Spaces:
Running
on
Zero
Running
on
Zero
| 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 | |
| from data_manager import get_dog_description | |
| from urllib.parse import quote | |
| dog_breeds = ["Afghan_Hound(阿富汗獵犬)", "African_Hunting_Dog(非洲野犬)", "Airedale(艾爾谷犬)", | |
| "American_Staffordshire_Terrier(美國斯塔福郡梗)", "Appenzeller(亞賓澤爾犬)", | |
| "Australian_Terrier(澳大利亞梗)", "Bedlington_Terrier(貝德靈頓梗)", | |
| "Bernese_Mountain_Dog(伯恩山犬)", "Blenheim_Spaniel(布萊尼姆獵犬)", | |
| "Border_Collie(邊境牧羊犬)", "Border_Terrier(邊境梗)", "Boston_Bull(波士頓梗)", | |
| "Bouvier_Des_Flandres(法蘭德斯牧羊犬)", "Brabancon_Griffon(布魯塞爾格里芬犬)", | |
| "Brittany_Spaniel(布列塔尼獵犬)", "Cardigan(卡迪根威爾士柯基犬)", | |
| "Chesapeake_Bay_Retriever(切薩皮克灣獵犬)", "Chihuahua(吉娃娃)", | |
| "Dandie_Dinmont(丹第丁蒙梗)", "Doberman(杜賓犬)", "English_Foxhound(英國獵狐犬)", | |
| "English_Setter(英國雪達犬)", "English_Springer(英國跳獵犬)", | |
| "EntleBucher(恩特雷布赫山地犬)", "Eskimo_Dog(愛斯基摩犬)", "French_Bulldog(法國鬥牛犬)", | |
| "German_Shepherd(德國牧羊犬)", "German_Short-Haired_Pointer(德國短毛指示犬)", | |
| "Gordon_Setter(戈登雪達犬)", "Great_Dane(大丹犬)", "Great_Pyrenees(大白熊犬)", | |
| "Greater_Swiss_Mountain_Dog(大瑞士山地犬)", "Ibizan_Hound(依比沙獵犬)", | |
| "Irish_Setter(愛爾蘭雪達犬)", "Irish_Terrier(愛爾蘭梗)", | |
| "Irish_Water_Spaniel(愛爾蘭水獵犬)", "Irish_Wolfhound(愛爾蘭獵狼犬)", | |
| "Italian_Greyhound(義大利灰狗)", "Japanese_Spaniel(日本狆)", | |
| "Kerry_Blue_Terrier(凱利藍梗)", "Labrador_Retriever(拉布拉多尋回犬)", | |
| "Lakeland_Terrier(湖畔梗)", "Leonberg(獅毛狗)", "Lhasa(拉薩犬)", | |
| "Maltese_Dog(馬爾濟斯犬)", "Mexican_Hairless(墨西哥無毛犬)", "Newfoundland(紐芬蘭犬)", | |
| "Norfolk_Terrier(諾福克梗)", "Norwegian_Elkhound(挪威獵麋犬)", | |
| "Norwich_Terrier(諾利治梗)", "Old_English_Sheepdog(古代英國牧羊犬)", | |
| "Pekinese(北京犬)", "Pembroke(威爾士柯基犬)", "Pomeranian(博美犬)", | |
| "Rhodesian_Ridgeback(羅得西亞脊背犬)", "Rottweiler(羅威納犬)", | |
| "Saint_Bernard(聖伯納犬)", "Saluki(薩路基獵犬)", "Samoyed(薩摩耶犬)", | |
| "Scotch_Terrier(蘇格蘭梗)", "Scottish_Deerhound(蘇格蘭獵鹿犬)", | |
| "Sealyham_Terrier(錫利哈姆梗)", "Shetland_Sheepdog(設得蘭牧羊犬)", | |
| "Shih-Tzu(西施犬)", "Siberian_Husky(西伯利亞哈士奇)", | |
| "Staffordshire_Bullterrier(斯塔福郡鬥牛梗)", "Sussex_Spaniel(蘇塞克斯獵犬)", | |
| "Tibetan_Mastiff(藏獒)", "Tibetan_Terrier(西藏梗)", "Walker_Hound(沃克獵犬)", | |
| "Weimaraner(威瑪犬)", "Welsh_Springer_Spaniel(威爾士跳獵犬)", | |
| "West_Highland_White_Terrier(西高地白梗)", "Yorkshire_Terrier(約克夏梗)", | |
| "Affenpinscher(猴犬)", "Basenji(巴辛吉犬)", "Basset(巴吉度獵犬)", "Beagle(比格犬)", | |
| "Black-and-Tan_Coonhound(黑褐獵浣熊犬)", "Bloodhound(尋血獵犬)", | |
| "Bluetick(布魯提克獵犬)", "Borzoi(俄羅斯獵狼犬)", "Boxer(拳師犬)", "Briard(布里亞犬)", | |
| "Bull_Mastiff(獒犬)", "Cairn(凱恩梗)", "Chow(鬆獅犬)", "Clumber(克倫伯獵犬)", | |
| "Cocker_Spaniel(可卡獵犬)", "Collie(柯利牧羊犬)", "Curly-Coated_Retriever(捲毛尋回犬)", | |
| "Dhole(豺)", "Dingo(澳洲野犬)", "Flat-Coated_Retriever(平毛尋回犬)", | |
| "Giant_Schnauzer(大型雪納瑞犬)", "Golden_Retriever(黃金獵犬)", | |
| "Groenendael(比利時牧羊犬)", "Keeshond(荷蘭毛獅犬)", "Kelpie(澳洲卡爾比犬)", | |
| "Komondor(匈牙利牧羊犬)", "Kuvasz(庫瓦茲犬)", "Malamute(阿拉斯加雪橇犬)", | |
| "Malinois(比利時瑪利諾犬)", "Miniature_Pinscher(迷你杜賓犬)", | |
| "Miniature_Poodle(迷你貴賓犬)", "Miniature_Schnauzer(迷你雪納瑞犬)", | |
| "Otterhound(水獺獵犬)", "Papillon(蝴蝶犬)", "Pug(巴哥犬)", "Redbone(紅骨獵浣熊犬)", | |
| "Schipperke(舒柏奇犬)", "Silky_Terrier(絲毛梗)", | |
| "Soft-Coated_Wheaten_Terrier(愛爾蘭軟毛梗)", "Standard_Poodle(標準貴賓犬)", | |
| "Standard_Schnauzer(標準雪納瑞犬)", "Toy_Poodle(玩具貴賓犬)", "Toy_Terrier(玩具梗)", | |
| "Vizsla(維茲拉犬)", "Whippet(惠比特犬)", "Wire-Haired_Fox_Terrier(硬毛獵狐梗)"] | |
| 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): | |
| # try: | |
| # image_tensor = preprocess_image(image) | |
| # with torch.no_grad(): | |
| # output = model(image_tensor) | |
| # if isinstance(output, tuple): | |
| # logits = output[0] | |
| # else: | |
| # logits = output | |
| # # 取得預測的top k結果 | |
| # probabilities = F.softmax(logits, dim=1) | |
| # topk_probs, topk_indices = torch.topk(probabilities, k=3) | |
