File size: 757 Bytes
27880c4 cb816fd e67cd9e 9953c0d e67cd9e 03c3cc5 e67cd9e |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 |
from PIL import Image
import io
import torch
from transformers import BlipProcessor, BlipForConditionalGeneration
device = "cuda" if torch.cuda.is_available() else "cpu"
class ImageCaptioning:
def __init__(self):
self.processor = BlipProcessor.from_pretrained("Salesforce/blip-image-captioning-base")
self.model = BlipForConditionalGeneration.from_pretrained("Salesforce/blip-image-captioning-base").to(device)
def get_caption(self, image_bytes):
img = Image.open(io.BytesIO(image_bytes))
img_tensors = self.processor(img, return_tensors="pt").to(device)
output = self.model.generate(**img_tensors)
caption = self.processor.batch_decode(output, skip_special_tokens=True)[0]
return caption
|