em;
|
790 |
transition: all 0.3s ease;
|
791 |
-
}
|
792 |
-
|
793 |
-
.akc-link:hover {
|
794 |
text-decoration: underline;
|
795 |
color: #D3E3F0;
|
796 |
-
}
|
797 |
-
.tooltip {
|
798 |
position: relative;
|
799 |
display: inline-flex;
|
800 |
align-items: center;
|
801 |
gap: 4px;
|
802 |
cursor: help;
|
803 |
-
}
|
804 |
-
|
805 |
-
.tooltip .tooltip-icon {{
|
806 |
font-size: 14px;
|
807 |
color: #666;
|
808 |
-
}
|
809 |
-
|
810 |
-
.tooltip .tooltip-text {{
|
811 |
visibility: hidden;
|
812 |
width: 250px;
|
813 |
background-color: rgba(44, 62, 80, 0.95);
|
@@ -826,47 +1024,43 @@ async def predict(image):
|
|
826 |
line-height: 1.3;
|
827 |
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.2);
|
828 |
border: 1px solid rgba(255, 255, 255, 0.1)
|
829 |
-
margin-bottom: 10px;
|
830 |
-
}
|
831 |
-
|
832 |
-
|
833 |
-
left: 0;
|
834 |
transform: translateX(0);
|
835 |
-
}
|
836 |
-
|
837 |
-
.tooltip.tooltip-right .tooltip-text {{
|
838 |
left: auto;
|
839 |
right: 0;
|
840 |
transform: translateX(0);
|
841 |
-
}
|
842 |
-
|
843 |
-
|
844 |
-
color:
|
845 |
-
background-color: transparent !important;
|
846 |
display: block; /* ่ฎๆจ้ก็จ็ซไธ่ก */
|
847 |
margin-bottom: 2px; /* ๅขๅ ๆจ้กไธๆน้่ท */
|
848 |
padding-bottom: 2px; /* ๅ ๅ
ฅๅฐ้่ท */
|
849 |
border-bottom: 1px solid rgba(255,255,255,0.2);
|
850 |
-
}
|
851 |
-
|
852 |
-
.tooltip-text {{
|
853 |
font-size: 13px; /* ็จๅพฎ็ธฎๅฐๅญ้ซ */
|
854 |
-
}
|
855 |
-
|
856 |
/* ่ชฟๆดๅ่กจ็ฌฆ่ๅๆๅญ็้่ท */
|
857 |
-
.tooltip-text ul {
|
858 |
margin: 0;
|
859 |
padding-left: 15px; /* ๆธๅฐๅ่กจ็ฌฆ่็็ธฎ้ฒ */
|
860 |
-
}
|
861 |
-
|
862 |
-
.tooltip-text li {
|
863 |
margin-bottom: 1px; /* ๆธๅฐๅ่กจ้
็ฎ้็้่ท */
|
864 |
-
}
|
865 |
-
.tooltip-text br {
|
866 |
line-height: 1.2; /* ๆธๅฐ่ก่ท */
|
867 |
-
}
|
868 |
-
|
869 |
-
.tooltip .tooltip-text::after {
|
870 |
content: "";
|
871 |
position: absolute;
|
872 |
top: 100%;
|
@@ -875,23 +1069,20 @@ async def predict(image):
|
|
875 |
border-width: 5px;
|
876 |
border-style: solid;
|
877 |
border-color: rgba(44, 62, 80, 0.95) transparent transparent transparent;
|
878 |
-
}
|
879 |
-
|
880 |
-
.tooltip-left .tooltip-text::after {{
|
881 |
left: 20%;
|
882 |
-
}
|
883 |
-
|
884 |
/* ๅณๅด็ฎญ้ ญ */
|
885 |
-
.tooltip-right .tooltip-text::after {
|
886 |
left: 80%;
|
887 |
-
}
|
888 |
-
|
889 |
-
.tooltip:hover .tooltip-text {{
|
890 |
visibility: visible;
|
891 |
opacity: 1;
|
892 |
-
}
|
893 |
-
|
894 |
-
.tooltip .tooltip-text::after {{
|
895 |
content: "";
|
896 |
position: absolute;
|
897 |
top: 100%;
|
@@ -900,9 +1091,8 @@ async def predict(image):
|
|
900 |
border-width: 8px;
|
901 |
border-style: solid;
|
902 |
border-color: rgba(44, 62, 80, 0.95) transparent transparent transparent;
|
903 |
-
}
|
904 |
-
|
905 |
-
.uncertainty-mode .tooltip .tooltip-text {{
|
906 |
position: absolute;
|
907 |
left: 100%;
|
908 |
bottom: auto;
|
@@ -910,9 +1100,9 @@ async def predict(image):
|
|
910 |
transform: translateY(-50%);
|
911 |
margin-left: 10px;
|
912 |
z-index: 1000; /* ็ขบไฟๆ็คบๆกๅจๆไธๅฑค */
|
913 |
-
}
|
914 |
-
|
915 |
-
.uncertainty-mode .tooltip .tooltip-text::after {
|
916 |
content: "";
|
917 |
position: absolute;
|
918 |
top: 50%;
|
@@ -921,220 +1111,379 @@ async def predict(image):
|
|
921 |
border-width: 5px;
|
922 |
border-style: solid;
|
923 |
border-color: transparent rgba(44, 62, 80, 0.95) transparent transparent;
|
924 |
-
}
|
925 |
-
|
926 |
-
.uncertainty-mode .breed-content {{
|
927 |
font-size: 1.1rem; /* ๅขๅ ๅญ้ซๅคงๅฐ */
|
928 |
-
}
|
929 |
-
|
930 |
.description-section,
|
931 |
.description-section p,
|
932 |
.temperament-section,
|
933 |
.temperament-section .value,
|
934 |
.info-item,
|
935 |
.info-item .value,
|
936 |
-
.breed-content {
|
937 |
font-size: 1.1rem !important; /* ไฝฟ็จ !important ็ขบไฟ่ฆ่ๅ
ถไปๆจฃๅผ */
|
938 |
-
}
|
939 |
-
</style>
|
940 |
-
{dogs_info}
|
941 |
-
"""
|
942 |
|
943 |
-
|
944 |
-
|
945 |
-
"image": annotated_image,
|
946 |
-
"is_multi_dog": len(dogs) > 1,
|
947 |
-
"html_output": html_output
|
948 |
}
|
949 |
-
|
950 |
-
return html_output, annotated_image, initial_state
|
951 |
|
952 |
-
|
953 |
-
|
954 |
-
|
955 |
-
|
956 |
-
|
|
|
957 |
|
958 |
-
|
959 |
-
|
960 |
-
|
961 |
|
962 |
-
|
963 |
-
|
964 |
-
|
965 |
-
|
966 |
-
|
967 |
-
|
968 |
-
|
969 |
-
<h2>{breed}</h2>
|
970 |
-
{formatted_description}
|
971 |
-
</div>
|
972 |
-
"""
|
973 |
-
|
974 |
-
initial_state["current_description"] = html_output
|
975 |
-
initial_state["original_buttons"] = initial_state.get("buttons", [])
|
976 |
-
|
977 |
-
return html_output, gr.update(visible=True), initial_state
|
978 |
-
except Exception as e:
|
979 |
-
error_msg = f"An error occurred while showing details: {e}"
|
980 |
-
print(error_msg)
|
981 |
-
return f"<p style='color: red;'>{error_msg}</p>", gr.update(visible=True), initial_state
|
982 |
-
|
983 |
|
984 |
-
|
985 |
-
|
986 |
-
|
987 |
-
|
988 |
-
|
989 |
-
|
990 |
-
html += f'''
|
991 |
-
<li style='margin-bottom: 10px;'>
|
992 |
-
<span class="tooltip">
|
993 |
-
<strong>{key}:</strong>
|
994 |
-
<span class="tooltip-icon">โ</span>
|
995 |
-
<span class="tooltip-text">
|
996 |
-
<strong>Size Categories:</strong><br>
|
997 |
-
โข Small: Under 20 pounds<br>
|
998 |
-
โข Medium: 20-60 pounds<br>
|
999 |
-
โข Large: Over 60 pounds
|
1000 |
-
</span>
|
1001 |
-
</span> {value}
|
1002 |
-
</li>
|
1003 |
-
'''
|
1004 |
-
elif key == "Exercise Needs":
|
1005 |
-
html += f'''
|
1006 |
-
<li style='margin-bottom: 10px;'>
|
1007 |
-
<span class="tooltip">
|
1008 |
-
<strong>{key}:</strong>
|
1009 |
-
<span class="tooltip-icon">โ</span>
|
1010 |
-
<span class="tooltip-text">
|
1011 |
-
<strong>Exercise Needs:</strong><br>
|
1012 |
-
โข High: 2+ hours of daily exercise<br>
|
1013 |
-
โข Moderate: 1-2 hours of daily activity<br>
|
1014 |
-
โข Low: Short walks and play sessions
|
1015 |
-
</span>
|
1016 |
-
</span> {value}
|
1017 |
-
</li>
|
1018 |
-
'''
|
1019 |
-
elif key == "Grooming Needs":
|
1020 |
-
html += f'''
|
1021 |
-
<li style='margin-bottom: 10px;'>
|
1022 |
-
<span class="tooltip">
|
1023 |
-
<strong>{key}:</strong>
|
1024 |
-
<span class="tooltip-icon">โ</span>
|
1025 |
-
<span class="tooltip-text">
|
1026 |
-
<strong>Grooming Requirements:</strong><br>
|
1027 |
-
โข High: Daily brushing, regular professional care<br>
|
1028 |
-
โข Moderate: Weekly brushing, occasional grooming<br>
