Create app.py

app.py

@@ -0,0 +1,104 @@
+import gradio as gr
+from transformers import pipeline
+import torch
+import os
+from PIL import Image
+import io
+
+# Check if CUDA is available (Hugging Face Spaces supports GPU acceleration)
+device = 0 if torch.cuda.is_available() else -1
+print(f"Using device: {'CUDA' if device == 0 else 'CPU'}")
+
+# Initialize the image processing pipeline
+# You can replace this with any Hugging Face model that processes images
+model_name = "google/vit-base-patch16-224"
+image_processor = pipeline("image-classification", model=model_name, device=device)
+
+def process_image(input_image):
+    """
+    Process the uploaded image through the model and return results
+    """
+    if input_image is None:
+        return [{"label": "No image provided", "score": 0.0}]
+    
+    # Run the image through the model
+    results = image_processor(input_image)
+    
+    # Return top 5 predictions
+    return results[:5]
+
+def save_output(results):
+    """
+    Convert results to a downloadable format
+    """
+    if not results or len(results) == 0:
+        return None
+        
+    output_text = "Model Predictions:\n\n"
+    for result in results:
+        output_text += f"Label: {result['label']}, Score: {result['score']:.4f}\n"
+    
+    # Create a file for download
+    with open("results.txt", "w") as f:
+        f.write(output_text)
+    
+    return "results.txt"
+
+# Create the Gradio interface with a more polished design
+with gr.Blocks(theme=gr.themes.Soft()) as demo:
+    gr.Markdown("# Image Classification Demo")
+    gr.Markdown("Upload an image and get classification results from the model.")
+    
+    with gr.Row():
+        with gr.Column(scale=1):
+            # Input components
+            input_image = gr.Image(type="pil", label="Upload Image")
+            with gr.Row():
+                submit_btn = gr.Button("Process Image", variant="primary")
+                clear_btn = gr.Button("Clear")
+        
+        with gr.Column(scale=1):
+            # Output components
+            output_results = gr.JSON(label="Model Predictions")
+            download_btn = gr.Button("Download Results")
+            download_output = gr.File(label="Download Output")
+    
+    # Set up the processing flow
+    submit_btn.click(
+        fn=process_image,
+        inputs=[input_image],
+        outputs=[output_results]
+    )
+    
+    clear_btn.click(
+        fn=lambda: (None, None, None),
+        inputs=[],
+        outputs=[input_image, output_results, download_output]
+    )
+    
+    download_btn.click(
+        fn=save_output,
+        inputs=[output_results],
+        outputs=[download_output]
+    )
+    
+    # Add example images
+    gr.Examples(
+        examples=[
+            os.path.join(os.path.dirname(__file__), "examples/cat.jpg"),
+            os.path.join(os.path.dirname(__file__), "examples/dog.jpg"),
+        ],
+        inputs=input_image,
+        label="Example Images"
+    )
+    
+    # Add information footer
+    gr.Markdown("""
+    ### About this demo
+    - Model: [google/vit-base-patch16-224](https://huggingface.co/google/vit-base-patch16-224)
+    - This demo classifies images into 1000 ImageNet categories
+    - Created with Gradio and Hugging Face Transformers
+    """)
+
+# For Hugging Face Spaces, we use the Gradio app directly
+demo.launch()