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):
   

   TimeGAN-pytorch/lib/model.py

   Line 167 in 4bde0de

   self.rnn = nn.GRU(input_size=opt.hidden_dim, hidden_size=opt.hidden_dim, num_layers=opt.num_layer)

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:
   

   TimeGAN-pytorch/lib/model.py

   Line 169 in 4bde0de

   self.fc = nn.Linear(opt.hidden_dim, opt.hidden_dim)

   
   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?