search

open-mmlab / mmdetection3d

OpenMMLab's next-generation platform for general 3D object detection.
https://mmdetection3d.readthedocs.io/en/latest/
Apache License 2.0
5.18k stars 1.52k forks source link

assertion error when changing samples_per_gpu in pointpilllars ( kitti 3class) #171

Closed Jsijon closed 3 years ago

Jsijon commented 3 years ago

i changed samples_per_gpu to 2 from default 6 and it gives me assertion error in anchor_3dhead.py line 330 assert len(featmap_sizes) == self.anchor_generator.num_levels

why this happens?

ZwwWayne commented 3 years ago

Please use the error template or the reimplementation issues to report your bug. The information is limited to debug.

Jsijon commented 3 years ago

What command or script did you run? python tools/train.py configs/pointpillars/hv_pointpillars_secfpn_6x8_160e_kitti-3d-3class.py

Did you make any modifications on the code or config? Did you understand what you have modified? i changed the samples_per_gpu from deafault 6 to 2

What dataset did you use? Kitti

Enviroment information sys.platform: linux Python: 3.8.3 (default, Jul 2 2020, 16:21:59) [GCC 7.3.0] CUDA available: True CUDA_HOME: / NVCC: Cuda compilation tools, release 10.1, V10.1.243 GPU 0: GeForce GTX 1650 SUPER GCC: gcc (Ubuntu 9.3.0-10ubuntu2) 9.3.0 PyTorch: 1.6.0 PyTorch compiling details: PyTorch built with:

GCC 7.3 C++ Version: 201402 Intel(R) Math Kernel Library Version 2020.0.1 Product Build 20200208 for Intel(R) 64 architecture applications Intel(R) MKL-DNN v1.5.0 (Git Hash e2ac1fac44c5078ca927cb9b90e1b3066a0b2ed0) OpenMP 201511 (a.k.a. OpenMP 4.5) NNPACK is enabled CPU capability usage: AVX2 CUDA Runtime 10.2 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_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_37,code=compute_37 CuDNN 7.6.5 Magma 2.5.2 Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -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 -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_STATIC_DISPATCH=OFF, TorchVision: 0.7.0 OpenCV: 4.3.0 MMCV: 1.0.5 MMDetection: 2.3.0 MMDetection3D: 0.5.0+5f7b31c MMDetection3D Compiler: GCC 9.3 MMDetection3D CUDA Compiler: 10.1

yinchimaoliang commented 3 years ago

Hi! I followed your description and changed 'samples_per_gpu' in kitti-3d-3class.py, but I can't reproduce the error, can you be more specific about what you've changed and share your changed config?