Issues

• Why self.num_features=4 in line 15?

  automan000/Convolutional_LSTM_PyTorch#21 · Filter by author LeronQ opened on Jul 27, 2020

• Peephole connections (Wci, Wcf, Wco) gradient update

  automan000/Convolutional_LSTM_PyTorch#20 · Filter by author Pozimek opened on Oct 31, 2019
  1

• why hidden_channels % 2 == 0 ?

  automan000/Convolutional_LSTM_PyTorch#19 · Filter by author Muggle-K opened on Oct 11, 2019

• Where is the squence length

  automan000/Convolutional_LSTM_PyTorch#18 · Filter by author 2294462474 opened on Sep 23, 2019
  1

• Why Wci, Wcf, Wco are Variables rather than nn.Parameters

  automan000/Convolutional_LSTM_PyTorch#17 · Filter by author bkoyuncu opened on Aug 6, 2019
  3

• The shape of the output

  automan000/Convolutional_LSTM_PyTorch#16 · Filter by author Hiker01 opened on May 20, 2019

• Input shape issue and lack of bias.

  automan000/Convolutional_LSTM_PyTorch#15 · Filter by author mikumeow opened on May 9, 2019
  9

• Found the code is much slower than Keras counterpart (takes 2-3 times longer time). Do you know why?

  automan000/Convolutional_LSTM_PyTorch#11 · Filter by author xychenunc opened on Apr 22, 2019

• Is there any experiments results provided?

  automan000/Convolutional_LSTM_PyTorch#10 · Filter by author ghost opened on Dec 30, 2018

• How to do the entire sequence all at once?

  automan000/Convolutional_LSTM_PyTorch#8 · Filter by author SampsonKwan opened on Oct 2, 2018