Piotr Ozimek

Detaching l_t

4

At the moment the location tensor _l_t_ is never detached from the computational graph in spite of both being produced by and 'consumed' by trainable modules. As far as I...

The readme doesn't explain at all what's the motivation for using this wrapper instead of [the PyTorch wrapper provided in nvvl](https://github.com/NVIDIA/nvvl/blob/master/pytorch/README.md). I myself don't know whether this wrapper would better...

Peephole connections (Wci, Wcf, Wco) gradient update

1

[The LSTM paper](ftp://ftp.idsia.ch/pub/juergen/TimeCount-IJCNN2000.pdf) defines [a specific rule](https://i.imgur.com/peOKqkL.png) for gradient updates of the 'peephole' connections. Specifically: >[...] during learning no error signals are propagated back from gates via peephole connections to...

Delta and the distribution

1

I know that this is an old repository, but if I correctly understand it the layer implemented is not computing the distance between the reconstructed tensor and the distribution of...

Openni2 fails to open Xtion camera

2

When trying to collect data from the Xtion camera via the Docker image I get the following issue: ``` **root@436e5c9570b0:/etc/udev/rules.d#** openni2-camera-lcm No matching device found.... waiting for devices. Reason: openni2_wrapper::OpenNI2Device::OpenNI2Device(const...