Spaces:
Running
on
Zero
Running
on
Zero
File size: 18,323 Bytes
406922d 1274075 2b82929 853de85 c255e80 4700246 c255e80 55b65ff c255e80 406922d b4e17e5 406922d 2439595 406922d 922691a 406922d 922691a 406922d 922691a 406922d 853de85 7babadc 4a1799c c255e80 3186b74 2db8b4f 78f3d66 7b1fc43 192f46e 7b1fc43 192f46e 7b1fc43 5d323e9 7b1fc43 5d323e9 192f46e 18b19dd 5d323e9 192f46e 5d323e9 192f46e 78f3d66 4700246 ad2c4a8 78f3d66 4700246 1274075 ad2c4a8 78f3d66 f810bab 63d6ec9 39f714b c255e80 406922d 3186b74 78f3d66 f810bab 18b19dd 43f7280 39f714b a06cdb4 c255e80 cdaf020 2db8b4f 01ae78a 39f714b 01ae78a 7b1fc43 f810bab 01ae78a 78f3d66 39f714b 78f3d66 01ae78a f810bab 43f7280 5d323e9 39f714b 5d323e9 cdaf020 39f714b 43f7280 2c3948c 12d9306 9236f5c 39f714b cdaf020 78f3d66 f810bab 2c3948c 39f714b c255e80 78f3d66 30157d2 18b19dd 30157d2 18b19dd 30157d2 e9cbeff 01ae78a e9cbeff cdaf020 30157d2 cdaf020 ef9de25 f810bab cdaf020 30157d2 34f44fd 78f3d66 406922d 2b04738 |
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 |
import os
import numpy as np
import torch
import torch.nn as nn
import gradio as gr
from torchvision.models import efficientnet_v2_m, EfficientNet_V2_M_Weights
import torch.nn.functional as F
from torchvision import transforms
from PIL import Image, ImageDraw, ImageFont
from data_manager import get_dog_description
from urllib.parse import quote
from ultralytics import YOLO
import asyncio
# 下載YOLOv8預訓練模型
model_yolo = YOLO('yolov8n.pt') # 使用 YOLOv8 預訓練模型
dog_breeds = ["Afghan_Hound", "African_Hunting_Dog", "Airedale", "American_Staffordshire_Terrier",
"Appenzeller", "Australian_Terrier", "Bedlington_Terrier", "Bernese_Mountain_Dog",
"Blenheim_Spaniel", "Border_Collie", "Border_Terrier", "Boston_Bull", "Bouvier_Des_Flandres",
"Brabancon_Griffon", "Brittany_Spaniel", "Cardigan", "Chesapeake_Bay_Retriever",
"Chihuahua", "Dandie_Dinmont", "Doberman", "English_Foxhound", "English_Setter",
"English_Springer", "EntleBucher", "Eskimo_Dog", "French_Bulldog", "German_Shepherd",
"German_Short-Haired_Pointer", "Gordon_Setter", "Great_Dane", "Great_Pyrenees",
"Greater_Swiss_Mountain_Dog", "Ibizan_Hound", "Irish_Setter", "Irish_Terrier",
"Irish_Water_Spaniel", "Irish_Wolfhound", "Italian_Greyhound", "Japanese_Spaniel",
"Kerry_Blue_Terrier", "Labrador_Retriever", "Lakeland_Terrier", "Leonberg", "Lhasa",
"Maltese_Dog", "Mexican_Hairless", "Newfoundland", "Norfolk_Terrier", "Norwegian_Elkhound",
"Norwich_Terrier", "Old_English_Sheepdog", "Pekinese", "Pembroke", "Pomeranian",
"Rhodesian_Ridgeback", "Rottweiler", "Saint_Bernard", "Saluki", "Samoyed",
"Scotch_Terrier", "Scottish_Deerhound", "Sealyham_Terrier", "Shetland_Sheepdog",
"Shih-Tzu", "Siberian_Husky", "Staffordshire_Bullterrier", "Sussex_Spaniel",
"Tibetan_Mastiff", "Tibetan_Terrier", "Walker_Hound", "Weimaraner",
"Welsh_Springer_Spaniel", "West_Highland_White_Terrier", "Yorkshire_Terrier",
"Affenpinscher", "Basenji", "Basset", "Beagle", "Black-and-Tan_Coonhound", "Bloodhound",
