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, 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() | |
| # Update the format_description to handle descriptions more cleanly | |
| def format_description(description, breed): | |
| if isinstance(description, dict): | |
| # 確保每一個描述項目換行顯示，並避免重複顯示 Breed | |
| formatted_description = "\n\n".join([f"**{key}**: {value}" for key, value in description.items()]) | |
| else: | |
| formatted_description = description | |
| formatted_description = f""" | |
| **Breed**: {breed} | |
| {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 | |
| async def predict_single_dog(image): | |
| return await asyncio.to_thread(_predict_single_dog, image) | |
| 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 | |
| async def detect_multiple_dogs(image, conf_threshold=0.3): | |
| # 調整 YOLO 模型的置信度閾值 | |
| return await asyncio.to_thread(_detect_multiple_dogs, image, conf_threshold) | |
| def _detect_multiple_dogs(image, conf_threshold): | |
| results = model_yolo(image, conf=conf_threshold) | |
| dogs = [] | |
| for result in results: | |
| for box in result.boxes: | |
| if box.cls == 16: # COCO 資料集中狗的類別是 16 | |
| xyxy = box.xyxy[0].tolist() | |
| confidence = box.conf.item() | |
| if confidence >= conf_threshold: # 只保留置信度高於閾值的框 | |
| cropped_image = image.crop((xyxy[0], xyxy[1], xyxy[2], xyxy[3])) | |
| dogs.append((cropped_image, confidence, xyxy)) | |
| return dogs | |
| 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) | |
| # 偵測圖片中的多個狗 | |
| dogs = await detect_multiple_dogs(image) | |
| # 單一狗情況處理 | |
| if len(dogs) == 0: | |
| top1_prob, topk_breeds, topk_probs_percent = await predict_single_dog(image) | |
| if top1_prob < 0.2: | |
| return "The image is unclear or the breed is not in the dataset. Please upload a clearer image of a dog.", None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False) | |
| breed = topk_breeds[0] | |
| description = get_dog_description(breed) | |
| formatted_description = format_description(description, breed) | |
| # 處理高置信度與低置信度情況 | |
| if top1_prob >= 0.5: | |
| return formatted_description, image, 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]}") | |
| # 多狗處理 | |
| color_list = ['#FF0000', '#00FF00', '#0000FF', '#FFFF00', '#00FFFF', '#FF00FF', '#800080', '#FFA500'] | |
| explanations = [] | |
| visible_buttons = [] | |
| annotated_image = image.copy() | |
| draw = ImageDraw.Draw(annotated_image) | |
| font = ImageFont.load_default() | |
| # 遍歷每一隻狗 | |
| for i, (cropped_image, _, box) in enumerate(dogs): | |
| top1_prob, topk_breeds, topk_probs_percent = await predict_single_dog(cropped_image) | |
| # 繪製方框 | |
| color = color_list[i % len(color_list)] | |
| draw.rectangle(box, outline=color, width=3) | |
| draw.text((box[0], box[1]), f"Dog {i+1}", fill=color, font=font) | |
| # 高置信度返回 | |
| if top1_prob >= 0.5: | |
| breed = topk_breeds[0] | |
| description = get_dog_description(breed) | |
| explanations.append(f"Dog {i+1}:\n{format_description(description, breed)}") | |
| elif 0.2 <= top1_prob < 0.5: | |
| explanation = f""" | |
| Dog {i+1}: 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) | |
| visible_buttons.extend([f"More about Dog {i+1}: {topk_breeds[0]}", f"More about Dog {i+1}: {topk_breeds[1]}", f"More about Dog {i+1}: {topk_breeds[2]}"]) | |
| else: | |
| explanations.append(f"Dog {i+1}: The image is unclear or the breed is not in the dataset.") | |
| final_explanation = "\n\n".join(explanations) | |
| return final_explanation, annotated_image, gr.update(visible=True, choices=visible_buttons), 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) | |
| async def show_details(choice): | |
| if not choice: | |
| return "Please select a breed to view details." | |
| try: | |
| if "Dog" in choice: | |
| _, breed = choice.split(": ", 1) | |
| else: | |
| _, breed = choice.split("More about ", 1) | |
| description = get_dog_description(breed) | |
| return format_description(description, breed) | |
| except Exception as e: | |
| return f"An error occurred while showing details: {e}" | |
| 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") | |
| async def safe_predict(image): | |
| try: | |
| return await predict(image) | |
| except Exception as e: | |
| return str(e), None, gr.update(visible=False), gr.update(visible=False), gr.update(visible=False) | |
| input_image.change( | |
| safe_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() | |