ConvLSTM-PyTorch

ConvLSTM-PyTorch copied to clipboard

大佬，我注意到您在每个cell之间还加了一层卷积和leaky relu这是为什么呢?

3

大佬，我注意到您在每个cell之间还加了一层卷积和leaky relu这是为什么呢?

KingRyu1998

Hello, awesome repo. I have been playing with various convlstm/gru implementation as we don't have an official one in Pytorch. I am having trouble getting good images as output. I...

tcapelle

How can I check the prediction effect and do I need to have test.py program? Thanks

4

After the program has run the training dataset and validation dataset normally, no corresponding test.py program is found, is there still this part of the program or am I misunderstanding...

tjnkyqcy

how to use this code to do some research on industrial process monitoring

graduatemazada

decoder的第一层输入都是初始化的么？

lf-demo

convlstm好像没有按照论文那种思想，而是直接套用trajgru的encoder-forcaster结构么？我看预测器状态都是从高维传递

lf-demo

窥视孔连接哪里去了呀？ it、ft应该有Ct-1的信息，ot应该有Ct的信息呀

Angry-Echo

After training for 20 epochs with default params, the validation results seem to be quite blurry.

4

 Could anyone offer a solution. Many thanks.

Crestina2001

请问大佬您这个模型的数据集可以用ERA5再分析数据集吗？，请问最后预测有可视化结果吗？

LIU-code-create

This error causes the model to be initialized using the parameters of ConvGRU regardless of whether the user passes in the "--convlstm" comand-line argument.

xyyntax