File size: 737 Bytes
859e6d1 c186c67 9e192f4 b6d2ff6 badd543 b6d2ff6 1b67c1b b6d2ff6 |
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 |
---
pipeline_tag: image-to-text
datasets:
- MMInstruction/M3IT
---
## Usage:
```
from transformers import BlipProcessor, BlipForConditionalGeneration
import torch
from PIL import Image
processor = BlipProcessor.from_pretrained("prasanna2003/blip-image-captioning")
if processor.tokenizer.eos_token is None:
processor.tokenizer.eos_token = '<|eos|>'
model = BlipForConditionalGeneration.from_pretrained("prasanna2003/blip-image-captioning")
image = Image.open('file_name.jpg').convert('RGB')
prompt = """Instruction: Generate a single line caption of the Image.
output: """
inputs = processor(image, prompt, return_tensors="pt")
output = model.generate(**inputs, max_length=100)
print(processor.tokenizer.decode(output[0]))
``` |