How to: looking for dublicates in image dataset

[K0nkere]

from collections import defaultdict
from hashlib import md5

hash_dict = defaultdict(list)

img_dir = Path('./images')
for image in img_dir.glob('*.jpg'):

    with image.open('rb') as f:
        img_hash = md5(f.read()).hexdigest()
        hash_dict[img_hash].append(image)

len(hash_dict)

duplicate_img = []

for k, v in hash_dict.items():
    if len(v) > 1:
        if v[0].name != v[1].name:
            duplicate_img.append(v[0])
            duplicate_img.append(v[1])
            print(v)
len(duplicate_img)