from datasets import load_dataset 
    dataset = load_dataset("ybelkada/football-dataset", split="train")

from transformers import AutoProcessor, BlipForConditionalGeneration

processor = AutoProcessor.from_pretrained("ai-nightcoder/Image2text")
model = BlipForConditionalGeneration.from_pretrained("ai-nightcoder/Image2text")

example = dataset[0]
image = example["image"]
image

inputs = processor(images=image, return_tensors="pt").to(device)
pixel_values = inputs.pixel_values
    
generated_ids = model.generate(pixel_values=pixel_values, max_length=50)
generated_caption = processor.batch_decode(generated_ids, skip_special_tokens=True)[0]
print(generated_caption)