Zhenyu Tang

Results 18 comments of Zhenyu Tang

> LGTM > > Any down sides to adding this? Additional memory perhaps? The only downside is additional memory for duplicating faces when this flag is active - face triangle...

Thanks for your reply. I am also looking forward to their new stable release. Currently, I have made the mentioned changes myself and will push that back once they release...

[This example script](https://github.com/GAMMA-UMD/pygsound/blob/master/examples/mesh_sim.py) is a good place to start with. We load the `cube.obj` file in the script, which can describe arbitrary shapes. You can find our implementations [here](https://github.com/GAMMA-UMD/pygsound/blob/master/src/pygsound/src/SoundMesh.cpp). This...

We did not test on M1 mac before. I can confirm that building on M1 will raise errors. I'll see if I can make it compatible this weekend.

I made some attempts in the new `m1-fix` branch but unfortunately, I don't think it's fully fixed yet and I cannot say when will this be done. It's mainly due...

From L171, I think the logic is to restore saved parameters trained on previous folders? So I guess it's not training 8 separate models if the `keep` option is set...

> I got this repo to work, however it took a lot of effort and many bug fixes. At the end, it's just not worth it - this repo has...

Easiest to do in conda: `conda install -c conda-forge libsndfile`

> Hi, I've noticed the same problem with HPF and LPF. I'm only training on a single GPU, but found that it only occurs if I'm using multiprocessing in my...