Error in CPU execution of 01_classification_modelnet
siddharthm28 opened this issue · 3 comments
Hi, Firstly thanks for the prompt reply regarding the previous issue. I subsequently tried running the code in examples/01_classification_modelnet and I got this error:
~/octnet/distro/install/bin/luajit: ...hesis/octnet/distro/install/share/lua/5.1/trepl/init.lua:389: module 'cunn' not found:No LuaRocks module found for cunn
no field package.preload['cunn']
no file '../../th/cunn/init.lua'
no file '~/.luarocks/share/lua/5.1/cunn.lua'
no file '~/.luarocks/share/lua/5.1/cunn/init.lua'
no file '~/thesis/octnet/distro/install/share/lua/5.1/cunn.lua'
no file '~/thesis/octnet/distro/install/share/lua/5.1/cunn/init.lua'
no file './cunn.lua'
no file '~/thesis/octnet/distro/install/share/luajit-2.1.0-beta1/cunn.lua'
no file '/usr/local/share/lua/5.1/cunn.lua'
no file '/usr/local/share/lua/5.1/cunn/init.lua'
no file '/cis/home/msid/.luarocks/lib/lua/5.1/cunn.so'
no file '/cis/home/msid/thesis/octnet/distro/install/lib/lua/5.1/cunn.so'
no file '/cis/home/msid/thesis/octnet/distro/install/lib/cunn.so'
no file './cunn.so'
no file '/usr/local/lib/lua/5.1/cunn.so'
no file '/usr/local/lib/lua/5.1/loadall.so'
stack traceback:
[C]: in function 'error'
...hesis/octnet/distro/install/share/lua/5.1/trepl/init.lua:389: in function 'require'
train_mn10_r64.lua:5: in main chunk
[C]: in function 'dofile'
...net/distro/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00406670
I don't know LUA but from what I understand, this error is coming either when it's loading a gpu model on a cpu machine or from the require('cunn') statement. I also see some :add( cudnn.xxxx) statements which require gpu version ? I guess my request is, can you make a cpu-only version of this code and a gpu version ? Thanks in advance !
The example requires the lua packages cunn and cudnn (and therefore also CUDA, and cudnn on your platform). If you look at th/oc/OctreeConvolutionMM.lua you will notice that the implementation for cpu is missing.
That said, you might still be able to run the example if you remove all the require('cunn')
, and require('cudnn')
, replace all :cuda()
with :float()
, and replace oc.OctreeConvolutionMM
with oc.OctreeConvolution3x3x3
.
Okay. Will it be possible to share the learnt model separately ? I'm personally more interested in using the learnt model for some other things rather than learning the model again. Also, maybe add a statement in the examples saying this code needs a gpu, so that future users don't have the same issue ? You can close this issue when you want. Thanks !
Hi, I wanted to comment and let you know that the GPU version works fine out the box without any problems. I had to wait for my sysadmin to install some dependencies and I was able to do everything smoothly after that. Thanks and looking forward to playing with your code/research !