File size: 874 Bytes
ff2be50
 
bb6938f
 
ff2be50
 
ca5f428
ff2be50
 
 
ca5f428
ff2be50
f0d5be4
 
ff2be50
 
 
f0d5be4
ff2be50
f0d5be4
 
ff2be50
f0d5be4
 
ff2be50
 
f0d5be4
 
 
 
ff2be50
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
---
library_name: transformers
license: apache-2.0
pipeline_tag: image-to-text
---

# BLIP-Image-to-recip



# Inference code

import requests
from PIL import Image



from transformers import BlipForConditionalGeneration, AutoProcessor

img_url = 'https://encrypted-tbn0.gstatic.com/images?q=tbn:ANd9GcSQuFg4LTHUattLGPU0kLzYpBGHRtuqgJY8Gho3uZe_cg&s' 
image = Image.open(requests.get(img_url, stream=True).raw).convert('RGB')

model = BlipForConditionalGeneration.from_pretrained("Fatehmujtaba/BLIP-Image-to-recipe").to(device)
processor = AutoProcessor.from_pretrained("Salesforce/blip-image-captioning-base")


inputs = processor(images=image, return_tensors="pt").to(device)
pixel_values = inputs.pixel_values
generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]