File size: 1,568 Bytes
dd33bd5
 
c8081ec
dd33bd5
c8081ec
56b9e35
d52fc21
 
 
c8081ec
dd33bd5
56b9e35
c8081ec
 
dd33bd5
c8081ec
dd33bd5
 
c8081ec
 
dd33bd5
 
 
 
49fe0a4
dd33bd5
b60e30a
c8081ec
e42c333
 
c8081ec
e42c333
 
 
 
60d48cd
c8081ec
 
 
 
 
ea5afdb
c8081ec
 
 
 
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
import torch 
import re 
import gradio as gr
from transformers import AutoTokenizer, ViTFeatureExtractor, VisionEncoderDecoderModel 

device='cpu'
encoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
decoder_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
model_checkpoint = "nlpconnect/vit-gpt2-image-captioning"
feature_extractor = ViTFeatureExtractor.from_pretrained(encoder_checkpoint)
tokenizer = AutoTokenizer.from_pretrained(decoder_checkpoint)
model = VisionEncoderDecoderModel.from_pretrained(model_checkpoint).to(device)


def predict(image,max_length=64, num_beams=4):
  image = image.convert('RGB')
  image = feature_extractor(image, return_tensors="pt").pixel_values.to(device)
  clean_text = lambda x: x.replace('<|endoftext|>','').split('\n')[0]
  caption_ids = model.generate(image, max_length = max_length)[0]
  caption_text = clean_text(tokenizer.decode(caption_ids))
  return caption_text 



input = gr.inputs.Image(label="Upload your Image", type = 'pil', optional=True)
output = gr.outputs.Textbox(type="auto",label="Captions")
examples = [f"example{i}.jpg" for i in range(1,3)]

article = "Image captioning application made using transformers"
title = "Image Captioning 🖼️"

gr.Markdown("""
        ### Created By : Shreyas Dixit
        Transormer uesd : nlpconnect/vit-gpt2-image-captioning
""")

interface = gr.Interface(
        fn=predict,
        inputs = input,
        theme="grass",
        outputs=output,
        examples = examples,
        title=title,
        description=article,
    )
interface.launch(debug=True)