import torch
from transformers import VisionEncoderDecoderModel, ViTFeatureExtractor, AutoTokenizer

model = VisionEncoderDecoderModel.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_step(image_paths):
  images = []
  for image_path in image_paths:
    i_image = Image.open(image_path)
    if i_image.mode != "RGB":
      i_image = i_image.convert(mode="RGB")

    images.append(i_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)
  preds = [pred.strip() for pred in preds]
  return preds

torch.hub.download_url_to_file('https://github.com/AaronCWacker/Yggdrasil/blob/main/images/35-Favorite-Games.jpg?raw=true', '35-Favorite-Games.jpg')

predict_step(['35-Favorite-Games.jpg'] # ['a woman in a hospital bed with a woman in a hospital bed']