mmpretrain
mmpretrain copied to clipboard
[Bug] KeyError: 'RANK' appears when using 'fusion_matrix. py'
Branch
main branch (mmpretrain version)
Describe the bug
KeyError: 'RANK' appears when using 'fusion_matrix. py' When I used the Confusion matrix to evaluate custom models and data sets, I found a bug. This problem will lead to a KeyError: 'RANK' when using a custom configuration file to evaluate the Confusion matrix. The simple way to solve this bug is to annotate the launcher='pytorch' in the configuration file, or change it to launcher='none'.
Environment
System environment: sys.platform: linux Python: 3.8.17 | packaged by conda-forge | (default, Jun 16 2023, 07:06:00) [GCC 11.4.0] CUDA available: True numpy_random_seed: 647731525 GPU 0,1,2,3,4,5,6,7: NVIDIA RTX A6000 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.3, V11.3.109 GCC: gcc (Ubuntu 9.5.0-1ubuntu1~22.04) 9.5.0 PyTorch: 1.10.1 PyTorch compiling details: PyTorch built with:
- GCC 7.3
- C++ Version: 201402
- Intel(R) oneAPI Math Kernel Library Version 2021.4-Product Build 20210904 for Intel(R) 64 architecture applications
- Intel(R) MKL-DNN v2.2.3 (Git Hash 7336ca9f055cf1bfa13efb658fe15dc9b41f0740)
- OpenMP 201511 (a.k.a. OpenMP 4.5)
- LAPACK is enabled (usually provided by MKL)
- NNPACK is enabled
- CPU capability usage: AVX512
- CUDA Runtime 11.3
Other information
No response
Traceback (most recent call last):
File "tools/analysis_tools/confusion_matrix.py", line 108, in