Dacheng Li

module not found for cpp_extension

1

I have some issues running the seeing_distribution notebook. It gives an import error No module named '_prroi_pooling' _prroi_pooling = load_extension('_prroi_pooling', [pjoin(root_dir, 'prroi_pooling_gpu.c'), pjoin(root_dir, 'prroi_pooling_gpu_impl.cu')],verbose=False) at funtional.py. I am not really...

To integrate with other distributed systems with built in synchronization optimization, it will be great to transfer synchronization ability to it. It will be great if we can expose a...

Hi there! I have verified flan-t5 training goes smoothly. Could you review the training file? I am rebasing inference file and will update later.  A sample answer by the...

Is it possible to get book3 metadata, specifically, which are fiction and which are not?

Potential reference for VAE-GAN

1

Hello there! I just read 1.1 report, and is absolutely amazing. I realize you are using GAN loss for training the VAE? I have done a similar work [here](https://openaccess.thecvf.com/content/CVPR2021/papers/Parmar_Dual_Contradistinctive_Generative_Autoencoder_CVPR_2021_paper.pdf). Maybe...

Why not reuse mixkit/pixabay/pexels in v1.1.0 for 1.2.0 training?

2

HI there, thanks a lot for the great work! I am wondering whether there is reason not to use the original (3000 hours) data collected in v1.1.0 training for 1.2.0...