PointNet2库可能需要GPU支持来运行。 你可以通过以下代码检查PyTorch是否能够使用GPU: import torch print(torch.cuda.is_available()) 如果输出为True,则表示PyTorch可以使用GPU。如果为False,则可能需要检查CUDA和GPU驱动是否正确安装。 5. 检查环境变量 确保你的环境变量设置正确,特别是与PyTorch和CUDA相关的环境变量。
[-Wdeprecated-declarations] if (!x.type().is_cuda()) { \ ^ /root/OpenPCDet/pcdet/ops/pointnet2/pointnet2_batch/src/ball_query.cpp:29:24: note: in expansion of macro ‘CHECK_CUDA’ #define CHECK_INPUT(x) CHECK_CUDA(x);CHECK_CONTIGUOUS(x) ^~~~ /root/OpenPCDet/pcdet/ops/point...
np_resource = np.dtype([("resource", np.ubyte, 1)]) No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda-10.0' /home/eric/anaconda3/lib/python3.6/site-packages/pointnet2_ops/pointnet2_utils.py:15: UserWarning: Unable to load pointnet2_ops cpp extension. JIT Compiling. warnings...
For me, CUDA 10, cuDNN 7.2, and Tensorflow 1.12.0 worked. 👍 3 NicksonYap mentioned this issue Jan 29, 2019 Import network module (No module named model) Scannet charlesq34/pointnet2#78 Closed sycophant-stone commented Mar 12, 2019 it seems like: reduce the batch_size reduce ...