Update app.py

app.py

@@ -1,27 +1,26 @@
-import torch
-
-print("PyTorch version:", torch.__version__)
-
-
+# Import necessary libraries
 from transformers import pipeline
 import gradio as gr
 
-# Step 1: Load a pre-trained model for image classification
-model = pipeline("image-classification", model="google/vit-base-patch16-224")
+# Load a lightweight image classification model
+model = pipeline("image-classification", model="facebook/deit-tiny-patch16-224", cache_dir="./model_cache")
 
-# Step 2: Define a function for classifying images
+# Function to classify an uploaded image
 def classify_image(image):
-    predictions = model(image)
-    return predictions
+    predictions = model(image)  # Make predictions
+    # Format predictions as a dictionary: Label -> Confidence
+    return {pred["label"]: round(pred["score"], 4) for pred in predictions}
 
-# Step 3: Create a Gradio interface
+# Create a Gradio interface for the app
 interface = gr.Interface(
-    fn=classify_image,
-    inputs="image",  # Input is an image
-    outputs="label",  # Output is a label (e.g., "sitting", "standing")
-    title="Pose Detection: Sitting or Standing"
+    fn=classify_image,          # Function to call
+    inputs=gr.Image(type="pil"),  # Input: Image (PIL format)
+    outputs=gr.Label(),         # Output: Label with confidence scores
+    title="Image Classification App",
+    description="Upload an image, and the app will classify it using a vision transformer model."
 )
 
-# Step 4: Launch the app
+# Run the app
 if __name__ == "__main__":
     interface.launch()
+