predict_caption.py

from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer
import torch
from PIL import Image

# Load model and tokenizer from the Hugging Face repository
model_name = "aryan083/vit-gpt2-image-captioning"
model = VisionEncoderDecoderModel.from_pretrained(model_name)
feature_extractor = ViTFeatureExtractor.from_pretrained(model_name)
tokenizer = AutoTokenizer.from_pretrained(model_name)

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_step(image_path):
    image = Image.open(image_path)
    pixel_values = feature_extractor(images=image, 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)
    preds = [pred.strip() for pred in preds]
    return preds[0]

# Example usage with your image file
image_path = 'jon-parry-C8eSYwQkwHw-unsplash.jpg'
print(predict_step(image_path=image_path))