ConvLSTM_pytorch

ConvLSTM_pytorch copied to clipboard

multi-gpu use

1

Hi, I just wanted to know if this implementation would work well in a DataParrallel model and if there was some adaptation to do ? Thanks

Xcrid

Does the stateful implementataion work similar to the LSTMs statefulness.

1

giridhar13

Any example using the implement like Moving MNIST?

1

First thanks for your implementing the conv-lstm which is useful in the video predict, I like to use pytorch, and find your implement, have you succeed training on the toy...

guanfuchen

I am not sure how to handle the situation of various length of input sample. I think padding is not okay for my problem. Is there any better way to...

calx-git

Understanding the algo.

1

Hello there, really interested in your work but i am still understanding the implementation. Can you explain you have used stacked version of x_(t) and h_(t-1) for convolution according to...

Osama26-byte

https://discuss.pytorch.org/t/lstm-generate-pkl-runtimeerror-cudnn-error-cudnn-status-mapping-error/181139?u=xukw123123 PLEASE

xukw123123

RuntimeError

2

When added the code below, I got an error:" RuntimeError: expected stride to be a single integer value or a list of 3 values to match the convolution dimensions, but...

yeyulege

Add the dropout parameter to ConvLSTM, which defaults to 0.0. For num_layers to 1, dropout does not work; For num_layers greater than 1, dropout works on the output of each...

lizhuoq

This is my codes, I use MSELoss(), and target is the size of torch.Size([4, 1, 1, 144, 256]), but the last layer is like torch.Size([4, 1, 64, 144, 256]), 64...

luckui