Binh-Son Hua

It is unclear what causes this error. Please upload the content of the log file. 2016-12-13 20:28 GMT+08:00 wudanhxh : > Hi,I run the dvo_slam according to https://github.com/songuke/dvo_slam in >...

I'm not sure what happens after seeing this log. But there's something you can try - Check the other three log files. Any useful log message there? - Check trajectory.txt...

[tf_conv3p.zip](https://github.com/scenenn/pointwise/files/3299460/tf_conv3p.zip) I doubt that using a precompiled dynamically linked library from my machine will work on yours. But as per your request, here it is. 2019年6月18日(火) 10:39 longma : >...

I think it could be the hdf5 file is not found. Please check the path to your ModelNet40 data in the training script. 2019年8月21日(水) 13:11 cc818 : > when i...

The code is only tested on Tensorflow 1 on Linux. Thanks for your interest! 2021年4月26日(月) 22:58 hduonggithub ***@***.***>: > Hi > > It is very nice work. > I am...

It's doable. You need to solve the compatibility problem in the Tensorflow 2 API, and the compilation issues for CUDA code. This is technically an engineering problem. If you are...

What is your Tensorflow version? You might want to try this instead: https://github.com/scenenn/pointwise/blob/master/tf_ops/conv3p/tf_conv3p_compile_tf14.sh

Could you see the solution in this issue: https://github.com/scenenn/pointwise/issues/7 It could be related to some ABI flag in gcc. Thanks.

Thanks Sai. Could you provide more details about the error? So you can run the forward convolution successfully? Which data are you testing? ModelNet40?

To produce this visualization, you need to predict the labels of each block of the scene, and use the global coordinates stored in each point and put all the points...