prepare_submission.py

import os

from PIL import Image
import numpy as np

def rle_encode(img):
    '''
    img: numpy array, 1 - mask, 0 - background
    Returns run length as string formated
    '''
    pixels = img.flatten()
    pixels = np.concatenate([[0], pixels, [0]])
    runs = np.where(pixels[1:] != pixels[:-1])[0] + 1
    runs[1::2] -= runs[::2]
    return ' '.join(str(x) for x in runs)

def rle_decode(mask_rle, shape):
    '''
    mask_rle: run-length as string formated (start length)
    shape: (height,width) of array to return
    Returns numpy array, 1 - mask, 0 - background
    '''
    s = mask_rle.split()
    starts, lengths = [np.asarray(x, dtype=int) for x in (s[0:][::2], s[1:][::2])]
    starts -= 1
    ends = starts + lengths
    img = np.zeros(shape[0]*shape[1], dtype=np.uint8)
    for lo, hi in zip(starts, ends):
        img[lo:hi] = 1
    return img.reshape(shape)


def create_rles():
    """Used for Kaggle submission: predicts and encode all test images"""
    dir = 'data/test_preds/'
    N = len(list(os.listdir(dir)))
    with open('submission_file.csv', 'w') as f:
        f.write('ImageClassId,rle_mask\n')
        for index, i in enumerate(os.listdir(dir)):
            # print('{}/{}'.format(index, N))

            mask = Image.open(dir + i)
            mask = mask.resize((1024, 1024), resample=Image.NEAREST)
            mask = np.array(mask)

            for x in range(1, 25):
                enc = rle_encode(mask == x)
                f.write(f"{i.split('_')[0]}_{x},{enc}\n")

create_rles()