Create app.py

app.py

@@ -0,0 +1,35 @@
+import gradio as gr
+from PIL import Image
+from transformers import BlipProcessor, BlipForConditionalGeneration
+import torch
+
+# Initialize BLIP model and processor
+device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
+model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
+
+def caption_image(image):
+    inputs = processor(images=image, return_tensors="pt").to(device)
+    out = model.generate(**inputs)
+    caption = processor.decode(out[0], skip_special_tokens=True)
+    return caption
+
+def process_image(image):
+    # Convert the input image to PIL Image
+    image = Image.fromarray(image)
+    # Get the caption
+    caption = caption_image(image)
+    return caption
+
+# Create Gradio Interface
+interface = gr.Interface(
+    fn=process_image,
+    inputs=gr.inputs.Image(type="numpy", label="Upload Image"),
+    outputs=gr.outputs.Textbox(label="Caption"),
+    title="BLIP Image Captioning",
+    description="Upload an image to get a caption generated by the BLIP model."
+)
+
+# Launch the Gradio app
+if __name__ == "__main__":
+    interface.launch()