Lucas Caccia

Error in projection_distribution (Distributional DQN) ?

1

Hi, I have a question regarding the `projection_distribution` method. It seems that when you are projecting back on the support/bins, at lines : ``` proj_dist.view(-1).index_add_(0, (l + offset).view(-1), (next_dist *...

Data download link broken

1

Hi, the link to download the data is broken. Could you please fix it ? Thanks, Lucas

Hyperparams for results reported in the paper

4

Hello, is it possible to have hyperparameters values that reproduce the NVRNN and LM results on the PTB dataset ? Many thanks, Lucas

Convolution Backward Pass with kernel_size > 1

5

Hi, I'm currently trying to implement a custom convolution operation (foward and backward passes). I am starting from the code provided [here](https://facebookresearch.github.io/TensorComprehensions/_sources/framework/pytorch_integration/autograd_with_tc.rst.txt) I am getting an error with the backward...

Replicating the bits / dim results in the original VQ-VAE paper

7

Hi, thanks for your clean implementation ! I was wondering, have you ever tried to calculate the bits / dimension metric (as in the original paper) ? I've tried to...

Error in NLL_oracle / NLL_test reported for LeakGAN

1

Hi, It seems that in the current setup, **a different temperature** is used to calculate NLL_oracle and NLL_test for LeakGAN. Is this intended ? This (in my opinion) gives a...

Feature Request : Gaussian GLN

2

Cool work! and clean implementation I saw the authors recently released a newer version called Gaussian Gated Linear Networks https://arxiv.org/pdf/2006.05964.pdf I'd be curious to know how hard it would be...

trouble converging with EMD

16

Hi, I was wondering if you had encountered convergence issues when training an point autoencoder with EMD as loss function. I find that using a strictly convolutional decoder (instead of...

Hi, First of all thanks for setting up this package :) It's super helpful, thanks I'm wondering, is there a way to use a smaller block size ? I tried...

Hi, I was wondering how to interpret the 12 dimensional velodyne imu measurement. Is it a 12-way split of the 360 degree surrounding ? Thanks