VirConv
VirConv copied to clipboard
hailanyi
Virtual Sparse Convolution for Multimodal 3D Object Detection
您好，我的电脑安装的是ubuntu22.04版本。torch是2.0.0版本，python是3.9版本，spconv是2.3.6版本，cuda是11.8版本。运行的时候出现：RuntimeError: Error compiling objects for extension的错误，请问该怎么有效的解决呢，谢谢！
hello！ My data set has nothing to do with the automatic driving of cars. Can I use it to detect the health of the mining bucket teeth? Thank you very...
while installing the model using python3 setup.py develop this error is raised C:/Program Files (x86)/Microsoft Visual Studio/2022/BuildTools/VC/Tools/MSVC/14.33.31629/include\crtdefs.h(10): fatal error C1083: Cannot open include file: 'corecrt.h': No such file or directory...
UserWarning: resource_tracker: There appear to be 4 leaked semaphore objects to clean up at shutdown
I encountered this error during training：UserWarning: resource_tracker: There appear to be 4 leaked semaphore objects to clean up at shutdown warnings.warn('resource_tracker: There appear to be %d ' /xiachenxing/students/2022/wangbaotong/miniconda3/envs/VirConv/lib/python3.9/multiprocessing/resource_tracker.py:216: UserWarning: resource_tracker:...
I could train with a single GPU, but when I try to run with multiple GPU by running dist_train.sh, the program stopped without reporting anything. My dist_train.sh is like this:...
running this line: `python3 -m pcdet.datasets.kitti.kitti_dataset_mm create_kitti_infos tools/cfgs/dataset_configs/kitti_dataset.yaml ` shows this error: > ImportError: cannot import name 'roiaware_pool3d_cuda' from 'pcdet.ops.roiaware_pool3d' (unknown location)
Hello author! I want to ask a question: In order to submit to KITTI and obtain better test results When dividing training set and validation set If I use 80%-20%...
Hi, thank you for your wonderful work. For my understanding, the features of virtual points and the features of the Lidar points have to be fused ultimately. However, i am...
Dear Hailanyi: When I was training with Virconv-L, I found an incredible problem: ` [Exception|implicit_gemm_backward]feat=torch.Size([0]),w=torch.Size([32, 3, 3, 32]),pair=torch.Size([9, 166197]),issubm=True,do=torch.Size([166197, 32]) epochs: 24%|██▍ | 12/50 [6:29:43
I have tried to fix the seed for VirConv, but the loss of the training keeps changing...