NyquistBodeTu
NyquistBodeTu
Hi, it's my great pleasure that the labelcloud is the wonderful tool to make KITTI untransformed kind dataset. By modifying some codes, it is easy to train 3D detection neural...
 自制点云数据集没有对应的图片,这一步没法完成,在模型训练中恰好又需要这一步生成的真值库,如何跳过这个步骤,请大佬支招,谢谢!
 这个是我在openpcdet里看到的,请问Paddle3D有这样的功能吗?
反向传播的报错
File "/home/user/anaconda3/envs/torch_py38/lib/python3.8/site-packages/adaPool-0.1-py3.8-linux-x86_64.egg/adaPool/idea.py", line 206, in backward adapool_cuda.backward_1d_em(*saved) RuntimeError: input.is_contiguous()INTERNAL ASSERT FAILED at "CUDA/adapool_cuda.cpp":348, please report a bug to PyTorch. input must be a contiguous tensor
是针对大中小三类目标分别设立不同尺度的检测头吗?
有老哥给了这个https://github.com/PaddlePaddle/Paddle/issues/60540 解决方案,cudnn换成8.5版本的,但是  paddle inference的wheel包只支持8.4的cudnn,无解。另外我用的是nvidia/cuda:11.4.3-cudnn8-runtime-ubuntu20.04这个镜像,这里cudnn是8.2.4的,希望工作人员能尽快更新这个镜像版本的whl包支持!