zouzhenhong98 / sensaturban-bev-seg3d Goto Github PK

您好！我preprocess后得到了alt,rgb,cls,vis，但是训练的好像是rgbd四通道数据？有点没明白能麻烦解答一下嘛

还是

I only found the archive version. May I know how I can find your paper in a conference? Need a non-archive version for citation.

Thanks,

Eric

您好，可以提供以下关于使用kpconv网络模型处理SensatUrban数据集的代码吗？我现在正在为这个事情着急。因为我需要对比不同网络处理该数据的性能，关于处理该数据的网络模型目前还是很少。

Thank you so much for your great work
When I train according to the readme process, the model always fails to achieve the same curve as img/single_scale_training.png
My experimental configuration is:
2 x 2080ti and batchsize=4
miou can only be up to 41% in the validation set

In addition, can you also provide pre-trained weights?
thank you very much

Hello, I'm searching for the code that can help me convert data into the Cityscapes format. Could someone please direct me to the repository or source where I can find this code? Thank you!

SensatUrban数据集分为train,val,test，train和val数据都是N×7，test是N程6（没有class），但是在point_EDA_31.py内生成test的BEV时并没有按照N×6的形式进行处理而是N×7.