pre_process_tiles.py

import os
import pandas as pd
from scripts.PlipDataProcess import PlipDataProcess  # Updated folder name
from transformers import CLIPImageProcessor
import argparse

def main(csv_file, root_dir, save_dir):
    # Load the CSV file and set 'PatientID' as the index
    df4 = pd.read_csv(csv_file).set_index('PatientID')

    # List directories in the root directory (assuming each directory corresponds to a patient)
    files = [file for file in os.listdir(root_dir) if os.path.isdir(os.path.join(root_dir, file))]

    # Initialize the image processor
    img_processor = CLIPImageProcessor.from_pretrained("./plip/")

    # Initialize the dataset processing object
    dataset = PlipDataProcess(
        root_dir=root_dir,
        files=files,
        df=df4,
        img_processor=img_processor,
        num_tiles_per_patient=2000,
        max_workers=64,
        save_dir=save_dir
    )

    # Process each item in the dataset
    for i in range(len(dataset)):
        _ = dataset[i]  # Trigger processing of the i-th item

if __name__ == '__main__':
    parser = argparse.ArgumentParser(description="Process WSI images and generate tiles")
    
    # Define arguments
    parser.add_argument('--csv_file', type=str, required=True, help='Path to the CSV file with patient scores')
    parser.add_argument('--root_dir', type=str, required=True, help='Root directory for WSI tiles')
    parser.add_argument('--save_dir', type=str, required=True, help='Directory to save the processed tile data')

    # Parse arguments
    args = parser.parse_args()

    # Call the main function with the parsed arguments
    main(csv_file=args.csv_file, root_dir=args.root_dir, save_dir=args.save_dir)