fast-style-transfer icon indicating copy to clipboard operation
fast-style-transfer copied to clipboard

Published 20 hours ago • verified publisher icon lengstrom

when training style.py, it got stuck, Help!

Open Uooga opened this issue 5 years ago • 8 comments

I try to train the model, but it shows as follows and then nothing happens. I don't know how to solve it, waiting for your kindly solution, Thanks

2019-03-01 10:41:08.289612: I tensorflow/core/platform/profile_utils/cpu_utils.cc:94] CPU Frequency: 2799980000 Hz 2019-03-01 10:41:08.293372: I tensorflow/compiler/xla/service/service.cc:150] XLA service 0x2798100 executing computations on platform Host. Devices: 2019-03-01 10:41:08.293420: I tensorflow/compiler/xla/service/service.cc:158] StreamExecutor device (0): , WARNING:tensorflow:From /home/xujia/.local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py:263: colocate_with (from tensorflow.python.framework.ops) is deprecated and will be removed in a future version. Instructions for updating: Colocations handled automatically by placer. WARNING:tensorflow:From /home/xujia/.local/lib/python2.7/site-packages/tensorflow/python/ops/math_ops.py:3066: to_int32 (from tensorflow.python.ops.math_ops) is deprecated and will be removed in a future version. Instructions for updating: Use tf.cast instead. UID:26

Uooga avatar Mar 01 '19 02:03 Uooga

The first print messages don't occur until the first checkpoint is written. Be patient, and be happy that it didn't just print the UID and then say it's done when it didn't train whatsoever.

JEF1056 avatar Mar 01 '19 16:03 JEF1056

I have the same problems as like UID=80 so what now I have do is just wait ?

DLove1204 avatar Aug 22 '19 04:08 DLove1204

Yep, just wait, it'll print the iterations when it has finished one

JEF1056 avatar Aug 22 '19 04:08 JEF1056

thanks a lot!it's very helpful for me!appreciate it !!!!!!!!!!!!!!!

DLove1204 avatar Aug 22 '19 04:08 DLove1204

I am facing the same issue. After waiting for 4 hours the training was still stuck! I was training style.py on google colab. The script was running smoothly the first time I ran style.py

taiftahmid avatar Sep 04 '19 09:09 taiftahmid

I am running this on a 1080ti. Could I get some sort of print screen for what a successfully running train is? It has been sitting for awhile and I expected it to print of iterations as it went, but it is just sitting at UID.

spot92 avatar Nov 12 '19 04:11 spot92

@spot92 Try changing --checkpoint-iterations to a lower value. It prints whenever it finishes that number of iterations

JEF1056 avatar Nov 12 '19 04:11 JEF1056

@spot92 Try changing --checkpoint-iterations to a lower value. It prints whenever it finishes that number of iterations

Thanks! How many iterations are in an epoch?

spot92 avatar Nov 12 '19 04:11 spot92