app.py

import gradio as gr
from PIL import Image
import clipGPT
import vitGPT
import skimage.io as io
import PIL.Image


# Caption generation functions
def generate_caption_clipgpt(image):
    caption = clipGPT.generate_caption_clipgpt(image)
    return caption

def generate_caption_vitgpt(image):
    caption = vitGPT.generate_caption(image)
    return caption

# Sample image paths
sample_images = [
    "CXR191_IM-0591-1001.png",
    "CXR192_IM-0598-1001.png",
    "CXR193_IM-0601-1001.png",
    "CXR194_IM-0609-1001.png",
    "CXR195_IM-0618-1001.png"
]

# Gradio interface 
with gr.Blocks() as demo:
    with gr.Row():
        image = gr.Image(label="Upload Chest X-ray") 
        sample_images_gallery = gr.Gallery(
            sample_images, 
            label="Sample Images",
        )  
    with gr.Row():  
        model_choice = gr.Radio(["CLIP-GPT2", "ViT-GPT2", "ViT-CoAttention"], label="Select Model")
    with gr.Row():
        caption = gr.Textbox(label="Generated Caption") 

    def predict(img, model_name):
        if model_name == "CLIP-GPT2":
            return generate_caption_clipgpt(img)
        elif model_name == "ViT-GPT2":
            return generate_caption_vitgpt(img)
        else:
            return "Caption generation for this model is not yet implemented."

    # Handle changes for both uploaded and sample images
    image.change(predict, [image, model_choice], caption)
    sample_images_gallery.change(predict, [sample_images_gallery, model_choice], caption)

demo.launch()