File size: 1,072 Bytes
6819cba
ec665e5
6819cba
6d97bc1
6819cba
 
 
b56d4a5
813ddfe
 
b56d4a5
813ddfe
 
01185b8
b56d4a5
813ddfe
 
 
 
 
 
 
 
62138e5
813ddfe
 
 
 
 
 
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
from transformers import ViTFeatureExtractor, ViTForImageToText, AutoTokenizer
import torch
from PIL import Image

model = ViTForImageToText.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTFeatureExtractor.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
tokenizer = AutoTokenizer.from_pretrained("nlpconnect/vit-gpt2-image-captioning")

device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)

max_length = 16
num_beams = 4
gen_kwargs = {"max_length": max_length, "num_beams": num_beams}

def predict_caption(image_paths):
    images = []
    for image_path in image_paths:
        image = Image.open(image_path)
        if image.mode != "RGB":
            image = image.convert(mode="RGB")
        images.append(image)

    pixel_values = feature_extractor(images=images, return_tensors="pt").pixel_values
    pixel_values = pixel_values.to(device)

    output_ids = model.generate(pixel_values, **gen_kwargs)

    preds = tokenizer.batch_decode(output_ids, skip_special_tokens=True)
    return preds