|
1029 |
-
โข Low: Minimal brushing, basic maintenance
|
1030 |
-
</span>
|
1031 |
-
</span> {value}
|
1032 |
-
</li>
|
1033 |
-
'''
|
1034 |
-
elif key == "Care Level":
|
1035 |
-
html += f'''
|
1036 |
-
<li style='margin-bottom: 10px;'>
|
1037 |
-
<span class="tooltip">
|
1038 |
-
<strong>{key}:</strong>
|
1039 |
-
<span class="tooltip-icon">โ</span>
|
1040 |
-
<span class="tooltip-text">
|
1041 |
-
<strong>Care Level Explained:</strong><br>
|
1042 |
-
โข High: Needs significant training and attention<br>
|
1043 |
-
โข Moderate: Regular care and routine needed<br>
|
1044 |
-
โข Low: More independent, basic care sufficient
|
1045 |
-
</span>
|
1046 |
-
</span> {value}
|
1047 |
-
</li>
|
1048 |
-
'''
|
1049 |
-
elif key == "Good with Children":
|
1050 |
-
html += f'''
|
1051 |
-
<li style='margin-bottom: 10px;'>
|
1052 |
-
<span class="tooltip">
|
1053 |
-
<strong>{key}:</strong>
|
1054 |
-
<span class="tooltip-icon">โ</span>
|
1055 |
-
<span class="tooltip-text">
|
1056 |
-
<strong>Child Compatibility:</strong><br>
|
1057 |
-
โข Yes: Excellent with kids, patient and gentle<br>
|
1058 |
-
โข Moderate: Good with older children<br>
|
1059 |
-
โข No: Better suited for adult households
|
1060 |
-
</span>
|
1061 |
-
</span> {value}
|
1062 |
-
</li>
|
1063 |
-
'''
|
1064 |
-
elif key == "Lifespan":
|
1065 |
-
html += f'''
|
1066 |
-
<li style='margin-bottom: 10px;'>
|
1067 |
-
<span class="tooltip">
|
1068 |
-
<strong>{key}:</strong>
|
1069 |
-
<span class="tooltip-icon">โ</span>
|
1070 |
-
<span class="tooltip-text">
|
1071 |
-
<strong>Average Lifespan:</strong><br>
|
1072 |
-
โข Short: 6-8 years<br>
|
1073 |
-
โข Average: 10-15 years<br>
|
1074 |
-
โข Long: 12-20 years
|
1075 |
-
</span>
|
1076 |
-
</span> {value}
|
1077 |
-
</li>
|
1078 |
-
'''
|
1079 |
-
elif key == "Temperament":
|
1080 |
-
html += f'''
|
1081 |
-
<li style='margin-bottom: 10px;'>
|
1082 |
-
<span class="tooltip">
|
1083 |
-
<strong>{key}:</strong>
|
1084 |
-
<span class="tooltip-icon">โ</span>
|
1085 |
-
<span class="tooltip-text">
|
1086 |
-
<strong>Temperament Guide:</strong><br>
|
1087 |
-
โข Describes the dog's natural behavior<br>
|
1088 |
-
โข Important for matching with owner
|
1089 |
-
</span>
|
1090 |
-
</span> {value}
|
1091 |
-
</li>
|
1092 |
-
'''
|
1093 |
-
else:
|
1094 |
-
# ๅ
ถไปๆฌไฝไฟๆๅๆจฃ้กฏ็คบ
|
1095 |
-
html += f"<li style='margin-bottom: 10px;'><strong>{key}:</strong> {value}</li>"
|
1096 |
-
else:
|
1097 |
-
html += f"<li>{description}</li>"
|
1098 |
-
html += "</ul>"
|
1099 |
-
|
1100 |
-
# ๆทปๅ AKC้ฃ็ต
|
1101 |
-
html += f'''
|
1102 |
-
<div class="action-section">
|
1103 |
-
<a href="{get_akc_breeds_link(breed)}" target="_blank" class="akc-button">
|
1104 |
-
<span class="icon">๐</span>
|
1105 |
-
Learn more about {breed} on AKC website
|
1106 |
-
</a>
|
1107 |
-
</div>
|
1108 |
-
'''
|
1109 |
-
return html
|
1110 |
|
|
|
|
|
|
|
|
|
|
|
1111 |
|
1112 |
-
|
1113 |
-
|
1114 |
-
|
1115 |
-
|
1116 |
-
|
1117 |
-
|
1118 |
-
|
1119 |
-
|
1120 |
-
|
1121 |
-
|
1122 |
-
|
1123 |
-
|
1124 |
-
|
1125 |
-
|
1126 |
-
|
1127 |
-
|
1128 |
-
|
1129 |
-
|
1130 |
-
|
1131 |
-
|
1132 |
-
|
1133 |
-
|
1134 |
-
|
1135 |
-
|
1136 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1137 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1138 |
|
1139 |
if __name__ == "__main__":
|
1140 |
-
|
|
|
|
15 |
import traceback
|
16 |
|
17 |
|
18 |
+
model_yolo = YOLO('yolov8l.pt')
|
19 |
+
|
20 |
+
|
21 |
+
dog_breeds = ["Afghan_Hound", "African_Hunting_Dog", "Airedale", "American_Staffordshire_Terrier",
|
22 |
+
"Appenzeller", "Australian_Terrier", "Bedlington_Terrier", "Bernese_Mountain_Dog",
|
23 |
+
"Blenheim_Spaniel", "Border_Collie", "Border_Terrier", "Boston_Bull", "Bouvier_Des_Flandres",
|
24 |
+
"Brabancon_Griffon", "Brittany_Spaniel", "Cardigan", "Chesapeake_Bay_Retriever",
|
25 |
+
"Chihuahua", "Dandie_Dinmont", "Doberman", "English_Foxhound", "English_Setter",
|
26 |
+
"English_Springer", "EntleBucher", "Eskimo_Dog", "French_Bulldog", "German_Shepherd",
|
27 |
+
"German_Short-Haired_Pointer", "Gordon_Setter", "Great_Dane", "Great_Pyrenees",
|
28 |
+
"Greater_Swiss_Mountain_Dog", "Ibizan_Hound", "Irish_Setter", "Irish_Terrier",
|
29 |
+
"Irish_Water_Spaniel", "Irish_Wolfhound", "Italian_Greyhound", "Japanese_Spaniel",
|
30 |
+
"Kerry_Blue_Terrier", "Labrador_Retriever", "Lakeland_Terrier", "Leonberg", "Lhasa",
|
31 |
+
"Maltese_Dog", "Mexican_Hairless", "Newfoundland", "Norfolk_Terrier", "Norwegian_Elkhound",
|
32 |
+
"Norwich_Terrier", "Old_English_Sheepdog", "Pekinese", "Pembroke", "Pomeranian",
|
33 |
+
"Rhodesian_Ridgeback", "Rottweiler", "Saint_Bernard", "Saluki", "Samoyed",
|
34 |
+
"Scotch_Terrier", "Scottish_Deerhound", "Sealyham_Terrier", "Shetland_Sheepdog",
|
35 |
+
"Shih-Tzu", "Siberian_Husky", "Staffordshire_Bullterrier", "Sussex_Spaniel",
|
36 |
+
"Tibetan_Mastiff", "Tibetan_Terrier", "Walker_Hound", "Weimaraner",
|
37 |
+
"Welsh_Springer_Spaniel", "West_Highland_White_Terrier", "Yorkshire_Terrier",
|
38 |
+
"Affenpinscher", "Basenji", "Basset", "Beagle", "Black-and-Tan_Coonhound", "Bloodhound",
|
39 |
+
"Bluetick", "Borzoi", "Boxer", "Briard", "Bull_Mastiff", "Cairn", "Chow", "Clumber",
|
40 |
+
"Cocker_Spaniel", "Collie", "Curly-Coated_Retriever", "Dhole", "Dingo",
|
41 |
+
"Flat-Coated_Retriever", "Giant_Schnauzer", "Golden_Retriever", "Groenendael", "Keeshond",
|
42 |
+
"Kelpie", "Komondor", "Kuvasz", "Malamute", "Malinois", "Miniature_Pinscher",
|
43 |
+
"Miniature_Poodle", "Miniature_Schnauzer", "Otterhound", "Papillon", "Pug", "Redbone",
|
44 |
+
"Schipperke", "Silky_Terrier", "Soft-Coated_Wheaten_Terrier", "Standard_Poodle",
|
45 |
+
"Standard_Schnauzer", "Toy_Poodle", "Toy_Terrier", "Vizsla", "Whippet",
|
46 |
"Wire-Haired_Fox_Terrier"]
|
47 |
|
48 |
class MultiHeadAttention(nn.Module):
|
|
|
141 |
topk_probs, topk_indices = torch.topk(probabilities, k=3)
|
142 |
top1_prob = topk_probs[0][0].item()
|
143 |
topk_breeds = [dog_breeds[idx.item()] for idx in topk_indices[0]]
|
144 |
+
|
145 |
# Calculate relative probabilities for display
|
146 |
raw_probs = [prob.item() for prob in topk_probs[0]]
|
147 |
sum_probs = sum(raw_probs)
|
148 |
relative_probs = [f"{(prob/sum_probs * 100):.2f}%" for prob in raw_probs]
|
149 |
+
|
150 |
return top1_prob, topk_breeds, relative_probs
|
151 |
+
|
152 |
|
153 |
