[Bug] Fail to use confusion_matrix to RGBPoseC3D

HoBeom commented 6 months ago

Branch

main branch (1.x version, such as v1.0.0, or dev-1.x branch)

Prerequisite

[X] I have searched Issues and Discussions but cannot get the expected help.
[X] I have read the documentation but cannot get the expected help.
[X] The bug has not been fixed in the latest version.

Environment

sys.platform: linux Python: 3.9.17 (main, Jul 5 2023, 20:41:20) [GCC 11.2.0] CUDA available: True numpy_random_seed: 2147483648 GPU 0,1,2,3: NVIDIA GeForce RTX 4090 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.8, V11.8.89 GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0 PyTorch: 2.0.1+cu117 PyTorch compiling details: PyTorch built with:

GCC 9.3
C++ Version: 201703
Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications
Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
OpenMP 201511 (a.k.a. OpenMP 4.5)
LAPACK is enabled (usually provided by MKL)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 11.7
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 8.8.1 (built against CUDA 11.8)
- Built with CuDNN 8.5
Magma 2.6.1
Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.1, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

TorchVision: 0.15.2 OpenCV: 4.8.0 MMEngine: 0.8.2 MMAction2: 1.2.0+4d6c934 MMCV: 2.0.1 MMDetection: 3.1.0

Describe the bug

While attempting to configure evaluators for validation and testing phases for the RGBPoseC3D, I encountered an issue where specifying ConfusionMatrix as part of the evaluators does not work as expected.

Reproduces the problem - code sample

The configuration is defined in configs/skeleton/posec3d/rgbpose_conv3d/rgbpose_conv3d.py. The relevant section of the configuration is as follows:

val_evaluator = [dict(type='AccMetric'), dict(type='ConfusionMatrix')]
test_evaluator = val_evaluator

Reproduces the problem - command or script

 ./tools/dist_train.sh configs/skeleton/posec3d/rgbpose_conv3d/rgbpose_conv3d.py 4

Reproduces the problem - error message

mmaction/evaluation/metrics/acc_metric.py", line 252, in process
    pred_label = pred_scores.argmax(dim=0, keepdim=True)
AttributeError: 'dict' object has no attribute 'argmax'

Additional information

The modified version in my branch, which was adjusted to operate identically to the AccMetric module, functions only for specific purposes. There is a need to redesign the abstraction of the evaluation code.

lmc2000 commented 5 months ago

解决了吗?

HoBeom commented 5 months ago

@lmc2000 Use modified version in my branch

https://github.com/HoBeom/mmaction2/blob/789c12d53ab830c8a7bfc01e34ae9ef777d8f775/mmaction/evaluation/metrics/acc_metric.py#L272-L300

lmc2000 commented 5 months ago

谢谢,我也对我自己的代码做了相应的修改

open-mmlab / mmaction2