dictdiffer | Dictdiffer is a module that helps you to diff and patch

from sklearn.metrics import accuracy_score

h = {'1': ['IMG_0001.png', 'IMG_0002.png', 'IMG_0003.png', 'IMG_0004.png'],
     '2': ['IMG_0020.png', 'IMG_0021.png', 'IMG_0022.png', 'IMG_0023.png'],
     '3': ['IMG_0051.png', 'IMG_0052.png', 'IMG_0053.png', 'IMG_0054.png']}

c = {'1': ['IMG_0001.png', 'IMG_0002.png', 'IMG_0053.png', 'IMG_0054.png'],
     '2': ['IMG_0020.png', 'IMG_0021.png', 'IMG_0022.png', 'IMG_0023.png'],
     '3': ['IMG_0003.png', 'IMG_0004.png', 'IMG_0051.png', 'IMG_0052.png']}

images = []
for key, value in h.items():
    images.extend(value)
print(images)  # ['IMG_0001.png', 'IMG_0002.png', 'IMG_0003.png', 'IMG_0004.png', 'IMG_0051.png', ..., 'IMG_0023.png']

reverse_h = {}
for key, value in h.items():
    for img in value:
        reverse_h[img] = key
print(reverse_h)  # {'IMG_0003.png': '1', 'IMG_0051.png': '3', 'IMG_0004.png': '1', ..., 'IMG_0054.png': '3'}

y_true = [reverse_h[img] for img in images]
print(y_true)  # ['1', '1', '1', '1', '3', '3', '3', '3', '2', '2', '2', '2']

reverse_c = {}
for key, value in c.items():
    for img in value:
        reverse_c[img] = key

print(reverse_c)  # {'IMG_0053.png': '1', 'IMG_0020.png': '2', 'IMG_0003.png': '3', ..., 'IMG_0054.png': '1'}

y_pred = [reverse_c[img] for img in images]
print(y_pred)  # ['1', '1', '3', '3', '3', '3', '1', '1', '2', '2', '2', '2']

score = accuracy_score(y_true, y_pred)
print(score)  # 0.6666666666666666