Generative adversarial network error in training process

I’m trying to make GAN which will generate art from random noise. I rely on this article https://towardsdatascience.com/generating-modern-arts-using-generative-adversarial-network-gan-on-spell-39f67f83c7b4
First off i’ve created training_data.npy file. For this purpose i wrote simple script.

import os
import numpy as np
from PIL import Image
import sys

args = sys.argv
del args[0]

if not args:
    print('Add at least 1 dir')
    sys.exit(0)

for i in args:
    if i not in os.listdir(os.getcwd()):
        print(f"Can't find {i} here")
        sys.exit()

IMAGE_SIZE = 128
IMAGE_CHANNELS = 3

training_data = []

print('resizing...')
for dir in args:
    for filename in os.listdir(os.path.abspath(dir)):
        path = os.path.join(os.getcwd(), dir, filename)
        image = Image.open(path).resize((IMAGE_SIZE, IMAGE_SIZE), Image.ANTIALIAS)
        training_data.append(np.asarray(image))

training_data = np.reshape(
    training_data, (-1, IMAGE_SIZE, IMAGE_SIZE, IMAGE_CHANNELS))
training_data = training_data / 127.5 - 1

print('saving file...')


def get_name():
    i = 1
    while True:
        if f'training_data_{i}.npy' in os.getcwd():
            i += 1
            continue
        return f'training_data_{i}.npy'


name = get_name()
print(f'saving to file {name}')
np.save(name, training_data)

There are folders(which contain images) in my current directory

After that i wrote code bellow for training model(this code locate in google colab, training_data.npy i also uploaded to google drive and use it in google colab)

https://colab.research.google.com/drive/1pLDdyRwQQe1SqYNUI8pwzgnOeUGrxnR6?usp=sharing

If u click on link above, u’ll see my error which i got. Please, help me to resolve it.
Thank u.

P.S
5 days ago i read this article carefully , and understood it. But now i’ve decided to just copy and paste the code from article and don’t reread it again. Forgive me if i make some errors in the code.