Upload app.py with huggingface_hub

app.py

@@ -1,53 +1,16 @@
-import torch
-import torch.nn.functional as F
-from torchvision import models, transforms
-from PIL import Image
-import gradio as gr
-from huggingface_hub import hf_hub_download
-
-# Define class labels
-clothing1m_classes = [
-    "T-shirt", "Shirt", "Knitwear", "Chiffon", "Sweater", "Hoodie", "Windbreaker",
-    "Jacket", "Down Coat", "Suits", "Shawl", "Dress", "Vest", "Underwear", "Shorts",
-    "Trousers", "Jeans", "Leather Shoes", "Casual Shoes", "Sport Shoes", "Sandals"
-]
-
-# Set device
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
 
-# Load model
-model = models.resnet50(weights=None)
-model.fc = torch.nn.Linear(model.fc.in_features, 21)
-model_path = hf_hub_download(repo_id="PrachiY/image-classification-model", filename="model.pth")
-model.load_state_dict(torch.load(model_path, map_location=device))
-model.to(device)
-model.eval()
-
-# Define preprocessing
-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]),
-])
+import gradio as gr
+from classify import classify_image
 
-def classify_image(image):
-    image = transform(image).unsqueeze(0).to(device)
-    with torch.no_grad():
-        output = model(image)
-        probs = F.softmax(output, dim=1)
-        pred_idx = probs.argmax(dim=1).item()
-        pred_label = clothing1m_classes[pred_idx]
-        return f"Predicted Class: {pred_label}"
+examples = ["example.jpg"]
 
-# Gradio Interface
 interface = gr.Interface(
     fn=classify_image,
     inputs=gr.Image(type="pil"),
-    outputs="text",
+    outputs=gr.Label(),
+    examples=examples,
     title="Clothing1M Classifier",
-    description="Upload a clothing image and get a predicted label from 21 Clothing1M categories.",
-    examples=[["example.jpg"]]  # Optional
+    description="Upload a clothing image to classify it into 14 categories."
 )
 
 if __name__ == "__main__":