Conan
Conan
Hi, I have two questions about the paper that I can't understand to ask you for full sincerity, hoping you can give some detail or explanation about them. The first...
I run the creation of the training data for Nuscene, and it displays that it need 48 hour to process this training data. I don't know other people need how...
numba should be version 0.40.0 `conda install numba==0.40.0` and set the variable in ~/.bashrc export NUMBAPRO_CUDA_DRIVER=/usr/lib/x86_64-linux-gnu/libcuda.so export NUMBAPRO_NVVM=/usr/local/cuda/nvvm/lib64/libnvvm.so export NUMBAPRO_LIBDEVICE=/usr/local/cuda/nvvm/libdevice
https://github.com/ConanCui/Research-Line 
1. The degree of nodes are different, so we usually need normalization in GCN (by using degree matrix). In equation 3, 4, 5, I can't find the normalization. 2. In...
Can you provide an example about how to process the feature and rating data?
Hi, I notice that you get the mu and sigma as https://github.com/ShellingFord221/My-implementation-of-What-Uncertainties-Do-We-Need-in-Bayesian-Deep-Learning-for-Computer-Vision/blob/e6ed204cd25ac995eb8ec8da701117dcd5aabb1d/classification_aleatoric.py#L81. As I know, sigma should be larger than zero, how can the real value in logit.split to satisfy...
Hi You have done a good job here, but I am little confused about the normalized beta, it is shows in the code Peiyao_Sheng_beta_VAE.ipynb. The KL loss is computed by...
Hi I run the training script with the config, and it shows that there is a typo in the config that "rpn" is spelled with "vpn" https://github.com/peiyunh/wysiwyg/blob/b1747a2aceb26bccfaeb825e0cac4b21f87eeb1e/second/configs/nuscenes/all.pp.mhead.vpn.config#L32 I correct it...