File size: 1,190 Bytes
e7febdd
 
c61d5a8
 
e7febdd
c61d5a8
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
e7febdd
c61d5a8
 
 
 
 
 
e7febdd
 
c61d5a8
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
#!/usr/bin/env python

from __future__ import annotations

import gradio as gr
import PIL.Image
import spaces
import torch
from transformers import AutoModelForCausalLM, AutoProcessor

DESCRIPTION = "# Image Captioning with GIT"

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")

model_id = "microsoft/git-large-coco"
processor = AutoProcessor.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id).to(device)


@spaces.GPU
def run(image: PIL.Image.Image) -> str:
    inputs = processor(images=image, return_tensors="pt").to(device)
    generated_ids = model.generate(pixel_values=inputs.pixel_values, num_beams=3, max_length=20, min_length=5)
    generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return generated_caption


with gr.Blocks(css="style.css") as demo:
    gr.Markdown(DESCRIPTION)
    input_image = gr.Image(type="pil")
    run_button = gr.Button("Caption")
    output = gr.Textbox(label="Result")

    run_button.click(
        fn=run,
        inputs=input_image,
        outputs=output,
        api_name="caption",
    )

if __name__ == "__main__":
    demo.queue(max_size=20).launch()