Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

The one_hot_labels in acgan is not pooled in tfgan.gan_loss function. #18041

Closed
fengyang0317 opened this issue Mar 28, 2018 · 9 comments
Closed

The one_hot_labels in acgan is not pooled in tfgan.gan_loss function. #18041

fengyang0317 opened this issue Mar 28, 2018 · 9 comments
Assignees
@joel-shor

Comments

@fengyang0317
Copy link

fengyang0317 commented Mar 28, 2018 •
edited

System information

  • Have I written custom code (as opposed to using a stock example script provided in TensorFlow): No.
  • OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 16.04
  • TensorFlow installed from (source or binary): binary
  • TensorFlow version (use command below): 1.6.0
  • Python version: 2.7
  • Bazel version (if compiling from source): N/A
  • GCC/Compiler version (if compiling from source): N/A
  • CUDA/cuDNN version: 9.0/7.0
  • GPU model and memory: GTX 980M 4G
  • Exact command to reproduce: N/A

Describe the problem

I am trying to use tfgan.acgan_model together with tfgan.features.tensor_pool. There are three inputs to the acgan_model, i.e. real_data, generator_inputs, and one_hot_labels. While only two of the inputs (read_data, generator_inputs) are manipulated by tensor_pool in tfgan.gan_loss, which means that the one_hot_labels are incorrectly used in the acgan_discriminator_loss function.

The following is the entrance to the error function call. The one_hot_labels should be read from the tensor pool before this function call.
https://github.com/tensorflow/tensorflow/blob/master/tensorflow/contrib/gan/python/train.py#L561
@fengyang0317 fengyang0317 changed the title The one_hot_labels in acgan is not pooled in gan_loss The one_hot_labels in acgan is not pooled in gan_loss function. Mar 28, 2018
@fengyang0317 fengyang0317 changed the title The one_hot_labels in acgan is not pooled in gan_loss function. The one_hot_labels in acgan is not pooled in tfgan.gan_loss function. Mar 28, 2018
@bignamehyp bignamehyp added the stat:awaiting tensorflower Status - Awaiting response from tensorflower label Apr 7, 2018
@bignamehyp
Copy link
Member

@joel-shor can you please take a look?

@tensorflowbutler tensorflowbutler removed the stat:awaiting tensorflower Status - Awaiting response from tensorflower label Apr 8, 2018
@bignamehyp bignamehyp added the stat:awaiting tensorflower Status - Awaiting response from tensorflower label Apr 21, 2018
@tensorflowbutler
Copy link
Member

Nagging Assignee @bignamehyp: It has been 14 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

@joel-shor joel-shor assigned joel-shor and unassigned bignamehyp May 6, 2018
@tensorflowbutler
Copy link
Member

Nagging Assignee @joel-shor: It has been 19 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

@tensorflowbutler
Copy link
Member

Nagging Assignee @joel-shor: It has been 34 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

@tensorflowbutler
Copy link
Member

Nagging Assignee @joel-shor: It has been 49 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

@tensorflowbutler
Copy link
Member

Nagging Assignee @joel-shor: It has been 64 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

tensorflow-copybara pushed a commit that referenced this issue Jul 23, 2018
@tensorflower-gardener
[tfgan] Issue #18041: Make pooling consistent in gan_loss.
931a305 
PiperOrigin-RevId: 205731279
@tensorflowbutler
Copy link
Member

Nagging Assignee @joel-shor: It has been 79 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

1 similar comment
@tensorflowbutler
Copy link
Member

Nagging Assignee @joel-shor: It has been 79 days with no activity and this issue has an assignee. Please update the label and/or status accordingly.

@joel-shor
Copy link
Contributor

Fixed by: 931a305

@joel-shor joel-shor removed the stat:awaiting tensorflower Status - Awaiting response from tensorflower label Jul 25, 2018
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees

@joel-shor joel-shor

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
4 participants
@bignamehyp @joel-shor @fengyang0317 @tensorflowbutler