"Bluetick", "Borzoi", "Boxer", "Briard", "Bull_Mastiff", "Cairn", "Chow", "Clumber",
"Cocker_Spaniel", "Collie", "Curly-Coated_Retriever", "Dhole", "Dingo",
"Flat-Coated_Retriever", "Giant_Schnauzer", "Golden_Retriever", "Groenendael", "Keeshond",
"Kelpie", "Komondor", "Kuvasz", "Malamute", "Malinois", "Miniature_Pinscher",
"Miniature_Poodle", "Miniature_Schnauzer", "Otterhound", "Papillon", "Pug", "Redbone",
"Schipperke", "Silky_Terrier", "Soft-Coated_Wheaten_Terrier", "Standard_Poodle",
"Standard_Schnauzer", "Toy_Poodle", "Toy_Terrier", "Vizsla", "Whippet",
"Wire-Haired_Fox_Terrier"]
class MultiHeadAttention(nn.Module):
def __init__(self, in_dim, num_heads=8):
super().__init__()
self.num_heads = num_heads
self.head_dim = max(1, in_dim // num_heads)
self.scaled_dim = self.head_dim * num_heads
self.fc_in = nn.Linear(in_dim, self.scaled_dim)
self.query = nn.Linear(self.scaled_dim, self.scaled_dim)
self.key = nn.Linear(self.scaled_dim, self.scaled_dim)
self.value = nn.Linear(self.scaled_dim, self.scaled_dim)
self.fc_out = nn.Linear(self.scaled_dim, in_dim)
def forward(self, x):
N = x.shape[0]
x = self.fc_in(x)
q = self.query(x).view(N, self.num_heads, self.head_dim)
k = self.key(x).view(N, self.num_heads, self.head_dim)
v = self.value(x).view(N, self.num_heads, self.head_dim)
energy = torch.einsum("nqd,nkd->nqk", [q, k])
attention = F.softmax(energy / (self.head_dim ** 0.5), dim=2)
out = torch.einsum("nqk,nvd->nqd", [attention, v])
out = out.reshape(N, self.scaled_dim)
out = self.fc_out(out)
return out
class BaseModel(nn.Module):
def __init__(self, num_classes, device='cuda' if torch.cuda.is_available() else 'cpu'):
super().__init__()
self.device = device
self.backbone = efficientnet_v2_m(weights=EfficientNet_V2_M_Weights.IMAGENET1K_V1)
self.feature_dim = self.backbone.classifier[1].in_features
self.backbone.classifier = nn.Identity()
self.num_heads = max(1, min(8, self.feature_dim // 64))
self.attention = MultiHeadAttention(self.feature_dim, num_heads=self.num_heads)
self.classifier = nn.Sequential(
nn.LayerNorm(self.feature_dim),
nn.Dropout(0.3),
nn.Linear(self.feature_dim, num_classes)
)
self.to(device)
def forward(self, x):
x = x.to(self.device)
features = self.backbone(x)
attended_features = self.attention(features)
logits = self.classifier(attended_features)
return logits, attended_features
num_classes = 120
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = BaseModel(num_classes=num_classes, device=device)
checkpoint = torch.load('best_model_81_dog.pth', map_location=torch.device('cpu'))
model.load_state_dict(checkpoint['model_state_dict'])
# evaluation mode
model.eval()
# Image preprocessing function
def preprocess_image(image):
# If the image is numpy.ndarray turn into PIL.Image
if isinstance(image, np.ndarray):
image = Image.fromarray(image)
# Use torchvision.transforms to process images
transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225]),
])
return transform(image).unsqueeze(0)
def get_akc_breeds_link():
return "https://www.akc.org/dog-breeds/"
