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

model = VisionEncoderDecoderModel.from_pretrained("nlpconnect/vit-gpt2-image-captioning")
feature_extractor = ViTImageProcessor.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


# Define paths to save the components in your Google Drive
drive_folder = "/content/drive/My Drive/image_captioning_streamlit"

saved_model_directory = f"{drive_folder}/saved_model"
saved_feature_extractor_directory = f"{drive_folder}/saved_feature_extractor"
saved_tokenizer_directory = f"{drive_folder}/saved_tokenizer"


# Save the model and its components
model.save_pretrained(saved_model_directory)
feature_extractor.save_pretrained(saved_feature_extractor_directory)
tokenizer.save_pretrained(saved_tokenizer_directory)