add gradio app demo

README.md

@@ -1,6 +1,6 @@
 ---
 title: ImageNet1k
-emoji: 🚀
+emoji: 🚀 🌟 
 colorFrom: red
 colorTo: gray
 sdk: gradio
@@ -9,4 +9,66 @@ app_file: app.py
 pinned: false
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# ImageNet1k Classification Demo
+
+This is a Gradio web application that demonstrates image classification using a ResNet50 model trained on the ImageNet1k dataset. The model can classify images into 1000 different categories.
+
+## Features
+
+- Upload and classify any image
+- Get top 5 predictions with confidence scores
+- Real-time inference
+- User-friendly interface
+- Example images included
+
+## Technical Details
+
+### Model Architecture
+- Base Model: ResNet50
+- Training Dataset: ImageNet1k (1000 classes)
+- Input Size: 224x224 pixels
+- Preprocessing: Standard ImageNet normalization (mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
+
+### Dependencies
+- gradio: Web interface framework
+- torch: PyTorch deep learning framework
+- torchvision: Computer vision utilities
+- Pillow: Image processing
+
+## Usage
+
+1. Upload an image using the interface
+2. The model will process the image and return:
+   - Top 5 predicted classes
+   - Confidence scores for each prediction
+
+## Tips for Best Results
+
+- Use clear, well-lit images
+- Ensure the main subject is centered and clearly visible
+- The model works best with common objects, animals, and scenes
+- Both color and black & white images are supported
+- Images will be automatically resized to 224x224
+
+## Local Setup
+
+1. Clone the repository
+2. Install dependencies:
+   ```bash
+   pip install -r requirements.txt
+   ```
+3. Place your trained model weights as `model_best.pth.tar` in the root directory
+4. Run the application:
+   ```bash
+   python app.py
+   ```
+
+## Model Weights
+
+The model weights (`model_best.pth.tar`) should be placed in the same directory as `app.py`. The weights file contains a ResNet50 model trained on ImageNet1k.
+
+## Links
+
+- [GitHub Repository](https://github.com/dhairyag/ImageNet1k_ResNet50)
+- [Hugging Face Space](https://huggingface.co/spaces/dhairyashil/ImageNet1k)
+

app.py

@@ -0,0 +1,92 @@
+import gradio as gr
+import torch
+import torchvision.models as models
+from torchvision import transforms
+from PIL import Image
+
+# Load the ImageNet class labels
+import json
+import urllib.request
+
+# Download ImageNet class labels
+labels_url = "https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt"
+labels = urllib.request.urlopen(labels_url).read().decode('utf-8').split('\n')
+
+# Initialize model
+model = models.resnet50()
+num_classes = 1000  # ImageNet1k classes
+
+# Load your trained weights
+checkpoint = torch.load('model_best.pth.tar', map_location=torch.device('cpu'))
+if 'state_dict' in checkpoint:
+    state_dict = checkpoint['state_dict']
+    # Remove 'module.' prefix if model was trained with DataParallel
+    state_dict = {k.replace('module.', ''): v for k, v in state_dict.items()}
+    model.load_state_dict(state_dict)
+else:
+    model.load_state_dict(checkpoint)
+
+model.eval()
+
+# Define image transforms
+transform = transforms.Compose([
+    transforms.Resize(256),
+    transforms.CenterCrop(224),
+    transforms.ToTensor(),
+    transforms.Normalize(mean=[0.485, 0.456, 0.406], 
+                       std=[0.229, 0.224, 0.225])
+])
+
+def predict(image):
+    # Ensure image is in RGB format
+    if image.mode != 'RGB':
+        image = image.convert('RGB')
+    
+    # Apply transforms
+    input_tensor = transform(image)
+    input_batch = input_tensor.unsqueeze(0)
+    
+    # Get prediction
+    with torch.no_grad():
+        output = model(input_batch)
+    
+    # Get probabilities
+    probabilities = torch.nn.functional.softmax(output[0], dim=0)
+    
+    # Get top 5 predictions
+    top5_prob, top5_indices = torch.topk(probabilities, 5)
+    
+    # Format results as dictionary
+    results = {}
+    for prob, idx in zip(top5_prob, top5_indices):
+        class_name = labels[idx]
+        results[class_name] = float(prob)
+    
+    return results
+
+# Create Gradio interface
+title = "ImageNet1k Classification"
+description = """Upload an image and the model will predict its category using the ImageNet1k classification system.
+Tips for best results:
+- Use clear, well-lit images; ensure the main subject is centered and clearly visible
+- The model works best with common objects, animals, and scenes
+- Images can be any size - they'll be automatically resized to 224x224
+- Both color and black & white images are supported
+
+The model will show the top 5 most likely categories with confidence scores.
+Link to github repo: [https://github.com/dhairyag/ImageNet1k_ResNet50](https://github.com/dhairyag/ImageNet1k_ResNet50)
+"""
+
+iface = gr.Interface(
+    fn=predict,
+    inputs=gr.Image(type="pil"),
+    outputs=gr.Label(num_top_classes=5),
+    title=title,
+    description=description,
+    examples=[
+        ["examples/dog.jpg"],
+        ["examples/cat.jpg"],
+    ],
+)
+
+iface.launch(share=True) 

requirements.txt

@@ -0,0 +1,4 @@
+gradio
+torch
+torchvision
+Pillow