async def detect_multiple_dogs(image, conf_threshold=0.3, iou_threshold=0.45):
|
154 |
results = model_yolo(image, conf=conf_threshold, iou=iou_threshold)[0]
|
155 |
dogs = []
|
156 |
boxes = []
|
157 |
for box in results.boxes:
|
158 |
+
if box.cls == 16: # COCO dataset class for dog is 16
|
159 |
xyxy = box.xyxy[0].tolist()
|
160 |
confidence = box.conf.item()
|
161 |
boxes.append((xyxy, confidence))
|
162 |
+
|
163 |
if not boxes:
|
164 |
dogs.append((image, 1.0, [0, 0, image.width, image.height]))
|
165 |
else:
|
166 |
nms_boxes = non_max_suppression(boxes, iou_threshold)
|
167 |
+
|
168 |
for box, confidence in nms_boxes:
|
169 |
x1, y1, x2, y2 = box
|
170 |
w, h = x2 - x1, y2 - y1
|
|
|
174 |
y2 = min(image.height, y2 + h * 0.05)
|
175 |
cropped_image = image.crop((x1, y1, x2, y2))
|
176 |
dogs.append((cropped_image, confidence, [x1, y1, x2, y2]))
|
177 |
+
|
178 |
return dogs
|
179 |
|
180 |
|
|
|
187 |
boxes = [box for box in boxes if calculate_iou(current[0], box[0]) < iou_threshold]
|
188 |
return keep
|
189 |
|
190 |
+
|
191 |
def calculate_iou(box1, box2):
|
192 |
x1 = max(box1[0], box2[0])
|
193 |
y1 = max(box1[1], box2[1])
|
194 |
x2 = min(box1[2], box2[2])
|
195 |
y2 = min(box1[3], box2[3])
|
196 |
+
|
197 |
intersection = max(0, x2 - x1) * max(0, y2 - y1)
|
198 |
area1 = (box1[2] - box1[0]) * (box1[3] - box1[1])
|
199 |
area2 = (box2[2] - box2[0]) * (box2[3] - box2[1])
|
200 |
+
|
201 |
iou = intersection / float(area1 + area2 - intersection)
|
202 |
return iou
|
203 |
|
204 |
|
205 |
async def process_single_dog(image):
|
206 |
top1_prob, topk_breeds, relative_probs = await predict_single_dog(image)
|
207 |
+
|
208 |
# Case 1: Low confidence - unclear image or breed not in dataset
|
209 |
if top1_prob < 0.2:
|
210 |
error_message = '''
|
|
|
225 |
return error_message, None, initial_state
|
226 |
|
227 |
breed = topk_breeds[0]
|
228 |
+
|
229 |
# Case 2: High confidence - single breed result
|
230 |
if top1_prob >= 0.45:
|
231 |
description = get_dog_description(breed)
|
|
|
243 |
"is_multi_dog": False
|
244 |
}
|
245 |
return html_content, image, initial_state
|
246 |
+
|
247 |
# Case 3: Medium confidence - show top 3 breeds with relative probabilities
|
248 |
else:
|
249 |
breeds_html = ""
|
|
|
269 |
}
|
270 |
return breeds_html, image, initial_state
|
271 |
|
272 |
+
|
273 |
+
def create_breed_comparison(breed1: str, breed2: str) -> dict:
|
274 |
+
"""ๆฏ่ผๅ
ฉๅ็ๅ็จฎ็็นๆง"""
|
275 |
+
breed1_info = get_dog_description(breed1)
|
276 |
+
breed2_info = get_dog_description(breed2)
|
277 |
+
|
278 |
+
# ๆจๆบๅๆธๅผ่ฝๆ
|
279 |
+
value_mapping = {
|
280 |
+
'Size': {'Small': 1, 'Medium': 2, 'Large': 3, 'Giant': 4},
|
281 |
+
'Exercise_Needs': {'Low': 1, 'Moderate': 2, 'High': 3, 'Very High': 4},
|
282 |
+
'Care_Level': {'Low': 1, 'Moderate': 2, 'High': 3},
|
283 |
+
'Grooming_Needs': {'Low': 1, 'Moderate': 2, 'High': 3}
|
284 |
+
}
|
285 |
+
|
286 |
+
comparison_data = {
|
287 |
+
breed1: {},
|
288 |
+
breed2: {}
|
289 |
+
}
|
290 |
+
|
291 |
+
for breed, info in [(breed1, breed1_info), (breed2, breed2_info)]:
|
292 |
+
comparison_data[breed] = {
|
293 |
+
'Size': value_mapping['Size'].get(info['Size'], 2), # ้ ่จญ Medium
|
294 |
+
'Exercise_Needs': value_mapping['Exercise_Needs'].get(info['Exercise Needs'], 2), # ้ ่จญ Moderate
|
295 |
+
'Care_Level': value_mapping['Care_Level'].get(info['Care Level'], 2),
|
296 |
+
'Grooming_Needs': value_mapping['Grooming_Needs'].get(info['Grooming Needs'], 2),
|
297 |
+
'Good_with_Children': info['Good with Children'] == 'Yes',
|
298 |
+
'Original_Data': info
|
299 |
+
}
|
300 |
+
|
301 |
+
return comparison_data
|
302 |
+
|
303 |
+
|
304 |
async def predict(image):
|
305 |
if image is None:
|
306 |
return "Please upload an image to start.", None, None
|
|
|
322 |
'#A233FF', # ็ดซ่ฒ
|
323 |
'#FF3333', # ็ด
่ฒ
|
324 |
'#33FFB7', # ้็ถ ่ฒ
|
325 |
+
'#FFE033' # ้้ป่ฒ
|
326 |
]
|
327 |
annotated_image = image.copy()
|
328 |
draw = ImageDraw.Draw(annotated_image)
|
|
|
336 |
|
337 |
for i, (cropped_image, detection_confidence, box) in enumerate(dogs):
|
338 |
color = single_dog_color if len(dogs) == 1 else color_list[i % len(color_list)]
|
339 |
+
|
340 |
# ๅชๅๅ็ไธ็ๆจ่จ
|
341 |
draw.rectangle(box, outline=color, width=4)
|
342 |
label = f"Dog {i+1}"
|
343 |
label_bbox = draw.textbbox((0, 0), label, font=font)
|
344 |
label_width = label_bbox[2] - label_bbox[0]
|
345 |
label_height = label_bbox[3] - label_bbox[1]
|
346 |
+
|
347 |
label_x = box[0] + 5
|
348 |
label_y = box[1] + 5
|
349 |
draw.rectangle(
|
|
|
353 |
width=2
|
354 |
)
|
355 |
draw.text((label_x, label_y), label, fill=color, font=font)
|
356 |
+
|
357 |
top1_prob, topk_breeds, relative_probs = await predict_single_dog(cropped_image)
|
358 |
combined_confidence = detection_confidence * top1_prob
|
359 |
+
|
360 |
# ้ๅง่ณ่จๅก็
|
361 |
dogs_info += f'<div class="dog-info-card" style="border-left: 6px solid {color};">'
|
362 |
+
|
363 |
if combined_confidence < 0.2:
|
364 |
dogs_info += f'''
|
365 |
<div class="dog-info-header" style="background-color: {color}10;">
|
|
|
418 |
<span class="value">{description['Lifespan']}</span>
|
419 |
</div>
|
420 |
</div>
|
421 |
+
|
422 |
<h2 class="section-title">
|
423 |
<span class="icon">๐</span> TEMPERAMENT & PERSONALITY
|
424 |
</h2>
|
|
|
434 |
</span>
|
435 |
</span>
|
436 |
</div>
|
437 |
+
|
438 |
<h2 class="section-title">
|
439 |
<span class="icon">๐ช</span> CARE REQUIREMENTS
|
440 |
</h2>
|
|
|
485 |
<span class="value">{description['Care Level']}</span>
|
486 |
</div>
|
487 |
</div>
|
488 |
+
|
489 |
<h2 class="section-title">
|
490 |
<span class="icon">๐จโ๐ฉโ๐งโ๐ฆ</span> FAMILY COMPATIBILITY
|
491 |
</h2>
|
|
|
505 |
<span class="value">{description['Good with Children']}</span>
|
506 |
</div>
|
507 |
</div>
|
508 |
+
|
509 |
<h2 class="section-title">
|
510 |
<span class="icon">๐</span> DESCRIPTION
|
511 |
</h2>
|
512 |
<div class="description-section">
|
513 |
<p>{description.get('Description', '')}</p>
|
514 |
</div>
|
515 |
+
|
516 |
<div class="action-section">
|
517 |
<a href="{get_akc_breeds_link(breed)}" target="_blank" class="akc-button">
|
518 |
<span class="icon">๐</span>
|
|
|
529 |
<div class="breed-info">
|
530 |
<div class="model-uncertainty-note">
|
531 |
<span class="icon">โน๏ธ</span>
|
532 |
+
Note: The model is showing some uncertainty in its predictions.