# def predict(image):
# if image is None:
# return "Please upload an image to get started.", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
# try:
# image_tensor = preprocess_image(image)
# with torch.no_grad():
# output = model(image_tensor)
# logits = output[0] if isinstance(output, tuple) else output
# probabilities = F.softmax(logits, dim=1)
# topk_probs, topk_indices = torch.topk(probabilities, k=3)
# top1_prob = topk_probs[0][0].item()
# topk_breeds = [dog_breeds[idx.item()] for idx in topk_indices[0]]
# topk_probs_percent = [f"{prob.item() * 100:.2f}%" for prob in topk_probs[0]]
# if top1_prob >= 0.5:
# breed = topk_breeds[0]
# description = get_dog_description(breed)
# return format_description(description, breed), gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
# elif top1_prob < 0.2:
# return ("The image is too unclear or the dog breed is not in the dataset. Please upload a clearer image of the dog.",
# gr.update(visible=False), gr.update(visible=False), gr.update(visible=False))
# else:
# explanation = (
# f"The model couldn't confidently identify the breed. Here are the top 3 possible breeds:\n\n"
# f"1. **{topk_breeds[0]}** ({topk_probs_percent[0]} confidence)\n"
# f"2. **{topk_breeds[1]}** ({topk_probs_percent[1]} confidence)\n"
# f"3. **{topk_breeds[2]}** ({topk_probs_percent[2]} confidence)\n\n"
# "Click on a button to view more information about the breed."
# )
# return explanation, gr.update(visible=True, value=f"More about {topk_breeds[0]}"), gr.update(visible=True, value=f"More about {topk_breeds[1]}"), gr.update(visible=True, value=f"More about {topk_breeds[2]}")
# except Exception as e:
# return f"An error occurred: {e}", gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
# def format_description(description, breed):
# if isinstance(description, dict):
# formatted_description = "\n\n".join([f"**{key}**: {value}" for key, value in description.items()])
# else:
# formatted_description = description
# akc_link = get_akc_breeds_link()
# formatted_description += f"\n\n**Want to learn more about dog breeds?** [Visit the AKC dog breeds page]({akc_link}) and search for {breed} to find detailed information."
# disclaimer = ("\n\n*Disclaimer: The external link provided leads to the American Kennel Club (AKC) dog breeds page. "
# "You may need to search for the specific breed on that page. "
# "I am not responsible for the content on external sites. "
# "Please refer to the AKC's terms of use and privacy policy.*")
# formatted_description += disclaimer
# return formatted_description
# def show_details(breed):
# breed_name = breed.split("More about ")[-1]
# description = get_dog_description(breed_name)
# return format_description(description, breed_name)
# with gr.Blocks(css="""
# .container {
# max-width: 900px;
# margin: 0 auto;
# padding: 20px;
# background-color: rgba(255, 255, 255, 0.9);
# border-radius: 15px;
# box-shadow: 0 0 20px rgba(0, 0, 0, 0.1);
# }
# .gr-form { display: flex; flex-direction: column; align-items: center; }
# .gr-box { width: 100%; max-width: 500px; }
# .output-markdown, .output-image {
# margin-top: 20px;
# padding: 15px;
# background-color: #f5f5f5;
# border-radius: 10px;
# }
# .examples {
# display: flex;
# justify-content: center;
# flex-wrap: wrap;
# gap: 10px;
# margin-top: 20px;
# }
# .examples img {
# width: 100px;
# height: 100px;
# object-fit: cover;
# }
# """) as iface:
# gr.HTML("<h1 style='font-family:Roboto; font-weight:bold; color:#2C3E50; text-align:center;'>🐶 Dog Breed Classifier 🔍</h1>")
# gr.HTML("<p style='font-family:Open Sans; color:#34495E; text-align:center;'>Upload a picture of a dog, and the model will predict its breed, provide detailed information, and include an extra information link!</p>")
# with gr.Row():
# input_image = gr.Image(label="Upload a dog image", type="numpy")
# output = gr.Markdown(label="Prediction Results")
# with gr.Row():
# btn1 = gr.Button("View More 1", visible=False)
# btn2 = gr.Button("View More 2", visible=False)
# btn3 = gr.Button("View More 3", visible=False)
# input_image.change(predict, inputs=input_image, outputs=[output, btn1, btn2, btn3])
# btn1.click(show_details, inputs=btn1, outputs=output)
# btn2.click(show_details, inputs=btn2, outputs=output)
# btn3.click(show_details, inputs=btn3, outputs=output)
# gr.Examples(
# examples=['Border_Collie.jpg', 'Golden_Retriever.jpeg', 'Saint_Bernard.jpeg', 'French_Bulldog.jpeg', 'Samoyed.jpg'],
# inputs=input_image
# )
# 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%20Breed%20Classifier">Dog Breed Classifier</a>')
# # launch the program
# if __name__ == "__main__":
# iface.launch()
# 格式化狗的品種描述函數
def format_description(description, breed, is_multi_dog=False, dog_number=None):
if isinstance(description, dict):
formatted_description = "\n\n".join([f"**{key}**: {value}" for key, value in description.items() if key != "Breed"])
else:
formatted_description = description
header = f"**Dog {dog_number}: {breed}**\n\n" if is_multi_dog else f"**Breed: {breed}**\n\n"
formatted_description = f"""
{header}
{formatted_description}
**Want to learn more about dog breeds?**
[Visit the AKC dog breeds page]({get_akc_breeds_link()}) and search for {breed} to find detailed information.
*Disclaimer: The external link provided leads to the American Kennel Club (AKC) dog breeds page.
You may need to search for the specific breed on that page.
I am not responsible for the content on external sites.
