crop_gain.py

from pathlib import Path

import mrcfile
import numpy as np

image_path = "CountRef_20250327_s004101_75-4_000_Mar27_17.04.37.mrc"
image = mrcfile.read(image_path)
image = np.array(image)
image = image[:, :4031]

output_dir = Path() / "cropped"
output_dir.mkdir(parents=True, exist_ok=True)
output_path = output_dir / image_path
mrcfile.write(output_path, image, voxel_size=1)

crop_images.py

import concurrent.futures
from pathlib import Path

import numpy as np
import tifffile


def crop_and_save(image_path: Path, output_path: Path):
    image = tifffile.imread(image_path)
    image = np.array(image)  # (t, h, w)
    image = image[:, :, :4031]
    tifffile.imwrite(output_path, image)


if __name__ == "__main__":
    # find image files
    files = list(Path().glob("*.tif"))
    n_files = len(files)
    print(f"Found {n_files} images...")

    # generate output filenames
    output_dir = Path() / "cropped"
    output_dir.mkdir(parents=True, exist_ok=True)
    output_files = [
        output_dir / file.name
        for file in files
    ]

    # Counter for completed tasks
    completed = 0

    # Process files in parallel using ThreadPoolExecutor
    with concurrent.futures.ThreadPoolExecutor(max_workers=20) as executor:
        # Submit all tasks
        futures = [
            executor.submit(crop_and_save, file, output_file)
            for file, output_file in zip(files, output_files)
        ]

        # Process results as they complete
        for future in concurrent.futures.as_completed(futures):
            future.result()  # Get result or raise exception if one occurred
            completed += 1
            print(f"\rProcessed {completed}/{n_files} images", end="")

    # Print a newline after the counter
    print("\nAll images processed successfully!")