There seems to be something strange when the data is loading

[MellowMemories]

Look at this official configuration written by USB, which means that for every training epoch, it will perform 1024 iterations, and each iteration will use 8 labeled images. Therefore, we can conclude that for each epoch, we would need 1024 * 8 = 8192 labeled images . However, in this configuration, we only have 400 labeled images . I don’t understand this. How can it work? Is it reasonable? By the way, I am a complete novice in deep learning and semi-supervised learning. Thanks a lot!

### Tasks