Wei Jiang

New release request

8

#201 this is resolved in current master branch. Please do a new release. Thanks!

have trouble with rendering to texture

5

Hi: I'm trying to render a Voronoi diagram to numpy array using the rasterizer. Here is my code: ``` # ----------------------------------------------------------------------------- # Copyright (c) 2009-2016 Nicolas P. Rougier. All rights...

Sharing raw data of ETH3D and KITTI

13

Hi everyone: I'd like to share the raw output from COTR for ETH3D and KITTI dataset. ETH3D eval: https://drive.google.com/file/d/1pfAuHRK7FvB6Hc9Rru-beH6F-2lpZAk6/view?usp=sharing KITTI: https://drive.google.com/file/d/1SiN5UbqautqosUCInQN2WhyxbRcbWt8b/view?usp=sharing The format is: {src_id}->{tgt_id}.npy, and I saved the results...

I found the following command can install the basic env for inference: ``` conda create -n cotr_env python=3.7 conda activate cotr_env conda install scipy=1.2.1 conda install pytorch==1.7.1 torchvision==0.8.2 torchaudio==0.7.2 cudatoolkit=10.2...

How do MAgent handle collision?

4

Hi geek-ai: Thank you for contributing this great work! I want know how MAgent handle collision? Could you provide some information about the mechanism of avoiding collision or handling the...

Hi: Thanks for sharing this project! I'm trying to understand one function: https://github.com/skyhehe123/VoxelNet-pytorch/blob/bfd7be1ca6e5c5b39eece8a4c5fad3ad7b1f7c74/voxelnet.py#L62-L81 Especially: https://github.com/skyhehe123/VoxelNet-pytorch/blob/bfd7be1ca6e5c5b39eece8a4c5fad3ad7b1f7c74/voxelnet.py#L73-L74 The mask is not used for generating the locally aggregated feature. This may cause the...

What's the correct way to switch to solo farming? For OG plots

Wrong depth image

2

Hi: Thank you for the great work! I downloaded the dataset, and inspected the depth images. I found that the all depth images are all white, all the pixel value...

❓ [Question] How to compile a model with A16W8?

1

Hi Torch-TensorRT team: I'm wondering how can I compile a model with 8 bit weights, but using 16 bit activations? Thanks a lot!

Hi AIT team: I'm working on compiling a generative video model into AIT. I can successfully compile the model, as you can see here: ``` 2024-02-09 07:20:35,614 INFO max_blob=19546740864 constant_offset=7630531776...