Skip to content

issues Search Results · repo:caogang/wgan-gp language:Python

Filter by

56 results
 (52 ms)

56 results

incaogang/wgan-gp (press backspace or delete to remove)

caogang/wgan-gp
一堆错误

  • zhangzherui123
  • 1
  • Opened 
    on Nov 19, 2021
  • #61

caogang/wgan-gp
how to decide the value of λ

Since the d_loss = fake-real+gp, how to decide the value of LAMBDA to get a reasonable gradient penalty. I mean, if fake=-10, real=10, is gp=10 appropriate？or the gp should be smaller(e.g. gp=5)?
  • silentsaber
  • 2
  • Opened 
    on Mar 5, 2021
  • #60

caogang/wgan-gp
How does optimizer work when there are 3 backwards(real, fake, penalty)?

I thought I should write like D_cost = D_fake - D_real + gradient_penalty D_cost.backward() but I don t know why you use backward like that. https://github.com/caogang/wgan-gp/blob/ae47a185ed2e938c39cf3eb2f06b32dc1b6a2064/gan_cifar10.py#L203-L226 ...
  • wook3024
  • Opened 
    on Dec 26, 2020
  • #59

caogang/wgan-gp
Is the G_loss wrong?

HI, Should the G_loss be written as G.backward(one) instead of G.backward(mone) in gan_cifar10.py lines 241?
  • fxcdl
  • Opened 
    on Dec 15, 2020
  • #58

caogang/wgan-gp
The loss funciont is wrong in the implement?

The loss should not be: D_real.backward(mone) It should be : D_real.backward(one)
  • wangpengabc
  • 1
  • Opened 
    on Dec 2, 2020
  • #57

caogang/wgan-gp
The aixs of norm of the gradient

https://github.com/caogang/wgan-gp/blob/ae47a185ed2e938c39cf3eb2f06b32dc1b6a2064/gan_mnist.py#L148 Hi, I accidently saw your code when I google W-GAN GP. I think there is something wrong with your implementationi ...
  • CharlesNord
  • 1
  • Opened 
    on Aug 29, 2020
  • #56

caogang/wgan-gp
A question about Dcost

excuse me, can you tell me how can we get the result from descriminator and then muiltiply -1 as the cost? especially in mnist dataset, we use the sigmoid as the last layer, and the cost is negtive all ...
  • etoilestar
  • Opened 
    on Jul 17, 2020
  • #55

caogang/wgan-gp
WGAN-gp loss keeps going large

Hello, I ve implemented your code on my own dataset. However, the d_loss decreases from 10(which equals to lambda) to a very small negative number(like -10000), the wasserstein distance keeps going to ...
  • haonanhe
  • 4
  • Opened 
    on May 18, 2020
  • #54

caogang/wgan-gp
Penalizing Norm of Jacobian

My understanding of WGAN-GP is that the loss function penalizes the norm of the end-to-end Jacobian. That code appears to be here: https://github.com/caogang/wgan-gp/blob/master/gan_cifar10.py#L116 What ...
  • RylanSchaeffer
  • Opened 
    on Dec 2, 2019
  • #53

caogang/wgan-gp
(op: 'FusedBatchNorm') with input shapes: [64,256,8,8], [256], [256], [0], [0].

How can we solve this problem? InvalidArgumentError: Dimensions must be equal, but are 8 and 256 for FusedBatchNorm_14 (op: FusedBatchNorm ) with input shapes: [64,256,8,8], [256], [256], [0], [0]. Thank ...
  • Ronzhen
  • Opened 
    on Oct 8, 2019
  • #52
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Press the
/
key to activate the search input again and adjust your query.
Issue origami icon

Learn how you can use GitHub Issues to plan and track your work.

Save views for sprints, backlogs, teams, or releases. Rank, sort, and filter issues to suit the occasion. The possibilities are endless.Learn more about GitHub Issues
ProTip! 
Restrict your search to the title by using the in:title qualifier.
Issue search results · GitHub