Yilin Liu

I want to figure out what is the difference between this implementation and the original one [Kazhdan et al. 2006]. As the README mentioned, the original implementation uses an adaptive...

Information to build this program?

5

Could anyone provide some informations to help me build this program. I have tried so many combinations but failed to build it. I have tried: - ubuntu14 + cuda7.5 +...

Can't compile using cinder

1

There is no cinder in the project so I download the latest cinder and compile it and add it to the project library, but there are a lot of compiling...

About the trajectory about NY-1

3

I took the trajectory following `makeTraj.sh` successfully and get a trajectory file `ny1_opti.traj`. However, I was confused about the content. In `makeTraj.sh`, the overlap is set to 80/80. Which generate...

Can we get the ground truth of NY-1 and UK-1 for further experiements?

2

We would like to use the ground truth of the model in the benchmark for further experiments. Such as visualizing the error map of the model or find the place...

Showing "invalid value 'nvcc' for toolset" when run premake5 gmake

7

Test both in win10 and ubuntu18.04, with cuda 8.0 `../premake-core/bin/release/premake5 gmake` ``` ➜ uavmvs git:(master) ../premake-core/bin/release/premake5 gmake ** Warning: the flags value C++11 has been deprecated and will be removed....

Will the 16 or 32 codebook dimension hamper the representational capacity of autoencoders?

2

Thanks for the excellent collection and implementation of vector quantization techniques! It is very helpful for me to get to know about this technique and study the details. I've integrated...