File size: 2,736 Bytes
7ebfeb9 afda258 cf05f8b 22ed06b 623b4fb 931c795 7fcb6d2 623b4fb 7ebfeb9 afda258 aafac25 5ce0179 7ebfeb9 aafac25 cf05f8b afda258 dee2758 6ae0110 dee2758 fc6f52f 7ebfeb9 623b4fb 22ed06b aafac25 22ed06b 0e534f1 1618050 dee2758 cb2be18 281dd11 b1241b7 dee2758 f63a88c e6a32cf 9afb73f e6a32cf 9afb73f e6a32cf 4c10f74 22ed06b b1241b7 f63a88c 22ed06b a4fcc26 afda258 aafac25 b51c75c aafac25 dee2758 afda258 623b4fb afda258 aafac25 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 75 76 77 78 79 80 81 |
import gradio as gr
from PIL import Image
import clipGPT
import vitGPT
import skimage.io as io
import PIL.Image
import difflib
import ViTCoAtt
from build_vocab import Vocabulary
# Caption generation functions
def generate_caption_clipgpt(image, max_tokens, temperature):
caption = clipGPT.generate_caption_clipgpt(image)
return caption
def generate_caption_vitgpt(image, max_tokens, temperature):
caption = vitGPT.generate_caption(image)
return caption
def generate_caption_vitCoAtt(image):
caption = ViTCoAtt.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():
sample_images = [
'https://imgur.com/W1pIr9b',
'https://imgur.com/MLJaWnf',
'https://imgur.com/6XymFW1',
'https://imgur.com/zdPjZZ1',
'https://imgur.com/DKUlZbF'
]
image = gr.Image(label="Upload Chest X-ray", type="pil")
sample_images_gallery = gr.Gallery(value = sample_images,label="Sample Images")
gr.HTML("<p style='text-align: center;'> Please select the Number of Max Tokens and Temperature setting, if you are testing CLIP GPT2 and VIT GPT2 Models</p>")
with gr.Row():
with gr.Column(): # Column for dropdowns and model choice
max_tokens = gr.Dropdown(list(range(50, 101)), label="Max Tokens", value=75)
temperature = gr.Slider(0.5, 0.9, step=0.1, label="Temperature", value=0.7)
model_choice = gr.Radio(["CLIP-GPT2", "ViT-GPT2", "ViT-CoAttention"], label="Select Model")
generate_button = gr.Button("Generate Caption")
caption = gr.Textbox(label="Generated Caption")
def predict(img, model_name, max_tokens, temperature):
if model_name == "CLIP-GPT2":
return generate_caption_clipgpt(img, max_tokens, temperature)
elif model_name == "ViT-GPT2":
return generate_caption_vitgpt(img, max_tokens, temperature)
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, max_tokens, temperature], caption)
sample_images_gallery.change(predict, [sample_images_gallery, model_choice, max_tokens, temperature], caption)
demo.launch()
|