app.py

from tranformers import VisionEncoderDecoderModle, ViTImageProcer, Autotokenizer
import torch
from PIL import Image

model = VisionEncoderDecoderModle.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_external = ViTImageProcer.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_pixel_values=True).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