Fail to run NAS methods on yolov5,yolov6 and RTMDet

[LishaTang]

Prerequisite

• [X] I have searched the existing and past issues but cannot get the expected help.
• [X] I have read the FAQ documentation but cannot get the expected help.
• [X] The bug has not been fixed in the latest version.

🐞 Describe the bug

Hi, I tried to run your config files listed in config/razor/subnets and all of them failed. It seems to be a problem caused by incompatible versions between mmyolo and mmrazor. Could you please help solve this? Or is there any way to test NAS-based methods and autoslim, a pruning method contained in mmrazor, on YOLO series and RTMDet? Thanks for your help! This is the bug produced: File "./tools/train.py", line 115, in main() File "./tools/train.py", line 104, in main runner = Runner.from_cfg(cfg) File "/home/tt/anaconda3/envs/mmyolo-v2/lib/python3.8/site-packages/mmengine/runner/runner.py", line 439, in from_cfg runner = cls( File "/home/tt/anaconda3/envs/mmyolo-v2/lib/python3.8/site-packages/mmengine/runner/runner.py", line 406, in init self.model = self.build_model(model) File "/home/tt/anaconda3/envs/mmyolo-v2/lib/python3.8/site-packages/mmengine/runner/runner.py", line 808, in build_model model = MODELS.build(model) File "/home/tt/anaconda3/envs/mmyolo-v2/lib/python3.8/site-packages/mmengine/registry/registry.py", line 548, in build return self.build_func(cfg, *args, **kwargs, registry=self) File "/home/tt/anaconda3/envs/mmyolo-v2/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 241, in build_model_from_cfg return build_from_cfg(cfg, registry, default_args) File "/home/tt/anaconda3/envs/mmyolo-v2/lib/python3.8/site-packages/mmengine/registry/build_functions.py", line 135, in build_from_cfg raise type(e)( TypeError: class YOLODetector in mmyolo/models/detectors/yolo_detector.py: class sub_model in mmrazor/registry/registry.py: class SearchableShuffleNetV2 in mmrazor/models/architectures/backbones/searchable_shufflenet_v2.py: init() takes 1 positional argument but 2 were given

Environment

sys.platform: linux Python: 3.8.16 (default, Mar 2 2023, 03:21:46) [GCC 11.2.0] CUDA available: True numpy_random_seed: 2147483648 GPU 0,1,2,3,4,5,6,7,8,9: NVIDIA GeForce RTX 3090 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.6, V11.6.124 GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0 PyTorch: 1.12.0 PyTorch compiling details: PyTorch built with:

• GCC 9.3
• 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 v2.6.0 (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 11.6
• 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_80,code=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
• CuDNN 8.3.2 (built against CUDA 11.5)
• Magma 2.6.1
• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.6, 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 OpenCV: 4.7.0 MMEngine: 0.7.0 MMCV: 2.0.0rc4 MMDetection: 3.0.0rc6 MMYOLO: 0.5.0+dc85144

Additional information

I didn't make any changes to the model or config. Besides, I have tried both 1.0.0rc2 and dev-1.x version for mmrazor, which didn't work.

[gaoyang07]

mmcls is required when using backbones in mmrazor: https://github.com/open-mmlab/mmrazor/blob/90c5435bb0c49cf0c85fd316b078b1718952e21a/mmrazor/models/architectures/backbones/searchable_shufflenet_v2.py#L14-L18

[LishaTang]

Problem solved! Thanks so much for your time and help! Btw, is it possible for u to release a config file which supports pruning methods on MMYolo in the future? I just find that most model compression libraries show limited support for downstream tasks:) Thanks again.