brannondorsey
commented
7 years ago Hi there, is it possible that you've disabled JavaScript in whatever browser you are using to try and view the display? Enabling/disabling javascript can generally be done from the web dev console.
On Tue, Mar 21, 2017 at 1:50 PM, coventry notifications@github.com wrote:
This is likely a newbie question, in which case apologies. It's my first time using torch.
The display output is basically blank. The
contains...and just shows up as a small green "online"/"offline" toggle button in the top left-hand corner.
I'm running display and train.lua as follows. Corrections very welcome.
root@44fbf66c8c00:/pix# th -ldisplay.start 8888 0.0.0.0 server listening on http://0.0.0.0:8888 GET /events GET / GET /style.css GET /panes.js GET /events GET /favicon.png
root@44fbf66c8c00:/pix# display_freq=1 display_plot='errL1,errG,errD' DATA_ROOT=./datasets/facades name=facades_generation which_direction=BtoA th train.lua [22/1993] { 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 : 1 display_freq : 1 display_id : 10 flip : 1 ntrain : inf lr : 0.0002 nThreads : 2 display_plot : "errL1,errG,errD" save_latest_freq : 5000 serial_batches : 0 } Random Seed: 8676
threads...2
Starting donkey with id: 1 seed: 8677 table: 0x402bbc08 Starting donkey with id: 2 seed: 8678 table: 0x41120d50 ./datasets/facades ./datasets/facades trainCache /pix/cache/_pix_datasets_facades_train_trainCache.t7 Creating train metadata serial batch:, 0 table: 0x40561be8 running "find" on each class directory, and concatenate all those filenames into a single file containing all image paths for a given class trainCache /pix/cache/_pix_datasets_facades_train_trainCache.t7 Creating train metadata serial batch:, 0 table: 0x415d9d68 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 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_K5voTT' |cut -f1 -d' ' load the large concatenated list of sample paths to self.imagePath cmd..wc -L '/tmp/lua_y4o7yL' |cut -f1 -d' ' 400 samples found......................... 0/400 .......................................] ETA: 0ms | Step: 0ms Updating classList and imageClass appropriately [======================================== 1/1 ========================================>] Tot: 0ms | Step: 0ms 400 samples found......................... 0/400 .......................................] ETA: 0ms | Step: 0ms Updating classList and imageClass appropriately [======================================== 1/1 ========================================>] Tot: 0ms | Step: 0ms Cleaning up temporary files 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... done Epoch: [1][ 49 / 400] Time: 0.223 DataTime: 0.000 Err_G: 0.8045 Err_D: 0.6729 ErrL1: 0.2700 Epoch: [1][ 99 / 400] Time: 0.223 DataTime: 0.000 Err_G: 0.8879 Err_D: 0.5638 ErrL1: 0.2848 Epoch: [1][ 149 / 400] Time: 0.223 DataTime: 0.000 Err_G: 0.5377 Err_D: 0.7555 ErrL1: 0.3924 Epoch: [1][ 199 / 400] Time: 0.224 DataTime: 0.000 Err_G: 2.4808 Err_D: 0.0926 ErrL1: 0.3895 Epoch: [1][ 249 / 400] Time: 0.224 DataTime: 0.000 Err_G: 3.5942 Err_D: 0.0906 ErrL1: 0.3900 Epoch: [1][ 299 / 400] Time: 0.224 DataTime: 0.000 Err_G: 1.9321 Err_D: 0.2085 ErrL1: 0.4939 Epoch: [1][ 349 / 400] Time: 0.235 DataTime: 0.000 Err_G: 4.0155 Err_D: 0.0537 ErrL1: 0.4394 Epoch: [1][ 399 / 400] Time: 0.256 DataTime: 0.000 Err_G: 3.3058 Err_D: 0.0382 ErrL1: 0.4399 End of epoch 1 / 200 Time Taken: 91.750 Epoch: [2][ 49 / 400] Time: 0.227 DataTime: 0.000 Err_G: 2.9637 Err_D: 0.1760 ErrL1: 0.3569 Epoch: [2][ 99 / 400] Time: 0.247 DataTime: 0.000 Err_G: 3.9921 Err_D: 0.1488 ErrL1: 0.5377
— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/phillipi/pix2pix/issues/64, or mute the thread https://github.com/notifications/unsubscribe-auth/ADC6vRot_0jjxEUkBLbA44opuF5smP-xks5roBwJgaJpZM4MkQDV .
-- PGP Public Key http://brannondorsey.com/publickey.asc http://brannondorsey.com @brannondorsey https://twitter.com/brannondorsey
coventry
d0t1q
happsky
sjain24
This is likely a newbie question, in which case apologies. It's my first time using torch.
The
displayoutput is basically blank. The<body>contains...and just shows up as a small green "online"/"offline" toggle button in the top left-hand corner.
I'm running
displayandtrain.luaas follows. Corrections very welcome.