|
533 |
Here are the most likely breeds based on the available visual features.
|
534 |
</div>
|
535 |
<div class="breeds-list">
|
536 |
'''
|
537 |
+
|
538 |
for j, (breed, prob) in enumerate(zip(topk_breeds, relative_probs)):
|
539 |
description = get_dog_description(breed)
|
540 |
dogs_info += f'''
|
541 |
+
<div class="breed-option uncertainty-mode">
|
542 |
<div class="breed-header">
|
543 |
<span class="option-number">Option {j+1}</span>
|
544 |
<span class="breed-name">{breed}</span>
|
|
|
552 |
</div>
|
553 |
'''
|
554 |
dogs_info += '</div></div>'
|
555 |
+
|
556 |
dogs_info += '</div>'
|
557 |
|
558 |
|
559 |
html_output = f"""
|
560 |
+
<div class="dog-info-card">
|
561 |
+
{dogs_info}
|
562 |
+
</div>
|
563 |
+
"""
|
564 |
+
|
565 |
+
initial_state = {
|
566 |
+
"dogs_info": dogs_info,
|
567 |
+
"image": annotated_image,
|
568 |
+
"is_multi_dog": len(dogs) > 1,
|
569 |
+
"html_output": html_output
|
570 |
+
}
|
571 |
+
|
572 |
+
return html_output, annotated_image, initial_state
|
573 |
+
|
574 |
+
except Exception as e:
|
575 |
+
error_msg = f"An error occurred: {str(e)}\n\nTraceback:\n{traceback.format_exc()}"
|
576 |
+
print(error_msg)
|
577 |
+
return error_msg, None, None
|
578 |
+
|
579 |
+
|
580 |
+
def show_details_html(choice, previous_output, initial_state):
|
581 |
+
if not choice:
|
582 |
+
return previous_output, gr.update(visible=True), initial_state
|
583 |
+
|
584 |
+
try:
|
585 |
+
breed = choice.split("More about ")[-1]
|
586 |
+
description = get_dog_description(breed)
|
587 |
+
formatted_description = format_description_html(description, breed)
|
588 |
+
|
589 |
+
html_output = f"""
|
590 |
+
<div class="dog-info">
|
591 |
+
<h2>{breed}</h2>
|
592 |
+
{formatted_description}
|
593 |
+
</div>
|
594 |
+
"""
|
595 |
+
|
596 |
+
initial_state["current_description"] = html_output
|
597 |
+
initial_state["original_buttons"] = initial_state.get("buttons", [])
|
598 |
+
|
599 |
+
return html_output, gr.update(visible=True), initial_state
|
600 |
+
except Exception as e:
|
601 |
+
error_msg = f"An error occurred while showing details: {e}"
|
602 |
+
print(error_msg)
|
603 |
+
return f"<p style='color: red;'>{error_msg}</p>", gr.update(visible=True), initial_state
|
604 |
+
|
605 |
+
|
606 |
+
def format_description_html(description, breed):
|
607 |
+
html = "<ul style='list-style-type: none; padding-left: 0;'>"
|
608 |
+
if isinstance(description, dict):
|
609 |
+
for key, value in description.items():
|
610 |
+
if key != "Breed": # ่ทณ้้่ค็ๅ็จฎ้กฏ็คบ
|
611 |
+
if key == "Size":
|
612 |
+
html += f'''
|
613 |
+
<li style='margin-bottom: 10px;'>
|
614 |
+
<span class="tooltip">
|
615 |
+
<strong>{key}:</strong>
|
616 |
+
<span class="tooltip-icon">โ</span>
|
617 |
+
<span class="tooltip-text">
|
618 |
+
<strong>Size Categories:</strong><br>
|
619 |
+
โข Small: Under 20 pounds<br>
|
620 |
+
โข Medium: 20-60 pounds<br>
|
621 |
+
โข Large: Over 60 pounds
|
622 |
+
</span>
|
623 |
+
</span> {value}
|
624 |
+
</li>
|
625 |
+
'''
|
626 |
+
elif key == "Exercise Needs":
|
627 |
+
html += f'''
|
628 |
+
<li style='margin-bottom: 10px;'>
|
629 |
+
<span class="tooltip">
|
630 |
+
<strong>{key}:</strong>
|
631 |
+
<span class="tooltip-icon">โ</span>
|
632 |
+
<span class="tooltip-text">
|
633 |
+
<strong>Exercise Needs:</strong><br>
|
634 |
+
โข High: 2+ hours of daily exercise<br>
|
635 |
+
โข Moderate: 1-2 hours of daily activity<br>
|
636 |
+
โข Low: Short walks and play sessions
|
637 |
+
</span>
|
638 |
+
</span> {value}
|
639 |
+
</li>
|
640 |
+
'''
|
641 |
+
elif key == "Grooming Needs":
|
642 |
+
html += f'''
|
643 |
+
<li style='margin-bottom: 10px;'>
|
644 |
+
<span class="tooltip">
|
645 |
+
<strong>{key}:</strong>
|
646 |
+
<span class="tooltip-icon">โ</span>
|
647 |
+
<span class="tooltip-text">
|
648 |
+
<strong>Grooming Requirements:</strong><br>
|
649 |
+
โข High: Daily brushing, regular professional care<br>
|
650 |
+
โข Moderate: Weekly brushing, occasional grooming<br>
|
651 |
+
โข Low: Minimal brushing, basic maintenance
|
652 |
+
</span>
|
653 |
+
</span> {value}
|
654 |
+
</li>
|
655 |
+
'''
|
656 |
+
elif key == "Care Level":
|
657 |
+
html += f'''
|
658 |
+
<li style='margin-bottom: 10px;'>
|
659 |
+
<span class="tooltip">
|
660 |
+
<strong>{key}:</strong>
|
661 |
+
<span class="tooltip-icon">โ</span>
|
662 |
+
<span class="tooltip-text">
|
663 |
+
<strong>Care Level Explained:</strong><br>
|
664 |
+
โข High: Needs significant training and attention<br>
|
665 |
+
โข Moderate: Regular care and routine needed<br>
|
666 |
+
โข Low: More independent, basic care sufficient
|
667 |
+
</span>
|
668 |
+
</span> {value}
|
669 |
+
</li>
|
670 |
+
'''
|
671 |
+
elif key == "Good with Children":
|
672 |
+
html += f'''
|
673 |
+
<li style='margin-bottom: 10px;'>
|
674 |
+
<span class="tooltip">
|
675 |
+
<strong>{key}:</strong>
|
676 |
+
<span class="tooltip-icon">โ</span>
|
677 |
+
<span class="tooltip-text">
|
678 |
+
<strong>Child Compatibility:</strong><br>
|
679 |
+
โข Yes: Excellent with kids, patient and gentle<br>
|
680 |
+
โข Moderate: Good with older children<br>
|
681 |
+
โข No: Better suited for adult households
|
682 |
+
</span>
|
683 |
+
</span> {value}
|
684 |
+
</li>
|
685 |
+
'''
|
686 |
+
elif key == "Lifespan":
|
687 |
+
html += f'''
|
688 |
+
<li style='margin-bottom: 10px;'>
|
689 |
+
<span class="tooltip">
|
690 |
+
<strong>{key}:</strong>
|
691 |
+
<span class="tooltip-icon">โ</span>
|
692 |
+
<span class="tooltip-text">
|
693 |
+
<strong>Average Lifespan:</strong><br>
|
694 |
+
โข Short: 6-8 years<br>
|
695 |
+
โข Average: 10-15 years<br>
|
696 |
+
โข Long: 12-20 years
|
697 |
+
</span>
|
698 |
+
</span> {value}
|
699 |
+
</li>
|
700 |
+
'''
|
701 |
+
elif key == "Temperament":
|
702 |
+
html += f'''
|
703 |
+
<li style='margin-bottom: 10px;'>
|
704 |
+
<span class="tooltip">
|
705 |
+
<strong>{key}:</strong>
