mmdetection3d icon indicating copy to clipboard operation
mmdetection3d copied to clipboard
verified publisher icon open-mmlab

When I was training with MVXnet, the trained APs were all 0. I have tried many methods and still can't solve this problem.

Open chfyyds opened this issue 2 years ago • 9 comments

What is the feature?

----------- AP11 Results ------------

Pedestrian [email protected], 0.50, 0.50: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000 Pedestrian [email protected], 0.25, 0.25: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000 Cyclist [email protected], 0.50, 0.50: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000 Cyclist [email protected], 0.25, 0.25: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000 Car [email protected], 0.70, 0.70: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000 Car [email protected], 0.50, 0.50: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000

Overall AP11@easy, moderate, hard: bbox AP11:0.0000, 0.0000, 0.0000 bev AP11:0.0000, 0.0000, 0.0000 3d AP11:0.0000, 0.0000, 0.0000

----------- AP40 Results ------------

Pedestrian [email protected], 0.50, 0.50: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 Pedestrian [email protected], 0.25, 0.25: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 Cyclist [email protected], 0.50, 0.50: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 Cyclist [email protected], 0.25, 0.25: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 Car [email protected], 0.70, 0.70: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000 Car [email protected], 0.50, 0.50: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000

Overall AP40@easy, moderate, hard: bbox AP40:0.0000, 0.0000, 0.0000 bev AP40:0.0000, 0.0000, 0.0000 3d AP40:0.0000, 0.0000, 0.0000

Any other context?

System environment: sys.platform: linux Python: 3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0] CUDA available: True numpy_random_seed: 1604293306 GPU 0: NVIDIA GeForce RTX 3060 CUDA_HOME: /usr/local/cuda-11.3 NVCC: Cuda compilation tools, release 11.3, V11.3.58 GCC: gcc (Ubuntu 7.5.0-6ubuntu2) 7.5.0 PyTorch: 1.12.0+cu113 PyTorch compiling details: PyTorch built with:

  • GCC 9.3

  • C++ Version: 201402

  • Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications

  • Intel(R) MKL-DNN v2.6.0 (Git Hash 52b5f107dd9cf10910aaa19cb47f3abf9b349815)

  • OpenMP 201511 (a.k.a. OpenMP 4.5)

  • LAPACK is enabled (usually provided by MKL)

  • NNPACK is enabled

  • CPU capability usage: AVX2

  • CUDA Runtime 11.3

  • NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_86,code=sm_86

  • CuDNN 8.2.1

    • Built with CuDNN 8.3.2

  • Magma 2.5.2

  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDGE_PROFILER_USE_KINETO -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Werror=cast-function-type -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.12.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

    TorchVision: 0.13.0+rocm5.1.1 OpenCV: 4.8.1 MMEngine: 0.8.4

Runtime environment: cudnn_benchmark: False mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0} dist_cfg: {'backend': 'nccl'} seed: 1604293306 Distributed launcher: none Distributed training: False GPU number: 1

chfyyds avatar Nov 21 '23 02:11 chfyyds

can you slove this problem?

mihudaner avatar Jul 04 '24 20:07 mihudaner

i have same problem---

mihudaner avatar Jul 04 '24 20:07 mihudaner

Please check the spcon-cuxxx matches your cuda version

Barath19 avatar Aug 06 '24 14:08 Barath19

i have same problem

Vish19-code avatar Apr 09 '25 12:04 Vish19-code

https://github.com/open-mmlab/mmdetection3d/issues/2815#issuecomment-2271385493

Barath19 avatar Apr 09 '25 14:04 Barath19

i already install but same problem i am using cuda11.3 in window

Vish19-code avatar Apr 09 '25 14:04 Vish19-code

Can you confirm your spcon-cuxxx version as well?

Barath19 avatar Apr 09 '25 15:04 Barath19

yes,

but i have still problem

Vish19-code avatar Apr 11 '25 11:04 Vish19-code

i have problem in kitti dataset because this is authorize data

Vish19-code avatar Apr 17 '25 17:04 Vish19-code