GPU issue

[guylsan]

Hi,
I have an issue when i tap this command "python pre_process.py -s 1 -i ./dicoms -o ./datasets/experiment/test" , prompt respond " warnings.warn(msg)
0 files in the folder" while i've lot of dicoms format images., and the root is good. Do you ve any idea of the problem ?
My laptop have only a AMD GPU...
Is it possible this made the error ?

There is a solution or a modification to run it with CPU ?
Thanks a lot

[Xin Yi]

Preprocessing doesn't need a gpu. The warning says it doesn't find any images in the given folder. So please check if your .dicom images are inside ./dicoms folder.

[guylsan]

Yes they are in this folder :( !

[Xin Yi]

It's hard to find out what's gone wrong in this case unless you post a snapshot of your folder structures.

I've updated my code for pre- and post-processing. You can try it out again to see if the warning still exists.

[guylsan]

It's working, thanks
but now i Have another problem when i tape DATA_ROOT=./datasets/experiment name=SAGAN which_direction=AtoB phase=test th test.lua

i got this error "guylain@guylain-HP-Pavilion-17-Notebook-PC:~/torch/torch-hdf5/SAGAN$ DATA_ROOT=./datasets/experiment name=SAGAN which_direction=AtoB phase=test th test.lua
{
input_nc : 3
results_dir : "./results/"
name : "SAGAN"
batchSize : 1
phase : "test"
fineSize : 512
aspect_ratio : 1
how_many : "all"
gpu : 1
nThreads : 1
DATA_ROOT : "./datasets/experiment"
serial_batch_iter : 1
preprocess : "regular"
norm : "batch"
which_epoch : "latest"
which_direction : "AtoB"
cudnn : 1
serial_batches : 1
display : 0
output_nc : 3
loadSize : 512
checkpoints_dir : "./checkpoints"
display_id : 200
flip : 0
}
Random Seed: 292
#threads...1
Starting donkey with id: 1 seed: 293
table: 0x40c9e3d0
./datasets/experiment
trainCache /home/guylain/torch/torch-hdf5/SAGAN/cache/_home_guylain_torch_torch-hdf5_SAGAN_datasets_experiment_test_trainCache.t7
Creating train metadata
serial batch:, 1
table: 0x40c9ba58
running "find" on each class directory, and concatenate all those filenames into a single file containing all image paths for a given class
now combine all the files to a single large file
load the large concatenated list of sample paths to self.imagePath
cmd..wc -L '/tmp/lua_owgTbK' |cut -f1 -d' '
62 samples found....... 0/62 .......................] ETA: 0ms | Step: 0ms
Updating classList and imageClass appropriately
[===================== 1/1 =======================>] Tot: 0ms | Step: 0ms
Cleaning up temporary files
Dataset Size: 62
checkpoints_dir ./checkpoints
/home/guylain/torch/install/bin/luajit: /home/guylain/torch/install/share/lua/5.1/trepl/init.lua:389: module 'cudnn' not found:No LuaRocks module found for cudnn
no field package.preload['cudnn']
no file '/home/guylain/.luarocks/share/lua/5.1/cudnn.lua'
no file '/home/guylain/.luarocks/share/lua/5.1/cudnn/init.lua'
no file '/home/guylain/torch/install/share/lua/5.1/cudnn.lua'
no file '/home/guylain/torch/install/share/lua/5.1/cudnn/init.lua'
no file './cudnn.lua'
no file '/home/guylain/torch/install/share/luajit-2.1.0-beta1/cudnn.lua'
no file '/usr/local/share/lua/5.1/cudnn.lua'
no file '/usr/local/share/lua/5.1/cudnn/init.lua'
no file '/home/guylain/.luarocks/lib/lua/5.1/cudnn.so'
no file '/home/guylain/torch/install/lib/lua/5.1/cudnn.so'
no file '/home/guylain/torch/install/lib/cudnn.so'
no file './cudnn.so'
no file '/usr/local/lib/lua/5.1/cudnn.so'
no file '/usr/local/lib/lua/5.1/loadall.so'
stack traceback:
[C]: in function 'error'
/home/guylain/torch/install/share/lua/5.1/trepl/init.lua:389: in function 'require'
/home/guylain/torch/torch-hdf5/SAGAN/util/util.lua:187: in function 'load'
test.lua:79: in main chunk
[C]: in function 'dofile'
...lain/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:150: in main chunk
[C]: at 0x00405d50
"
and i don't find on the internet a solution for this issues
Thanks you for everything