File size: 2,330 Bytes
112b8aa
 
 
 
 
2265414
112b8aa
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
import transformers
import torch
import gradio as gr
import requests

from transformers import BlipForConditionalGeneration
from transformers import AutoProcessor
from transformers.utils import logging
from PIL import Image

model = BlipForConditionalGeneration.from_pretrained(
    "Salesforce/blip-image-captioning-base")
processor = AutoProcessor.from_pretrained(
    "Salesforce/blip-image-captioning-base")

def process_image(input_type, image_url, image_upload):
    if input_type == "URL":
        raw_image =  Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
    else:
        raw_image = image_upload

    inputs = processor(raw_image,return_tensors="pt")
    out = model.generate(**inputs)[0]
    description = processor.decode(out, skip_special_tokens=True).capitalize()

    formatted_description = (
        f"""<div><h1 style='text-align: center; font-size: 40px; color: orange;'>
        {description}
        </h1></div>"""
    )
    return formatted_description

def display_image_from_url(image_url):
    if image_url:
        image = Image.open(requests.get(image_url, stream=True).raw).convert('RGB')
        return image
    return None

def toggle_inputs(input_type):
    if input_type == "URL":
        return gr.update(visible=True), gr.update(visible=True), gr.update(visible=False)
    else:
        return gr.update(visible=False), gr.update(visible=False), gr.update(visible=True)

with gr.Blocks() as demo:
    gr.Markdown(
    """
    # Image Captioning - test & demo app by Srinivas.V..
    Paste either URL of an image or upload the image and submit.
    """)

    input_type = gr.Radio(choices=["URL", "Upload"], label="Input Type")
    image_url = gr.Textbox(label="Image URL", visible=False)
    url_image = gr.Image(type="pil", label="URL Image", visible=False)
    image_upload = gr.Image(type="pil", label="Upload Image", visible=False)

    input_type.change(fn=toggle_inputs, inputs=input_type, outputs=[image_url, url_image, image_upload])
    image_url.change(fn=display_image_from_url, inputs=image_url, outputs=url_image)

    submit_btn = gr.Button("Submit")
    processed_image = gr.HTML(label="Caption for the Image")
    submit_btn.click(fn=process_image, inputs=[input_type, image_url, image_upload], outputs=processed_image)

demo.launch(debug=True, share=True)