|
706 |
+
<span class="tooltip-icon">โ</span>
|
707 |
+
<span class="tooltip-text">
|
708 |
+
<strong>Temperament Guide:</strong><br>
|
709 |
+
โข Describes the dog's natural behavior<br>
|
710 |
+
โข Important for matching with owner
|
711 |
+
</span>
|
712 |
+
</span> {value}
|
713 |
+
</li>
|
714 |
+
'''
|
715 |
+
else:
|
716 |
+
# ๅ
ถไปๆฌไฝไฟๆๅๆจฃ้กฏ็คบ
|
717 |
+
html += f"<li style='margin-bottom: 10px;'><strong>{key}:</strong> {value}</li>"
|
718 |
+
else:
|
719 |
+
html += f"<li>{description}</li>"
|
720 |
+
html += "</ul>"
|
721 |
+
|
722 |
+
# ๆทปๅ AKC้ฃ็ต
|
723 |
+
html += f'''
|
724 |
+
<div class="action-section">
|
725 |
+
<a href="{get_akc_breeds_link(breed)}" target="_blank" class="akc-button">
|
726 |
+
<span class="icon">๐</span>
|
727 |
+
Learn more about {breed} on AKC website
|
728 |
+
</a>
|
729 |
+
</div>
|
730 |
+
'''
|
731 |
+
return html
|
732 |
+
|
733 |
+
|
734 |
+
with gr.Blocks(css="""
|
735 |
+
.dog-info-card {
|
736 |
+
border: 1px solid #e1e4e8;
|
737 |
margin: 40px 0; /* ๅขๅ ๅก็้่ท */
|
738 |
+
padding: 0;
|
739 |
+
border-radius: 12px;
|
740 |
box-shadow: 0 2px 12px rgba(0,0,0,0.08);
|
741 |
overflow: hidden;
|
742 |
transition: all 0.3s ease;
|
743 |
background: white;
|
744 |
+
}
|
745 |
+
|
746 |
+
.dog-info-card:hover {
|
747 |
box-shadow: 0 4px 16px rgba(0,0,0,0.12);
|
748 |
+
}
|
749 |
+
|
750 |
+
.dog-info-header {
|
751 |
padding: 24px 28px; /* ๅขๅ ๅ
ง่ท */
|
752 |
margin: 0;
|
753 |
font-size: 22px;
|
754 |
font-weight: bold;
|
755 |
border-bottom: 1px solid #e1e4e8;
|
756 |
+
}
|
757 |
+
|
758 |
+
.breed-info {
|
759 |
padding: 28px; /* ๅขๅ ๆด้ซๅ
ง่ท */
|
760 |
line-height: 1.6;
|
761 |
+
}
|
762 |
+
|
763 |
+
.section-title {
|
764 |
font-size: 1.3em;
|
765 |
font-weight: 700;
|
766 |
color: #2c3e50;
|
767 |
margin: 32px 0 20px 0;
|
768 |
+
padding: 12px 0;
|
769 |
border-bottom: 2px solid #e1e4e8;
|
770 |
text-transform: uppercase;
|
771 |
letter-spacing: 0.5px;
|
|
|
773 |
align-items: center;
|
774 |
gap: 8px;
|
775 |
position: relative;
|
776 |
+
}
|
777 |
+
|
778 |
+
.icon {
|
779 |
font-size: 1.2em;
|
780 |
display: inline-flex;
|
781 |
align-items: center;
|
782 |
justify-content: center;
|
783 |
+
}
|
784 |
+
|
785 |
+
.info-section, .care-section, .family-section {
|
786 |
display: flex;
|
787 |
flex-wrap: wrap;
|
788 |
gap: 16px;
|
|
|
791 |
background: #f8f9fa;
|
792 |
border-radius: 12px;
|
793 |
border: 1px solid #e1e4e8; /* ๆทปๅ ้ๆก */
|
794 |
+
}
|
795 |
+
|
796 |
+
.info-item {
|
797 |
background: white; /* ๆน็บ็ฝ่ฒ่ๆฏ */
|
798 |
padding: 14px 18px; /* ๅขๅ ๅ
ง่ท */
|
799 |
border-radius: 8px;
|
|
|
804 |
border: 1px solid #e1e4e8;
|
805 |
flex: 1 1 auto;
|
806 |
min-width: 200px;
|
807 |
+
}
|
808 |
+
|
809 |
+
.label {
|
810 |
color: #666;
|
811 |
font-weight: 600;
|
812 |
font-size: 1.1rem;
|
813 |
+
}
|
814 |
+
|
815 |
+
.value {
|
816 |
color: #2c3e50;
|
817 |
font-weight: 500;
|
818 |
font-size: 1.1rem;
|
819 |
+
}
|
820 |
+
|
821 |
+
.temperament-section {
|
822 |
background: #f8f9fa;
|
823 |
padding: 20px; /* ๅขๅ ๅ
ง่ท */
|
824 |
border-radius: 12px;
|
825 |
margin-bottom: 28px; /* ๅขๅ ้่ท */
|
826 |
color: #444;
|
827 |
border: 1px solid #e1e4e8; /* ๆทปๅ ้ๆก */
|
828 |
+
}
|
829 |
+
|
830 |
+
.description-section {
|
831 |
background: #f8f9fa;
|
832 |
padding: 24px; /* ๅขๅ ๅ
ง่ท */
|
833 |
border-radius: 12px;
|
|
|
836 |
color: #444;
|
837 |
border: 1px solid #e1e4e8; /* ๆทปๅ ้ๆก */
|
838 |
fontsize: 1.1rem;
|
839 |
+
}
|
840 |
+
.description-section p {
|
|
|
841 |
margin: 0;
|
842 |
padding: 0;
|
843 |
text-align: justify; /* ๆๅญๅ
ฉ็ซฏๅฐ้ฝ */
|
844 |
word-wrap: break-word; /* ็ขบไฟ้ทๅฎๅญๆๆ่ก */
|
845 |
white-space: pre-line; /* ไฟ็ๆ่กไฝๅไฝต็ฉบ็ฝ */
|
846 |
max-width: 100%; /* ็ขบไฟไธๆ่ถ
ๅบๅฎนๅจ */
|
847 |
+
}
|
848 |
+
|
849 |
+
.action-section {
|
850 |
margin-top: 24px;
|
851 |
text-align: center;
|
852 |
+
}
|
853 |
+
|
854 |
.akc-button,
|
855 |
.breed-section .akc-link,
|
856 |
+
.breed-option .akc-link {
|
857 |
display: inline-flex;
|
858 |
align-items: center;
|
859 |
+
padding: 14px 28px;
|
860 |
background: linear-gradient(145deg, #00509E, #003F7F);
|
861 |
color: white;
|
862 |
border-radius: 12px; /* ๅขๅ ๅ่ง */
|
|
|
865 |
transition: all 0.3s ease;
|
866 |
font-weight: 600;
|
867 |
font-size: 1.1em;
|
868 |
+
box-shadow:
|
869 |
0 2px 4px rgba(0,0,0,0.1),
|
870 |
inset 0 1px 1px rgba(255,255,255,0.1);
|
871 |
+
border: 1px solid rgba(255,255,255,0.1);
|
872 |
+
}
|
873 |
+
|
874 |
.akc-button:hover,
|
875 |
.breed-section .akc-link:hover,
|
876 |
+
.breed-option .akc-link:hover {
|
877 |
background: linear-gradient(145deg, #003F7F, #00509E);
|
878 |
+
transform: translateY(-2px);
|
879 |
color: white;
|
880 |
+
box-shadow:
|
881 |
+
0 6px 12px rgba(0,0,0,0.2),
|
882 |
inset 0 1px 1px rgba(255,255,255,0.2);
|
883 |
+
border: 1px solid rgba(255,255,255,0.2);
|
884 |
+
}
|
885 |
+
.icon {
|
886 |
+
font-size: 1.3em;
|
887 |
+
filter: drop-shadow(0 1px 1px rgba(0,0,0,0.2));
|
888 |
+
}
|
889 |
+
|
890 |
+
.warning-message {
|
|
|
891 |
display: flex;
|
892 |
align-items: center;
|
893 |
gap: 8px;
|
|
|
897 |
padding: 16px;
|
898 |
background: #fff5f5;
|
899 |
border-radius: 8px;
|
900 |
+
}
|
901 |
+
|
902 |
+
.model-uncertainty-note {
|
903 |
display: flex;
|
904 |
align-items: center;
|
905 |
gap: 12px;
|
|
|
909 |
margin-bottom: 20px;
|
910 |
color: #495057;
|
911 |
border-radius: 4px;
|
912 |
+
}
|
913 |
+
|
914 |
+
.breeds-list {
|
915 |
display: flex;
|
916 |
flex-direction: column;
|
917 |
gap: 20px;
|
918 |
+
}
|
919 |
+
|
920 |
+
.breed-option {
|
921 |
background: white;
|
922 |
border: 1px solid #e1e4e8;
|
923 |
border-radius: 8px;
|
924 |
overflow: hidden;
|
925 |
+
}
|
926 |
+
|
927 |
+
.breed-header {
|
928 |
display: flex;
|
929 |
align-items: center;
|
930 |
padding: 16px;
|
931 |
background: #f8f9fa;
|
932 |
gap: 12px;
|
933 |
