Bugs in Discriminator (batch dimension and Linear layer output dim)

[itakatz]

It seems to me that the implementation of the Discriminator class has 2 issues:

1. The RNN should have the input parameter batch_first set to True, but it is not set (and defaults to False): https://github.com/zzw-zwzhang/TimeGAN-pytorch/blob/4bde0ded33d84af1504d3bc85686d10e328b8580/lib/model.py#L167
2. The output dimension of the Linear layer should be 1 as this is a binary classification block (predicting fake or not), but it is set to the hidden dimension: https://github.com/zzw-zwzhang/TimeGAN-pytorch/blob/4bde0ded33d84af1504d3bc85686d10e328b8580/lib/model.py#L169 this does not produce an error, since later the loss function averages its input. But it means the calculation is not as it shold be.

[010606zss]

How long is the training time? Why do you start iterating again after 50,000 iterations, and have been cycling this iterative process of 50,000 times?