-
I'm confused about the category loss "l_d_cls_fake = self.cri_ce(cls_d_fake, self.var_cat)", which seems the same behaviour as "l_g_cls = self.l_gan_w * self.cri_ce(cls_g_fake, self.var_cat)" in gener…
-
#### TensorFlow.js version
v2.0+
#### Browser version
Google chrome v84.0.4147.125
#### Describe the problem or feature request
Problem is located in [gan.js](https://github.com/tensorflow/tfjs-e…
-
I tried to run your sgan code on GPU but it is giving me,
[D loss: nan, acc: 0.00%, op_acc: 6.25%] [G loss: nan]
However, it is working fine on my local cpu machine. Do you know why I am getting th…
-
Is it possible to use the Estimator API for ACGAN?
Can you provide an example to show how to train an ACGAN in tf-gan?
Thanks.
-
I tried to run age_lsgan_transfer.py with CACD2000 dataset and this was what i got
C:\Users\Thanh\Python37\python.exe D:/Documents/Deep_learning_xu_ly_anh/Source_code/GAN/Face-aging/Face-Aging-with…
-
Hi, @joebradly @joshalbrecht @akanimax @SaoYan
I met this error when run your cifar-10 train code.
--
Files already downloaded and verified
Starting the training process ...
Currently w…
-
**Hello, thank you for sharing your code! Could please help me in solving this problem?**
/home/umair/.local/lib/python3.6/site-packages/tensorflow/python/framework/dtypes.py:516: FutureWarning: Pa…
-
Hey,
I needed to normalize my input data, to keep the norm and inverse the normalization. I used a Lambda layer for this and it works well.
```
import numpy as np
from keras import backend as…
-
Hi guys,
Thank you for your great work. I have a question.
I found that generate_data.py works very well with my style-gan models, but when I trained PGGAN with the same dataset of images and t…
-
### System information
Red Hat Enterprise 7.4
### Describe the current behavior
I am interested in saving the generator of a gan to onnx format. I have sampled the code from applications/test_ker…