border-bottom: 1px solid #e1e4e8;
|
934 |
+
}
|
935 |
+
|
936 |
+
.option-number {
|
937 |
font-weight: 600;
|
938 |
color: #666;
|
939 |
padding: 4px 8px;
|
940 |
background: #e1e4e8;
|
941 |
border-radius: 4px;
|
942 |
+
}
|
943 |
+
|
944 |
+
.breed-name {
|
945 |
font-size: 1.5em;
|
946 |
font-weight: bold;
|
947 |
color: #2c3e50;
|
948 |
flex-grow: 1;
|
949 |
+
}
|
950 |
+
|
951 |
+
.confidence-badge {
|
952 |
padding: 4px 12px;
|
953 |
border-radius: 20px;
|
954 |
font-size: 0.9em;
|
955 |
font-weight: 500;
|
956 |
+
}
|
957 |
+
|
958 |
+
.breed-content {
|
959 |
padding: 20px;
|
960 |
+
}
|
961 |
+
.breed-content li {
|
|
|
962 |
margin-bottom: 8px;
|
963 |
display: flex;
|
964 |
align-items: flex-start; /* ๆน็บ้ ้จๅฐ้ฝ */
|
965 |
gap: 8px;
|
966 |
flex-wrap: wrap; /* ๅ
่จฑๅ
งๅฎนๆ่ก */
|
967 |
+
}
|
968 |
+
.breed-content li strong {
|
|
|
969 |
flex: 0 0 auto; /* ไธ่ฎๆจ้ก็ธฎๆพ */
|
970 |
min-width: 100px; /* ็ตฆๆจ้กไธๅๅบๅฎๆๅฐๅฏฌๅบฆ */
|
971 |
+
}
|
972 |
+
|
973 |
+
ul {
|
974 |
padding-left: 0;
|
975 |
margin: 0;
|
976 |
list-style-type: none;
|
977 |
+
}
|
978 |
+
|
979 |
+
li {
|
980 |
margin-bottom: 8px;
|
981 |
display: flex;
|
982 |
align-items: center;
|
983 |
gap: 8px;
|
984 |
+
}
|
985 |
+
.akc-link {
|
|
|
986 |
color: white;
|
987 |
text-decoration: none;
|
988 |
font-weight: 600;
|
989 |
font-size: 1.1em;
|
990 |
transition: all 0.3s ease;
|
991 |
+
}
|
992 |
+
|
993 |
+
.akc-link:hover {
|
994 |
text-decoration: underline;
|
995 |
color: #D3E3F0;
|
996 |
+
}
|
997 |
+
.tooltip {
|
998 |
position: relative;
|
999 |
display: inline-flex;
|
1000 |
align-items: center;
|
1001 |
gap: 4px;
|
1002 |
cursor: help;
|
1003 |
+
}
|
1004 |
+
.tooltip .tooltip-icon {
|
|
|
1005 |
font-size: 14px;
|
1006 |
color: #666;
|
1007 |
+
}
|
1008 |
+
.tooltip .tooltip-text {
|
|
|
1009 |
visibility: hidden;
|
1010 |
width: 250px;
|
1011 |
background-color: rgba(44, 62, 80, 0.95);
|
|
|
1024 |
line-height: 1.3;
|
1025 |
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.2);
|
1026 |
border: 1px solid rgba(255, 255, 255, 0.1)
|
1027 |
+
margin-bottom: 10px;
|
1028 |
+
}
|
1029 |
+
.tooltip.tooltip-left .tooltip-text {
|
1030 |
+
left: 0;
|
|
|
1031 |
transform: translateX(0);
|
1032 |
+
}
|
1033 |
+
.tooltip.tooltip-right .tooltip-text {
|
|
|
1034 |
left: auto;
|
1035 |
right: 0;
|
1036 |
transform: translateX(0);
|
1037 |
+
}
|
1038 |
+
.tooltip-text strong {
|
1039 |
+
color: white !important;
|
1040 |
+
background-color: transparent !important;
|
|
|
1041 |
display: block; /* ่ฎๆจ้ก็จ็ซไธ่ก */
|
1042 |
margin-bottom: 2px; /* ๅขๅ ๆจ้กไธๆน้่ท */
|
1043 |
padding-bottom: 2px; /* ๅ ๅ
ฅๅฐ้่ท */
|
1044 |
border-bottom: 1px solid rgba(255,255,255,0.2);
|
1045 |
+
}
|
1046 |
+
.tooltip-text {
|
|
|
1047 |
font-size: 13px; /* ็จๅพฎ็ธฎๅฐๅญ้ซ */
|
1048 |
+
}
|
1049 |
+
|
1050 |
/* ่ชฟๆดๅ่กจ็ฌฆ่ๅๆๅญ็้่ท */
|
1051 |
+
.tooltip-text ul {
|
1052 |
margin: 0;
|
1053 |
padding-left: 15px; /* ๆธๅฐๅ่กจ็ฌฆ่็็ธฎ้ฒ */
|
1054 |
+
}
|
1055 |
+
|
1056 |
+
.tooltip-text li {
|
1057 |
margin-bottom: 1px; /* ๆธๅฐๅ่กจ้
็ฎ้็้่ท */
|
1058 |
+
}
|
1059 |
+
.tooltip-text br {
|
1060 |
line-height: 1.2; /* ๆธๅฐ่ก่ท */
|
1061 |
+
}
|
1062 |
+
|
1063 |
+
.tooltip .tooltip-text::after {
|
1064 |
content: "";
|
1065 |
position: absolute;
|
1066 |
top: 100%;
|
|
|
1069 |
border-width: 5px;
|
1070 |
border-style: solid;
|
1071 |
border-color: rgba(44, 62, 80, 0.95) transparent transparent transparent;
|
1072 |
+
}
|
1073 |
+
.tooltip-left .tooltip-text::after {
|
|
|
1074 |
left: 20%;
|
1075 |
+
}
|
1076 |
+
|
1077 |
/* ๅณๅด็ฎญ้ ญ */
|
1078 |
+
.tooltip-right .tooltip-text::after {
|
1079 |
left: 80%;
|
1080 |
+
}
|
1081 |
+
.tooltip:hover .tooltip-text {
|
|
|
1082 |
visibility: visible;
|
1083 |
opacity: 1;
|
1084 |
+
}
|
1085 |
+
.tooltip .tooltip-text::after {
|
|
|
1086 |
content: "";
|
1087 |
position: absolute;
|
1088 |
top: 100%;
|
|
|
1091 |
border-width: 8px;
|
1092 |
border-style: solid;
|
1093 |
border-color: rgba(44, 62, 80, 0.95) transparent transparent transparent;
|
1094 |
+
}
|
1095 |
+
.uncertainty-mode .tooltip .tooltip-text {
|
|
|
1096 |
position: absolute;
|
1097 |
left: 100%;
|
1098 |
bottom: auto;
|
|
|
1100 |
transform: translateY(-50%);
|
1101 |
margin-left: 10px;
|
1102 |
z-index: 1000; /* ็ขบไฟๆ็คบๆกๅจๆไธๅฑค */
|
1103 |
+
}
|
1104 |
+
|
1105 |
+
.uncertainty-mode .tooltip .tooltip-text::after {
|
1106 |
content: "";
|
1107 |
position: absolute;
|
1108 |
top: 50%;
|
|
|
1111 |
border-width: 5px;
|
1112 |
border-style: solid;
|
1113 |
border-color: transparent rgba(44, 62, 80, 0.95) transparent transparent;
|
1114 |
+
}
|
1115 |
+
.uncertainty-mode .breed-content {
|
|
|
1116 |
font-size: 1.1rem; /* ๅขๅ ๅญ้ซๅคงๅฐ */
|
1117 |
+
}
|
|
|
1118 |
.description-section,
|
1119 |
.description-section p,
|
1120 |
.temperament-section,
|
1121 |
.temperament-section .value,
|
1122 |
.info-item,
|
1123 |
.info-item .value,
|
1124 |
+
.breed-content {
|
1125 |
font-size: 1.1rem !important; /* ไฝฟ็จ !important ็ขบไฟ่ฆ่ๅ
ถไปๆจฃๅผ */
|
1126 |
+
}
|
|
|
|
|
|
|
1127 |
|
1128 |
+
.recommendation-card {
|
1129 |
+
margin-bottom: 40px;
|
|
|
|
|
|
|
1130 |
}
|
|
|
|
|
1131 |
|
1132 |
+
.compatibility-scores {
|
1133 |
+
background: #f8f9fa;
|
1134 |
+
padding: 24px;
|
1135 |
+
border-radius: 12px;
|
1136 |
+
margin: 20px 0;
|
1137 |
+
}
|
1138 |
|
1139 |
+
.score-item {
|
1140 |
+
margin: 15px 0;
|
1141 |
+
}
|
1142 |
|
1143 |
+
.progress-bar {
|
1144 |
+
height: 12px;
|
1145 |
+
background-color: #e9ecef;
|
1146 |
+
border-radius: 6px;
|
1147 |
+
overflow: hidden;
|
1148 |
+
margin: 8px 0;
|
1149 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1150 |
|
1151 |
+
.progress {
|
1152 |
+
height: 100%;
|
1153 |
+
background: linear-gradient(90deg, #34C759, #30B350);
|
1154 |
+
border-radius: 6px;
|
1155 |
+
transition: width 0.6s ease;
|
1156 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1157 |
