Create app.py

app.py

@@ -0,0 +1,37 @@
+# 1. Import Libraries
+import gradio as gr
+from transformers import CLIPProcessor, CLIPModel
+from PIL import Image
+import torch
+
+# 2. Load the Pre-trained Model
+model_name = "openai/clip-vit-base-patch16"
+processor = CLIPProcessor.from_pretrained(model_name)
+model = CLIPModel.from_pretrained(model_name)
+
+# 3. Define the Prediction Function
+def classify_image_text(image, text):
+    # Process the inputs
+    inputs = processor(text=[text], images=image, return_tensors="pt", padding=True)
+    
+    # Get model predictions
+    with torch.no_grad():
+        outputs = model(**inputs)
+    
+    # Calculate similarity between image and text
+    logits_per_image = outputs.logits_per_image
+    probs = logits_per_image.softmax(dim=1)  # Convert logits to probabilities
+    
+    # Return the prediction
+    return {text: probs.item()}
+
+# 4. Create the Gradio Interface
+iface = gr.Interface(
+    fn=classify_image_text,
+    inputs=[gr.Image(type="pil"), gr.Textbox(label="Enter description")],
+    outputs=gr.Label(),
+    live=True
+)
+
+# 5. Launch the App
+iface.launch()