-
Hi
I tried to train GAN model with PlaidML (to testing conv2d_transposed).
But error occurred in backend.py
```bash
$ python mnist_cond_gan_plaidml.py
Discriminator model:
INFO:plaidml:Open…
shi3z updated
6 years ago
-
On a M6000 with 12GB the reported memory consumption from MXNet `debug_str` does not correspond to the real memory consumption measured with nvidia-smi.
cuDNN v5
| Phase | nvidia-smi | debug_str | ba…
-
I noticed that the current iteration of the toy-nn library has two activation functions; the sigmoid (aka logistic) function and the TanH function.
There are actually a ton of activation functions…
-
With Bazel 0.3.2, on Windows, it's failing to compile this particular target:
https://github.com/GerritCodeReview/gerrit/blob/master/gerrit-patch-jgit/BUILD#L27-L37
With this outcome:
```
da…
-
Hi, I have been experimenting the [u-net code ](https://github.com/jocicmarko/ultrasound-nerve-segmentation/blob/master/train.py) . It works fine. In order to let the trained network to be able to pre…
-
Greetings,
Some published NMT architectures rely on adding extra linguistic information to the source sentence. Examples include POS tags (https://www.aclweb.org/anthology/U/U16/U16-1001.pdf) and s…
-
Look-up table is an essential technique used to speed up some core part of mpv's `opengl` backend, including most scaler based on convolution kernel (polar or not), dithering and 3dlut based color man…
-
Seems like a few people including myself are looking to understand how to use Fold for convolution. I've been bashing my head against this for a while now but haven't been able to figure it out and ha…
-
To build a convolutional RNN, we need to run convolutions inside a for loop. It was working in the hand coded Theano, but now I'm getting an error I couldn't figure out. Can anybody help? It crashes u…
-
I have a convnet loaded from a file and would like to compute some of its properties. To do that, I need to go through all the layers and get their types. I figured out how to do this. Now I need to f…