|
1158 |
+
.percentage {
|
1159 |
+
float: right;
|
1160 |
+
color: #34C759;
|
1161 |
+
font-weight: 600;
|
1162 |
+
}
|
1163 |
|
1164 |
+
.breed-details-section {
|
1165 |
+
margin: 30px 0;
|
1166 |
+
}
|
1167 |
+
|
1168 |
+
.subsection-title {
|
1169 |
+
font-size: 1.2em;
|
1170 |
+
color: #2c3e50;
|
1171 |
+
margin-bottom: 20px;
|
1172 |
+
display: flex;
|
1173 |
+
align-items: center;
|
1174 |
+
gap: 8px;
|
1175 |
+
}
|
1176 |
+
|
1177 |
+
.details-grid {
|
1178 |
+
display: grid;
|
1179 |
+
grid-template-columns: repeat(auto-fit, minmax(250px, 1fr));
|
1180 |
+
gap: 20px;
|
1181 |
+
background: #f8f9fa;
|
1182 |
+
padding: 20px;
|
1183 |
+
border-radius: 12px;
|
1184 |
+
border: 1px solid #e1e4e8;
|
1185 |
+
}
|
1186 |
+
|
1187 |
+
.detail-item {
|
1188 |
+
background: white;
|
1189 |
+
padding: 15px;
|
1190 |
+
border-radius: 8px;
|
1191 |
+
border: 1px solid #e1e4e8;
|
1192 |
+
}
|
1193 |
+
|
1194 |
+
.description-text {
|
1195 |
+
line-height: 1.8;
|
1196 |
+
color: #444;
|
1197 |
+
margin: 0;
|
1198 |
+
padding: 24px 30px; /* ่ชฟๆดๅ
ง้จ้่ท๏ผๅพ 20px ๆน็บ 24px 30px */
|
1199 |
+
background: #f8f9fa;
|
1200 |
+
border-radius: 12px;
|
1201 |
+
border: 1px solid #e1e4e8;
|
1202 |
+
text-align: justify; /* ๆทปๅ ๆๅญๅฐ้ฝ */
|
1203 |
+
word-wrap: break-word; /* ็ขบไฟ้ทๆๅญๆๆ่ก */
|
1204 |
+
word-spacing: 1px; /* ๅ ๅ
ฅๅญ้่ท */
|
1205 |
+
}
|
1206 |
+
|
1207 |
+
/* ๅทฅๅ
ทๆ็คบๆน้ฒ */
|
1208 |
+
.tooltip {
|
1209 |
+
position: relative;
|
1210 |
+
display: inline-flex;
|
1211 |
+
align-items: center;
|
1212 |
+
gap: 4px;
|
1213 |
+
cursor: help;
|
1214 |
+
padding: 5px 0;
|
1215 |
+
}
|
1216 |
+
|
1217 |
+
.tooltip .tooltip-text {
|
1218 |
+
visibility: hidden;
|
1219 |
+
width: 280px;
|
1220 |
+
background-color: rgba(44, 62, 80, 0.95);
|
1221 |
+
color: white;
|
1222 |
+
text-align: left;
|
1223 |
+
border-radius: 8px;
|
1224 |
+
padding: 12px 15px;
|
1225 |
+
position: absolute;
|
1226 |
+
z-index: 1000;
|
1227 |
+
bottom: calc(100% + 15px);
|
1228 |
+
left: 50%;
|
1229 |
+
transform: translateX(-50%);
|
1230 |
+
opacity: 0;
|
1231 |
+
transition: all 0.3s ease;
|
1232 |
+
font-size: 14px;
|
1233 |
+
line-height: 1.4;
|
1234 |
+
box-shadow: 0 4px 6px rgba(0, 0, 0, 0.2);
|
1235 |
+
white-space: normal;
|
1236 |
+
}
|
1237 |
+
|
1238 |
+
.tooltip:hover .tooltip-text {
|
1239 |
+
visibility: visible;
|
1240 |
+
opacity: 1;
|
1241 |
+
}
|
1242 |
+
|
1243 |
+
.score-badge {
|
1244 |
+
background-color: #34C759;
|
1245 |
+
color: white;
|
1246 |
+
padding: 6px 12px;
|
1247 |
+
border-radius: 20px;
|
1248 |
+
font-size: 0.9em;
|
1249 |
+
margin-left: 10px;
|
1250 |
+
font-weight: 500;
|
1251 |
+
box-shadow: 0 2px 4px rgba(52, 199, 89, 0.2);
|
1252 |
+
}
|
1253 |
+
""") as iface:
|
1254 |
|
1255 |
+
gr.HTML("<h1 style='text-align: center;'>๐ถ Dog Breed Classifier ๐</h1>")
|
1256 |
+
|
1257 |
+
# ไฝฟ็จ Tabs ไพๅ้ๅ
ฉๅๅ่ฝ
|
1258 |
+
with gr.Tabs():
|
1259 |
+
# ็ฌฌไธๅ Tab๏ผๅๆ็่พจ่ญๅ่ฝ
|
1260 |
+
with gr.TabItem("Breed Detection"):
|
1261 |
+
gr.HTML("<p style='text-align: center;'>Upload a picture of a dog, and the model will predict its breed and provide detailed information!</p>")
|
1262 |
+
gr.HTML("<p style='text-align: center; color: #666; font-size: 0.9em;'>Note: The model's predictions may not always be 100% accurate, and it is recommended to use the results as a reference.</p>")
|
1263 |
+
|
1264 |
+
with gr.Row():
|
1265 |
+
input_image = gr.Image(label="Upload a dog image", type="pil")
|
1266 |
+
output_image = gr.Image(label="Annotated Image")
|
1267 |
+
|
1268 |
+
output = gr.HTML(label="Prediction Results")
|
1269 |
+
initial_state = gr.State()
|
1270 |
+
|
1271 |
+
input_image.change(
|
1272 |
+
predict,
|
1273 |
+
inputs=input_image,
|
1274 |
+
outputs=[output, output_image, initial_state]
|
1275 |
+
)
|
1276 |
+
|
1277 |
+
gr.Examples(
|
1278 |
+
examples=['Border_Collie.jpg',
|
1279 |
+
'Golden_Retriever.jpeg',
|
1280 |
+
'Saint_Bernard.jpeg',
|
1281 |
+
'Samoyed.jpg',
|
1282 |
+
'French_Bulldog.jpeg'],
|
1283 |
+
inputs=input_image
|
1284 |
+
)
|
1285 |
+
|
1286 |
+
# ็ฌฌไบๅ Tab๏ผๅ็จฎๆฏ่ผๅ่ฝ
|
1287 |
+
with gr.TabItem("Breed Comparison"):
|
1288 |
+
gr.HTML("<p style='text-align: center;'>Select two dog breeds to compare their characteristics and care requirements.</p>")
|
1289 |
+
|
1290 |
+
with gr.Row():
|
1291 |
+
breed1_dropdown = gr.Dropdown(
|
1292 |
+
choices=dog_breeds,
|
1293 |
+
label="Select First Breed",
|
1294 |
+
value="Golden_Retriever"
|
1295 |
+
)
|
1296 |
+
breed2_dropdown = gr.Dropdown(
|
1297 |
+
choices=dog_breeds,
|
1298 |
+
label="Select Second Breed",
|
1299 |
+
value="Border_Collie"
|
1300 |
+
)
|
1301 |
+
|
1302 |
+
compare_btn = gr.Button("Compare Breeds")
|
1303 |
+
comparison_output = gr.HTML(label="Comparison Results")
|
1304 |
+
|
1305 |
+
def show_comparison(breed1, breed2):
|
1306 |
+
if not breed1 or not breed2:
|
1307 |
+
return "Please select two breeds to compare"
|
1308 |
+
|
1309 |
+
breed1_info = get_dog_description(breed1)
|
1310 |
+
breed2_info = get_dog_description(breed2)
|
1311 |
+
|
1312 |
+
html_output = f"""
|
1313 |
+
<div class="dog-info-card">
|
1314 |
+
<div class="comparison-grid" style="display: grid; grid-template-columns: 1fr 1fr; gap: 20px;">
|
1315 |
+
<div class="breed-info">
|
1316 |
+
<h2 class="section-title">
|
1317 |
+
<span class="icon">๐</span> {breed1.replace('_', ' ')}
|
1318 |
+
</h2>
|
1319 |
+
<div class="info-section">
|
1320 |
+
<div class="info-item">
|
1321 |
+
<span class="tooltip">
|
1322 |
+
<span class="icon">๐</span>
|
1323 |
+
<span class="label">Size:</span>
|
1324 |
+
<span class="value">{breed1_info['Size']}</span>
|
1325 |
+
</span>
|
1326 |
+
</div>
|
1327 |
+
<div class="info-item">
|
1328 |
+
<span class="tooltip">
|
1329 |
+
<span class="icon">๐</span>
|
1330 |
+
<span class="label">Exercise Needs:</span>
|
1331 |
+
<span class="value">{breed1_info['Exercise Needs']}</span>
