-
In a private experiment, I found that Adam with a learning rate of .001 works much better than the tutorial default. It's worth checking if this holds true for the tutorial or if it was specific to th…
-
The description of the pywt.dwt_max_levels function seems ambiguous to me.
```
Compute the maximum useful level of decomposition.
```
I've tried to do some digging/reading (a couple hours worth). …
-
-
Hi,
I have implemented a model which seems to be working. However, when I kill it, with `kill PID`, the gpu memory is not freed:
![alt text](https://discuss.pytorch.org/uploads/default/original/1X…
-
I had to add these dependencies to resolve:
```
org.slf4j
log4j-over-slf4j
1.5.11
org.slf4j
slf4j-nop
…
fakeh updated
6 years ago
-
Hi everyone and thanks for this work. I was wondering if you could give me some hint on a problem that I'm facing. Recently I've been trying to run the `mnist_tutorial_jsma.py`. So I've took that exam…
-
@arahuja has some ideas on this one.
-
I think our current model with `TensorGraph` can't nicely support GANs. In order to train GANs, you need to train both a discriminator `D` and a generator `G`. The training of these two models is thre…
-
I am trying to implement the SRGAN model from the paper [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://arxiv.org/abs/1609.04802). Since this uses both a…
-
```
Traceback (most recent call last):
File "cnn_mnist.py", line 140, in
adv_x = fgsm(batch_xs[0], y_conv, 0.3)
File "cnn_mnist.py", line 43, in fgsm
signed_grad = tf.sign(grad)
F…