SnowflakeNet

SnowflakeNet copied to clipboard

Code for L2 Chamfer distance

1

Hello, authors! I would like to know how you obtained the L2 Chamfer distance in Table 2 of your paper. After executing your code on the c3d dataset, I obtained...

ShenZheng2000

Training with special point cloud dataset

5

Hi, I want to use myself training dataset, dose it possible? Could I set each of these point cloud dataset to a fixed size of 200000 points for-example, instead of...

ema2161

Visualization issue

4

May I ask the software used for visualization, thanks!

Fayeben

Regarding validation transforms

3

Hi, I noticed that you are scaling the point clouds by 0.85 during validation - [#](https://github.com/AllenXiangX/SnowflakeNet/blob/main/utils/data_loaders.py#L244). Wouldn't this reduce the chamfer value as the whole object is now compressed to...

MukundVarmaT

About training duration

2

hi, I wonder how do you define your training strategy (e.g. batchsize in pcn case and hardware infos) and how much epochs does it take to converge? Looking forward to...

leonardozcm

Thanks for the nice work! Recently I want to reproduce your paper result on the Completion3D dataset, however, the official standford completion3d dataset link no longer works... Although I know...

symphonylyh

Testing on my point cloud

1

I want to test the completion model on my point cloud. I load it as a Nx3 array where N~9000 and I feed it to the ckpt-best-shapenet34_21-cd_l2.pth model checkpoint. The...

FSet89

编译出错

1

作者您好！ 我在编译该代码下的chamfer3D和emd时报错。错误如下： creating build/temp.linux-x86_64-cpython-37 /usr/local/cuda-11.0/bin/nvcc -I/home/whc/miniconda3/envs/spd/lib/python3.7/site-packages/torch/include -I/home/w/miniconda3/envs/spd/lib/python3.7/site-packages/torch/include/torch/csrc/api/include -I/home/w/miniconda3/envs/spd/lib/python3.7/site-packages/torch/include/TH -I/home/w/miniconda3/envs/spd/lib/python3.7/site-packages/torch/include/THC -I/usr/local/cuda-11.0/include -I/home/whc/miniconda3/envs/spd/include/python3.7m -c chamfer3D.cu -o build/temp.linux-x86_64-cpython-37/chamfer3D.o -D__CUDA_NO_HALF_OPERATORS__ -D__CUDA_NO_HALF_CONVERSIONS__ -D__CUDA_NO_HALF2_OPERATORS__ --expt-relaxed-constexpr --compiler-options '-fPIC' -DTORCH_API_INCLUDE_EXTENSION_H -DPYBIND11_COMPILER_TYPE=\"_gcc\" -DPYBIND11_STDLIB=\"_libstdcpp\" -DPYBIND11_BUILD_ABI=\"_cxxabi1011\" -DTORCH_EXTENSION_NAME=chamfer_3D -D_GLIBCXX_USE_CXX11_ABI=0 -gencode=arch=compute_86,code=sm_86 -std=c++14 nvcc...

Wanghc233

How to obtain point cloud files in point cloud completion testing

7

Thank you for your excellent work! I am a beginner who trained the point cloud completion task using your code and obtained the checkpoint and log files in the exp...

yizhiboyan

Errors when training the completion models :1、raise self.exc_type(msg) ValueError: Caught ValueError in DataLoader worker process 0. 2、ValueError: high <= 0

2

Dear sir, I am a beginner tring to repeat your fantastic work. I made sure that the environment and PyTorch extensions are installed according to the instructions , then I...

by0619