|
1332 |
+
</span>
|
1333 |
+
</div>
|
1334 |
+
<div class="info-item">
|
1335 |
+
<span class="tooltip">
|
1336 |
+
<span class="icon">โ๏ธ</span>
|
1337 |
+
<span class="label">Grooming:</span>
|
1338 |
+
<span class="value">{breed1_info['Grooming Needs']}</span>
|
1339 |
+
</span>
|
1340 |
+
</div>
|
1341 |
+
<div class="info-item">
|
1342 |
+
<span class="tooltip">
|
1343 |
+
<span class="icon">๐จโ๐ฉโ๐งโ๐ฆ</span>
|
1344 |
+
<span class="label">Good with Children:</span>
|
1345 |
+
<span class="value">{breed1_info['Good with Children']}</span>
|
1346 |
+
</span>
|
1347 |
+
</div>
|
1348 |
+
</div>
|
1349 |
+
</div>
|
1350 |
+
|
1351 |
+
<div class="breed-info">
|
1352 |
+
<h2 class="section-title">
|
1353 |
+
<span class="icon">๐</span> {breed2.replace('_', ' ')}
|
1354 |
+
</h2>
|
1355 |
+
<div class="info-section">
|
1356 |
+
<div class="info-item">
|
1357 |
+
<span class="tooltip">
|
1358 |
+
<span class="icon">๐</span>
|
1359 |
+
<span class="label">Size:</span>
|
1360 |
+
<span class="value">{breed2_info['Size']}</span>
|
1361 |
+
</span>
|
1362 |
+
</div>
|
1363 |
+
<div class="info-item">
|
1364 |
+
<span class="tooltip">
|
1365 |
+
<span class="icon">๐</span>
|
1366 |
+
<span class="label">Exercise Needs:</span>
|
1367 |
+
<span class="value">{breed2_info['Exercise Needs']}</span>
|
1368 |
+
</span>
|
1369 |
+
</div>
|
1370 |
+
<div class="info-item">
|
1371 |
+
<span class="tooltip">
|
1372 |
+
<span class="icon">โ๏ธ</span>
|
1373 |
+
<span class="label">Grooming:</span>
|
1374 |
+
<span class="value">{breed2_info['Grooming Needs']}</span>
|
1375 |
+
</span>
|
1376 |
+
</div>
|
1377 |
+
<div class="info-item">
|
1378 |
+
<span class="tooltip">
|
1379 |
+
<span class="icon">๐จโ๐ฉโ๐งโ๐ฆ</span>
|
1380 |
+
<span class="label">Good with Children:</span>
|
1381 |
+
<span class="value">{breed2_info['Good with Children']}</span>
|
1382 |
+
</span>
|
1383 |
+
</div>
|
1384 |
+
</div>
|
1385 |
+
</div>
|
1386 |
+
</div>
|
1387 |
+
</div>
|
1388 |
+
"""
|
1389 |
+
return html_output
|
1390 |
+
|
1391 |
+
compare_btn.click(
|
1392 |
+
show_comparison,
|
1393 |
+
inputs=[breed1_dropdown, breed2_dropdown],
|
1394 |
+
outputs=comparison_output
|
1395 |
+
)
|
1396 |
+
|
1397 |
+
# ็ฌฌไธๅ Tab๏ผๅ็จฎๆจ่ฆๅ่ฝ
|
1398 |
+
with gr.TabItem("Breed Recommendation"):
|
1399 |
+
gr.HTML("<p style='text-align: center;'>Tell us about your lifestyle, and we'll recommend the perfect dog breeds for you!</p>")
|
1400 |
+
|
1401 |
+
with gr.Row():
|
1402 |
+
with gr.Column():
|
1403 |
+
living_space = gr.Radio(
|
1404 |
+
choices=["apartment", "house_small", "house_large"],
|
1405 |
+
label="What type of living space do you have?",
|
1406 |
+
info="Choose your current living situation",
|
1407 |
+
value="apartment"
|
1408 |
+
)
|
1409 |
+
|
1410 |
+
exercise_time = gr.Slider(
|
1411 |
+
minimum=0,
|
1412 |
+
maximum=180,
|
1413 |
+
value=60,
|
1414 |
+
label="Daily exercise time (minutes)",
|
1415 |
+
info="Consider walks, play time, and training"
|
1416 |
+
)
|
1417 |
+
|
1418 |
+
grooming_commitment = gr.Radio(
|
1419 |
+
choices=["low", "medium", "high"],
|
1420 |
+
label="Grooming commitment level",
|
1421 |
+
info="Low: monthly, Medium: weekly, High: daily",
|
1422 |
+
value="medium"
|
1423 |
+
)
|
1424 |
+
|
1425 |
+
with gr.Column():
|
1426 |
+
experience_level = gr.Radio(
|
1427 |
+
choices=["beginner", "intermediate", "advanced"],
|
1428 |
+
label="Dog ownership experience",
|
1429 |
+
info="Be honest - this helps find the right match",
|
1430 |
+
value="beginner"
|
1431 |
+
)
|
1432 |
+
|
1433 |
+
has_children = gr.Checkbox(
|
1434 |
+
label="Have children at home",
|
1435 |
+
info="Helps recommend child-friendly breeds"
|
1436 |
+
)
|
1437 |
+
|
1438 |
+
noise_tolerance = gr.Radio(
|
1439 |
+
choices=["low", "medium", "high"],
|
1440 |
+
label="Noise tolerance level",
|
1441 |
+
info="Some breeds are more vocal than others",
|
1442 |
+
value="medium"
|
1443 |
+
)
|
1444 |
+
|
1445 |
+
|
1446 |
+
# ่จญ็ฝฎๆ้็้ปๆไบไปถ
|
1447 |
+
get_recommendations_btn = gr.Button("Find My Perfect Match! ๐", variant="primary")
|
1448 |
+
recommendation_output = gr.HTML(label="Breed Recommendations")
|
1449 |
+
|
1450 |
+
def process_recommendations(living_space, exercise_time, grooming_commitment,
|
1451 |
+
experience_level, has_children, noise_tolerance):
|
1452 |
+
try:
|
1453 |
+
user_prefs = UserPreferences(
|
1454 |
+
living_space=living_space,
|
1455 |
+
exercise_time=exercise_time,
|
1456 |
+
grooming_commitment=grooming_commitment,
|
1457 |
+
experience_level=experience_level,
|
1458 |
+
has_children=has_children,
|
1459 |
+
noise_tolerance=noise_tolerance,
|
1460 |
+
space_for_play=True if living_space != "apartment" else False,
|
1461 |
+
other_pets=False,
|
1462 |
+
climate="moderate"
|
1463 |
+
)
|
1464 |
+
|
1465 |
+
recommendations = get_breed_recommendations(user_prefs)
|
1466 |
+
return format_recommendation_html(recommendations)
|
1467 |
+
except Exception as e:
|
1468 |
+
print(f"Error in process_recommendations: {str(e)}")
|
1469 |
+
return f"An error occurred: {str(e)}"
|
1470 |
+
|
1471 |
+
# ้่กๆฏ้้ต - ็ขบไฟๆ้้ปๆไบไปถๆๆญฃ็ขบ้ฃๆฅๅฐ่็ๅฝๆธ
|
1472 |
+
get_recommendations_btn.click(
|
1473 |
+
fn=process_recommendations, # ่็ๅฝๆธ
|
1474 |
+
inputs=[
|
1475 |
+
living_space,
|
1476 |
+
exercise_time,
|
1477 |
+
grooming_commitment,
|
1478 |
+
experience_level,
|
1479 |
+
has_children,
|
1480 |
+
noise_tolerance
|
1481 |
+
],
|
1482 |
+
outputs=recommendation_output # ่ผธๅบ็ตๆ็ไฝ็ฝฎ
|
1483 |
+
)
|
1484 |
+
|
1485 |
+
gr.HTML('For more details on this project and other work, feel free to visit my GitHub <a href="https://github.com/Eric-Chung-0511/Learning-Record/tree/main/Data%20Science%20Projects/Dog_Breed_Classifier">Dog Breed Classifier</a>')
|
1486 |
|
1487 |
if __name__ == "__main__":
|
1488 |
+
|
1489 |
+
iface.launch(share=True)
|