-
hello!
There are 'img_celeba.7z' 'img_align_celeba_png.7z' 'img_align_celeba.zip',which did you use?
cmyyy updated
5 years ago
-
Hi, I have a question about your implementation to evaluate Lipschitz norm of a convolutional layer.
You follow the following instruction described in [Spectral Norm Regularization for Improving th…
-
Is it possible to share the 31255 dataset?
31255 128p images will be not that big. It is very easy to upload it to Internet.
In fact we have some unique GAN training tricks and would like to help to…
-
看到代码中 generator loss 所需的 reward 有下面各种表达形式：
reward = 2 * (tf.sigmoid(...) - 0.5)
reward = tf.sigmoid(tf.maximum(0.0, 1.0 - (pos_score - neg_score)))
reward = tf.log(tf.sigmoid(neg_score - pos_score)…
-
to foster community involvement - some richer sample code beyond MNIST should be tackled.
Generative Adversarial Networks is a hot topic amongst ML - and some sample code using swift should help enco…
-
I am having a similar issue as in #1291 but it is also somewhat different. I do observe that after a certain number of iterations the algorithm is slowing down massively. I have tried many things to f…
-
to foster community involvement - some richer sample code beyond MNIST should be tackled.
Generative Adversarial Networks is a hot topic amongst ML - and some sample code using swift should help enco…
-
NMF in scikit-learn overview :
**Current implementation ([code](https://github.com/scikit-learn/scikit-learn/blob/master/sklearn/decomposition/nmf.py)):**
- loss = squared (aka Frobenius norm)
…
-
It seems to me that lightning does not fit the intercept anytime. So is it necessary to have a `intercept_` attribute?