Closed ellick53 closed 4 years ago
The dataset link is missing. https://davischallenge.org/code.html Which DAVIS dataset are you using?
Thanks for replying! I am using Davis 2016: https://davischallenge.org/davis2016/code.html
The code requires Optical Flow result from mpnet. However, I do not have MATLAB, so I cannot test it.
The problem is probably the last CMaxTable change.
https://github.com/torch/nn/commit/db4244e6ee30b0ec689815a00fcc0c8c45f91b12
This commit breaks old pre-training model that uses CMaxTable (The added variables mask
, maxVals
, and gradMaxVals
are not defined in the loaded model.).
Copying the previous version of CMaxTable.lua to ~/torch/extra/nn/CMaxTable.lua
, ~/torch/install/share/lua/5.1/nn/CMaxTable.lua
, may fix it (not tested) .
the previous version of CMaxTable.lua: https://raw.githubusercontent.com/torch/nn/c463e548ecf795b84b171121a0206e5e326d4858/CMaxTable.lua
I have not yet decided whether to fix existing bugs in torch7.
Thanks! It worked! Could this replacement cause any side effects, though?
Could this replacement cause any side effects, though?
Performance may be slightly degraded. Probably the pre-trained model with the newer CMaxTable will also work, but the code accessing the added variables(maxVals) will not work.
I see. In any case, I should still be able train the network without issues?
http://lear.inrialpes.fr/research/lvo/ 's pre-trained models is trained with the previous version of CMaxTable. So I think that train without the newer CMaxTable is correct as replicated experiment.
I see, thanks!
I am trying to train this network: http://lear.inrialpes.fr/research/lvo/ using your Torch distro.
I am using Ubuntu 18 + CUDA 10.0. I also installed rnn from https://github.com/Element-Research/rnn and extracunn from https://github.com/viorik/extracunn.git.
Unfortunately, when I start the training I get this error:
I get a similar error if I try to train the network. I am not familiar with Lua or Torch (I usually use TensorFlow 2).
Could someone help me? I really need to make this work, but the only thing I can think of is some obscure incompatibility with more recent systems, which would require installing Ubuntu 14 + CUDA 7.5.
Thanks!