Update app.py

app.py

@@ -1,38 +1,15 @@
 from transformers import AutoProcessor, AutoModelForCausalLM
+import requests
 from PIL import Image
-import gradio as gr
 
-# Load the processor and model
 processor = AutoProcessor.from_pretrained("microsoft/git-base-coco")
 model = AutoModelForCausalLM.from_pretrained("microsoft/git-base-coco")
 
-# Define the captioning function
-def caption_image(image):
-    # Process the image
-    pixel_values = processor(images=image, return_tensors="pt").pixel_values
-    # Generate captions
-    generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
-    generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
-    return generated_caption
+url = "http://images.cocodataset.org/val2017/000000039769.jpg"
+image = Image.open(requests.get(url, stream=True).raw)
 
-# Define Gradio interface components
-inputs = [
-    gr.inputs.Image(type='pil', label='Upload Image')
-]
+pixel_values = processor(images=image, return_tensors="pt").pixel_values
 
-outputs = [
-    gr.outputs.Textbox(label='Generated Caption')
-]
-
-# Define Gradio app properties
-title = "Image Captioning Application"
-description = "Upload an image to see the caption generated by the model"
-
-# Create and launch the Gradio interface
-gr.Interface(
-    fn=caption_image,
-    inputs=inputs,
-    outputs=outputs,
-    title=title,
-    description=description,
-).launch(debug=True)
+generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
+generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
+print(generated_caption)