Please refer to the AKC's terms of use and privacy policy.*
"""
return formatted_description
# 預測單隻狗的品種
async def predict_single_dog(image):
image_tensor = preprocess_image(image)
with torch.no_grad():
output = model(image_tensor)
logits = output[0] if isinstance(output, tuple) else output
probabilities = F.softmax(logits, dim=1)
topk_probs, topk_indices = torch.topk(probabilities, k=3)
top1_prob = topk_probs[0][0].item()
topk_breeds = [dog_breeds[idx.item()] for idx in topk_indices[0]]
topk_probs_percent = [f"{prob.item() * 100:.2f}%" for prob in topk_probs[0]]
return top1_prob, topk_breeds, topk_probs_percent
# 偵測多隻狗的函數
async def detect_multiple_dogs(image):
try:
results = model_yolo(image)
dogs = []
for result in results:
for box in result.boxes:
if box.cls == 16: # COCO dataset class for dog is 16
xyxy = box.xyxy[0].tolist()
confidence = box.conf.item()
cropped_image = image.crop((xyxy[0], xyxy[1], xyxy[2], xyxy[3]))
dogs.append((cropped_image, confidence, xyxy))
return dogs
except Exception as e:
print(f"Error in detect_multiple_dogs: {e}")
return []
# 主預測函數
async def predict(image):
if image is None:
return "Please upload an image to start.", None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
try:
if isinstance(image, np.ndarray):
image = Image.fromarray(image)
# YOLO 偵測多隻狗
dogs = await detect_multiple_dogs(image)
if len(dogs) == 0:
return "No dogs detected. Please upload a clear image of a dog.", None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
explanations = []
buttons = []
annotated_image = image.copy()
draw = ImageDraw.Draw(annotated_image)
font = ImageFont.load_default()
for i, (cropped_image, _, box) in enumerate(dogs, 1):
top1_prob, topk_breeds, topk_probs_percent = await predict_single_dog(cropped_image)
# 標註框框標籤更醒目
draw.rectangle(box, outline="red", width=3)
draw.text((box[0], box[1]), f"Dog {i}", fill="yellow", font=font)
if top1_prob >= 0.5:
breed = topk_breeds[0]
description = get_dog_description(breed)
explanations.append(f"Dog {i}: **{breed}**\n\n{format_description(description, breed, is_multi_dog=True, dog_number=i)}")
else:
explanation = f"""
Dog {i}: Detected with moderate confidence. Here are the top 3 possible breeds:
1. **{topk_breeds[0]}** ({topk_probs_percent[0]})
2. **{topk_breeds[1]}** ({topk_probs_percent[1]})
3. **{topk_breeds[2]}** ({topk_probs_percent[2]})
"""
explanations.append(explanation)
for breed in topk_breeds:
buttons.append(f"More about Dog {i}: {breed}")
final_explanation = "\n\n---\n\n".join(explanations)
if buttons:
return final_explanation, annotated_image, gr.update(visible=True, choices=buttons), gr.update(visible=False), gr.update(visible=False)
else:
return final_explanation, annotated_image, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
except Exception as e:
return f"An error occurred: {e}", None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False)
# 顯示選擇的品種詳細信息
async def show_details(choice):
if not choice:
return "Please select a breed to view details."
try:
_, breed = choice.split(": ", 1)
description = get_dog_description(breed)
return format_description(description, breed)
except Exception as e:
return f"An error occurred while showing details: {e}"
# Gradio 介面設置
with gr.Blocks(css="""
.container { max-width: 900px; margin: auto; padding: 20px; }
.gr-box { border-radius: 15px; }
.output-markdown { margin-top: 20px; padding: 15px; background-color: #f5f5f5; border-radius: 10px; }
.examples { display: flex; justify-content: center; flex-wrap: wrap; gap: 10px; margin-top: 20px; }
.examples img { width: 100px; height: 100px; object-fit: cover; }
""") as iface:
gr.HTML("<h1 style='text-align: center;'>🐶 Dog Breed Classifier 🔍</h1>")
gr.HTML("<p style='text-align: center;'>Upload a picture of a dog, and the model will predict its breed, provide detailed information, and include an extra information link!</p>")
with gr.Row():
input_image = gr.Image(label="Upload a dog image", type="pil")
output_image = gr.Image(label="Annotated Image")
output = gr.Markdown(label="Prediction Results")
breed_buttons = gr.Radio([], label="Select breed for more details", visible=False)
breed_details = gr.Markdown(label="Breed Details")
input_image.change(
predict,
inputs=input_image,
outputs=[output, output_image, breed_buttons, breed_details]
)
breed_buttons.select(
show_details,
inputs=breed_buttons,
outputs=breed_details
)
gr.Examples(
examples=['Border_Collie.jpg', 'Golden_Retriever.jpeg', 'Saint_Bernard.jpeg', 'French_Bulldog.jpeg', 'Samoyed.jpg'],
inputs=input_image
)
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>')
if __name__ == "__main__":
iface.launch()
|