Size of Real Image & Synthetic Image not matching

[nitish116]

You put an assert statement to check , if size of real images and synthetic images are matching for pre training Discriminator , but the sizes are different

128 != 52 , because of this it is throwing an error.

Why is that necessary ? How do I fix the error ? Am I working with wrong dataset ?

[AlexHex7]

I couldn't remember the details, but this assert means the batch size of real image and synthetic image must be equal. If it is not equal, it can not calculate the loss. In fact, most people use data_loader to load the image now, and pass the batch size parameter to it. I think you should check the code of loading images.

[Temofey]

Ошибка из-за того что в наборе данных с реальными изображениями находится всего 52 картинки. Я решил проблему тем, что просто уменьшил batch_size до 32