| # # 檢查最高的預測機率 | |
| # top1_prob = topk_probs[0][0].item() | |
| # if top1_prob >= 0.5: | |
| # # 正確辨識時，返回該品種資訊 | |
| # predicted = topk_indices[0][0] | |
| # breed = dog_breeds[predicted.item()] | |
| # description = get_dog_description(breed) | |
| # akc_link = get_akc_breeds_link() | |
| # if isinstance(description, dict): | |
| # description_str = "\n\n".join([f"**{key}**: {value}" for key, value in description.items()]) | |
| # else: | |
| # description_str = description | |
| # # 添加AKC連結 | |
| # description_str += 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." | |
| # # 添加免責聲明 | |
| # 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.*") | |
| # description_str += disclaimer | |
| # return description_str | |
| # else: | |
| # # 不確定時，返回top 3的預測結果 | |
| # 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]] | |
| # # 用粗體返回品種和機率 | |
| # topk_results = "\n\n".join([f"**{i+1}. {breed}** ({prob} confidence)" for i, (breed, prob) in enumerate(zip(topk_breeds, topk_probs_percent))]) | |
| # # 提供說明 | |
| # explanation = ( | |
| # f"The model couldn't confidently identify the breed. Here are the top 3 possible breeds:\n\n{topk_results}\n\n" | |
| # "This can happen if the image quality is low or the breed is rare in the dataset. " | |
| # "Please try uploading a clearer image or a different angle of the dog. " | |
| # "For more accurate results, ensure the dog is the main subject of the photo." | |
| # ) | |
| # return explanation | |
| # except Exception as e: | |
| # return f"An error occurred: {e}" | |
| # iface = gr.Interface( | |
| # fn=predict, | |
| # inputs=gr.Image(label="Upload a dog image", type="numpy"), | |
| # outputs=gr.Markdown(label="Prediction Results"), | |
| # title="<h1 style='font-family:Roboto; font-weight:bold; color:#2C3E50; text-align:center;'>🐶 Dog Breed Classifier 🔍</h1>", | |
| # article= 'For more details on this project and other work, feel free to visit my GitHub [Dog Breed Classifier](https://github.com/Eric-Chung-0511/Learning-Record/tree/main/Data%20Science%20Projects/Dog%20Breed%20Classifier)', | |
| # description="<p style='font-family:Open Sans; color:#34495E; text-align:center;'>Upload a picture of a dog, and model will predict its breed, provide detailed information, and include an extra information link!</p>", | |
| # examples=['Border_Collie.jpg', | |
| # 'Golden_Retriever.jpeg', | |
| # 'Saint_Bernard.jpeg', | |
| # 'French_Bulldog.jpeg', | |
| # 'Samoyed.jpg'], | |
| # 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; | |
| # } | |
| # """, | |
| # theme='default') | |
| # # Launch the app | |
| # if __name__ == "__main__": | |
| # iface.launch() | |
| def predict(image): | |
| 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: | |
| # High confidence prediction | |
| 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 < 0.1: | |
| # Very low confidence prediction | |
| 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: | |
| # Medium confidence prediction | |
| explanation = ( | |
| f"The model couldn't confidently identify the breed. Here are the top 3 possible breeds:\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): | |
| description_str = "\n\n".join([f"**{key}**: {value}" for key, value in description.items()]) | |
| else: | |
| description_str = description | |
| akc_link = get_akc_breeds_link() | |
| description_str += 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.*") | |
| description_str += disclaimer | |
| return description_str | |
| def show_details(breed): | |
| description = get_dog_description(breed) | |
| return format_description(description, breed) | |
| 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>') | |
| if __name__ == "__main__": | |
| iface.launch() | |