pix2pix icon indicating copy to clipboard operation
pix2pix copied to clipboard

There is a error occured when training the model using GPU

Open happsky opened this issue 7 years ago • 1 comments

Hello, Thanks for your code. but when I tried your code, it always shows the problem that :

hao@sibiu:~/pix2pix-master1$ DATA_ROOT=./datasets/facades name=facades_generation which_direction=BtoA th train.lua { cudnn : 1 name : "facades_generation" niter : 200 batchSize : 1 n_layers_D : 0 ndf : 64 which_model_netG : "unet" save_display_freq : 5000 print_freq : 50 gpu : 1 use_GAN : 1 DATA_ROOT : "./datasets/facades" serial_batch_iter : 1 use_L1 : 1 save_epoch_freq : 50 output_nc : 3 checkpoints_dir : "./checkpoints" input_nc : 3 beta1 : 0.5 continue_train : 0 which_direction : "BtoA" phase : "train" fineSize : 256 condition_GAN : 1 loadSize : 286 lambda : 100 ngf : 64 preprocess : "regular" which_model_netD : "basic" display_freq : 100 display : 1 display_id : 10 ntrain : inf nThreads : 2 lr : 0.0002 flip : 1 save_latest_freq : 5000 serial_batches : 0 } Random Seed: 8967 #threads...2 Starting donkey with id: 1 seed: 8968 table: 0x40530d80 Starting donkey with id: 2 seed: 8969 table: 0x406f7280 ./datasets/facades trainCache /home/hao/pix2pix-master1/cache/_home_hao_pix2pix-master1_datasets_facades_train_trainCache.t7 Creating train metadata serial batch:, 0 table: 0x400aeb38 running "find" on each class directory, and concatenate all those filenames into a single file containing all image paths for a given class ./datasets/facades trainCache /home/hao/pix2pix-master1/cache/_home_hao_pix2pix-master1_datasets_facades_train_trainCache.t7 Creating train metadata serial batch:, 0 table: 0x406dee78 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 now combine all the files to a single large file cmd..wc -L '/tmp/lua_DOjJKU' |cut -f1 -d' ' 400 samples found......................... 0/400 .......................................] ETA: 0ms | Step: 0ms
Updating classList and imageClass appropriately [======================================== 1/1 ========================================>] Tot: 1ms | Step: 1ms
load the large concatenated list of sample paths to self.imagePath cmd..wc -L '/tmp/lua_PCaggu' |cut -f1 -d' ' Cleaning up temporary files 400 samples found......................... 0/400 .......................................] ETA: 0ms | Step: 0ms
Updating classList and imageClass appropriately [======================================== 1/1 ========================================>] Tot: 1ms | Step: 1ms
Cleaning up temporary files Dataset Size: 400 define model netG... define model netD... nn.gModule nn.Sequential { [input -> (1) -> (2) -> (3) -> (4) -> (5) -> (6) -> (7) -> (8) -> (9) -> (10) -> (11) -> (12) -> (13) -> output] (1): nn.SpatialConvolution(6 -> 64, 4x4, 2,2, 1,1) (2): nn.LeakyReLU(0.2) (3): nn.SpatialConvolution(64 -> 128, 4x4, 2,2, 1,1) (4): nn.SpatialBatchNormalization (5): nn.LeakyReLU(0.2) (6): nn.SpatialConvolution(128 -> 256, 4x4, 2,2, 1,1) (7): nn.SpatialBatchNormalization (8): nn.LeakyReLU(0.2) (9): nn.SpatialConvolution(256 -> 512, 4x4, 1,1, 1,1) (10): nn.SpatialBatchNormalization (11): nn.LeakyReLU(0.2) (12): nn.SpatialConvolution(512 -> 1, 4x4, 1,1, 1,1) (13): nn.Sigmoid } transferring to gpu... /home/gloria/torch/install/bin/luajit: ...e/gloria/torch/install/share/lua/5.1/nngraph/gmodule.lua:205: attempt to call method 'replace' (a nil value) stack traceback: ...e/gloria/torch/install/share/lua/5.1/nngraph/gmodule.lua:205: in function 'cudnn' train.lua:186: in main chunk [C]: in function 'dofile' ...oria/torch/install/lib/luarocks/rocks/trepl/scm-1/bin/th:145: in main chunk [C]: at 0x00406670

@phillipi I am a beginner of deep learning and Linux. The torch I used is Torch7. Besides, I run this code on a server machine and do not have the sudo rights. Any suggestion for that ? thanks!


The following shows the libs I have installed.

hao@sibiu:~/pix2pix-master1$ luarocks list

Installed rocks:

argcheck scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

async scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

audio 0.1-0 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

cudnn scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

cunn scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

cunnx scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

cutorch scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

cwrap scm-1 (installed) - /home/hao/.luarocks/lib/luarocks/rocks scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

display scm-0 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

dok scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

env scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

fftw3 scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

gnuplot scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

graph scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

graphicsmagick 1.scm-0 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

image 1.1.alpha-0 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

lua-cjson 2.1devel-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

luaffi scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

luafilesystem 1.6.3-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

luasocket 3.0rc1-2 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

matio scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

nn scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

nngraph scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

nnx 0.1-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

optim 1.0.5-0 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

paths scm-1 (installed) - /home/hao/.luarocks/lib/luarocks/rocks scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

penlight scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

qtlua scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

qttorch scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

signal scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

sundown scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

sys 1.1-0 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

threads scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

torch scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

trepl scm-1 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

xlua 1.0-0 (installed) - /home/gloria/torch/install/lib/luarocks/rocks

happsky avatar Mar 15 '17 20:03 happsky

Have you installed cudnn library?

junyanz avatar Apr 05 '17 08:04 junyanz