SPGAN training problem

[banxia1994]

follow the instructions，I train the SPGAN， but Every time I get stuck in training for the first epoch。
#######
2018-11-07 21:52:58.269039: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
[] Loading checkpoint...
None
[] No suitable checkpoint!
================ Begining Training time (Wed Nov 7 21:54:31 2018) ================

---

Epoch: ( 0) ( 1/ 50)
######################

It was repeated many times, once to the second epoch，But it's stuck again

################

2018-11-07 21:52:58.268951: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.1 instructions, but these are available on your machine and could speed up CPU computations.
2018-11-07 21:52:58.269018: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use SSE4.2 instructions, but these are available on your machine and could speed up CPU computations.
2018-11-07 21:52:58.269039: W tensorflow/core/platform/cpu_feature_guard.cc:45] The TensorFlow library wasn't compiled to use AVX instructions, but these are available on your machine and could speed up CPU computations.
[] Loading checkpoint...
None
[] No suitable checkpoint!
================ Begining Training time (Wed Nov 7 21:54:31 2018) ================

---

Epoch: ( 0) ( 1/ 50)

Epoch: ( 0) ( 6/ 50)

Epoch: ( 0) ( 11/ 50)

Epoch: ( 0) ( 16/ 50)

Epoch: ( 0) ( 21/ 50)

Epoch: ( 0) ( 26/ 50)

Epoch: ( 0) ( 31/ 50)

Epoch: ( 0) ( 36/ 50)

Epoch: ( 0) ( 41/ 50)

Epoch: ( 0) ( 46/ 50)
================ Training time (Wed Nov 7 22:35:27 2018) ================

Model saved in file: ./checkpoints/market2duke_spgan/Epoch_(0)_(50of50).ckpt

Epoch: ( 1) ( 1/ 50)

################

Anybody have the same problem？

[Simon4Yan]

Hello, I am not an expert at TF. Maybe you could see https://www.cnblogs.com/gaoss/p/7694682.html and tensorflow/tensorflow#7778 for the solution. Good luck to you.

BTW, I will release the pytorch vision code in few weeks.

[GuangxingHan]

@Simon4Yan Is your pytorch code based on this project https://github.com/layumi/Person_reID_baseline_pytorch? Could you share with us your new experimental results in advance?

[Simon4Yan]

@GuangxingHan Now, SPGAN and feature learning (IDE+) are both based on Pytorch.
We conduct the experiment base on pytorch framework, and the results are higher than our paper. For example, we gain 44.2% in rank accuracy on Duke. With LMP, we get about 48.6%.

You can send E-mail to me, and tell me Ur Wechat. And I will seed our new code to you in advance. Thanks for your attention.

[banxia1994]

Hello, I am not an expert at TF. Maybe you could see https://www.cnblogs.com/gaoss/p/7694682.html and tensorflow/tensorflow#7778 for the solution. Good luck to you.

BTW, I will release the pytorch vision code in few weeks.

thx for your reply， i will try for it.

[xxx2974]

@Simon4Yan ,hello,do you have the pytorch version code? I can not run this version successfully.

[2110317008]

@Simon4Yan hello,do you have the pytorch version code? I can not run this version successfully.If so, I hope you can provide it, I will be very grateful!