Yuxuan Liu

Pytorch cuda error assertion failed

1

Thank you for your great work! I was trying out your work in a newer version of pytorch (1.5.1 to be exact). I have updated the operations of iou3d and...

About a fix in "compute_radius" (kitti_data_utils.py)

1

There is an old problem of mis-implementation of the [CornetNet](https://github.com/princeton-vl/CornerNet). And "has been fixed" in CenterNet [https://github.com/Duankaiwen/CenterNet/issues/47](https://github.com/Duankaiwen/CenterNet/issues/47). This repo, by default, makes ground truth heatmap following CenterNet who follows CornerNet....

Segmentation fault on CUDA 11.0/torch 1.7.1

23

Thank you for your great contribution. ### CUDA 11.0? I do manage to compile everything in a docker with CUDA 11.0/pytorch 1.7.1. including spconv (it seems that spconv show no...

A problem with pretrain dla model

4

Thanks for your great work. Some users reported that the pretrained model links failed. Please help fix the problem? https://github.com/Owen-Liuyuxuan/visualDet3D/issues/73

feat(include_launch_description): only check required arguments in the local launch file

8

## Description In a feature request issue on https://github.com/ros2/launch/issues/745. It suggests that the argument checking mechanism in `include_launch_description.py` introduces unnecessary overhead for launching large systems. In this PR, a mechanism...

## Feature request ### Feature description I would hope to add an argument to skip the argument checking in [`actions/include_launch_description.py` ](https://github.com/ros2/launch/blob/dce6bd86ce84b010bfc7b9c00c11e6331a6381cb/launch/launch/actions/include_launch_description.py#L163). ### Background 1. `include_launch_description` now searches **exhaustively** for all...

feat(pull_request_templates): improve the pull request template to enhance requirements on documenting interface changes

1

## Description Augment the pull request template to enhance requirements for documenting interface changes. 1. Add the "Interface changes" section in small-change, because we witness many small changes including additional...

Two minor bugs in the initial code

1

Thanks for the contribution of the code and paper. It is inspiring and helps the community forward. From the initial version, it seems that two minor bugs are presented in...

Failed to train well using the preset parameters

1

Tensorflow 1.10 Ubuntu 16.04 Python 2.7 First, thank you for your contribution. Here is the issue. I first changed tf.mul into tf.multiply to make tensorflow compatible to my current version....

About the Splat module

4

Thanks for your great work. We have been quite eager to know more about this work. For me, it is still rather confusing how the network converts the (C,D,H,W) image...