open-mmlab/mmyolo

parameters from config are not updated in module

maximefuchs opened this issue · 0 comments

maximefuchs commented

Prerequisite

🐞 Describe the bug

Some parameters that are specified in a config file are not updated in the right module.

Expected behaviour:
if, in config, we specify train_batch_size_per_gpu = 20, then, for the output of the following :

cfg = Config.fromfile(path_to_config)
print(cfg.train_batch_size_per_gpu) # 20
print(cfg.train_dataloader.batch_size) # 20

The value of the batch size of the dataloader has been updated.
I mention, that for this train_batch_size_per_gpu parameter, it works.

However, concerning the weight losses, the values are not updated. In the outputted config file, we have loss_bbox_weight, loss_cls_weight and loss_dfl_weight (not part of any dictionnary).
If I add these in my config file, and change the values, the modules are not updated:

cfg = Config.fromfile(path_to_config)
print(cfg.loss_bbox_weight) # 8
print(cfg.model.bbox_head.loss_bbox.loss_weight) # 7.5

The same problem happens with a log of other hyperparameters. Do we have to update all the occurences manually in the config file?

Environment

sys.platform: linux
Python: 3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA RTX A4000
CUDA_HOME: /usr
NVCC: Cuda compilation tools, release 11.5, V11.5.119
GCC: x86_64-linux-gnu-gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 1.11.0+cu115
PyTorch compiling details: PyTorch built with:

  • GCC 7.3
  • 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 v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e)
  • OpenMP 201511 (a.k.a. OpenMP 4.5)
  • LAPACK is enabled (usually provided by MKL)
  • NNPACK is enabled
  • CPU capability usage: AVX2
  • CUDA Runtime 11.5
  • 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 8.3.2
  • Magma 2.5.2
  • Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.5, CUDNN_VERSION=8.3.2, CXX_COMPILER=/opt/rh/devtoolset-7/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-sign-compare -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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.11.0, 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,

OpenCV: 4.9.0
MMEngine: 0.10.3
MMCV: 2.0.0rc4
MMDetection: 3.3.0
MMYOLO: 0.6.0+077e230

Additional information

No response