File size: 2,223 Bytes
7ebfeb9 afda258 cf05f8b 22ed06b 623b4fb dee2758 7fcb6d2 623b4fb 7ebfeb9 afda258 5ce0179 7ebfeb9 cf05f8b afda258 dee2758 bfd318a dee2758 fc6f52f 7ebfeb9 623b4fb 22ed06b 5d8bab6 22ed06b f63a88c 22ed06b 31bbcd0 22ed06b fc733f6 dee2758 cb2be18 281dd11 b1241b7 dee2758 f63a88c 22ed06b b1241b7 f63a88c 22ed06b 281dd11 afda258 623b4fb b51c75c cf05f8b dee2758 afda258 623b4fb afda258 b1241b7 ad8b91f dee2758 623b4fb 22ed06b |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 |
import gradio as gr
from PIL import Image
import clipGPT
import vitGPT
import skimage.io as io
import PIL.Image
import difflib
import tester
from build_vocab import Vocabulary
# 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
def generate_caption_vitCoAtt(image):
caption = tester.CaptionSampler.main(image)
return caption
with gr.Blocks() as demo:
gr.HTML("<h1 style='text-align: center;'>MedViT: A Vision Transformer-Driven Method for Generating Medical Reports 🏥🤖</h1>")
gr.HTML("<p style='text-align: center;'>You can generate captions by uploading an X-Ray and selecting a model of your choice below</p>")
with gr.Row():
model_choice = gr.Radio(["CLIP-GPT2", "ViT-GPT2", "ViT-CoAttention"], label="Select Model")
with gr.Row():
sample_images = [
"https://upload.wikimedia.org/wikipedia/commons/0/09/TheCheethcat.jpg",
"CXR192_IM-0598-1001.png",
"CXR193_IM-0601-1001.png",
"CXR194_IM-0609-1001.png",
"CXR195_IM-0618-1001.png"
]
image = gr.Image(label="Upload Chest X-ray", type="pil")
sample_images_gallery = gr.Gallery(value = sample_images,label="Sample Images")
with gr.Row():
generate_button = gr.Button("Generate Caption")
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)
elif model_name == "ViT-CoAttention":
return generate_caption_vitCoAtt(img)
else:
return "Caption generation for this model is not yet implemented."
# Event handlers
generate_button.click(predict, [image, model_choice], caption) # Trigger prediction on button click
sample_images_gallery.change(predict, [sample_images_gallery, model_choice], caption) # Handle sample images
demo.launch()
|