computation graph broken
swappysh opened this issue · 1 comments
swappysh commented
I am trying to train a simple model:
model = seq2seq(input_dim=1,
hidden_dim=[64],
num_layers=1,
kernel_size=(3, 3),
batch_first=True,
bias=True,
return_all_layers=False).to(device)
but the computational graph is broken somewhere and I can't seem to find the place.
swappysh commented
It was unrelated to this repository