Create app.py

app.py

@@ -0,0 +1,39 @@
+import gradio as gr
+from transformers import BlipProcessor, BlipForConditionalGeneration
+from PIL import Image
+import torch
+
+# Load model and processor from your Hugging Face repo
+model_id = "khalednabawi11/blip-roco-weights-v2"
+
+processor = BlipProcessor.from_pretrained(model_id)
+model = BlipForConditionalGeneration.from_pretrained(model_id)
+model.eval()
+
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+model.to(device)
+
+def generate_caption(image):
+    # Preprocess
+    inputs = processor(image, return_tensors="pt").to(device)
+
+    # Generate caption
+    with torch.no_grad():
+        output = model.generate(**inputs, max_new_tokens=50)
+
+    # Decode
+    caption = processor.decode(output[0], skip_special_tokens=True)
+    return caption
+
+# Gradio UI
+demo = gr.Interface(
+    fn=generate_caption,
+    inputs=gr.Image(type="pil", label="Upload an Image"),
+    outputs=gr.Textbox(label="Generated Caption"),
+    title="BLIP Medical Caption Generator",
+    description="Upload an image and get a caption generated by your fine-tuned BLIP model.",
+    examples=["example1.png", "example2.png"]  # Optional: add example images in your repo
+)
+
+if __name__ == "__main__":
+    demo.launch()