TypeError: Mask2Former: __init__() got an unexpected keyword argument 'pretrained'

LiWentomng commented 2 years ago

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

When I try the script of the below to get the FPS

python -m torch.distributed.launch --nproc_per_node=1 --master_port=29500 tools/analysis_tools/benchmark.py configs/mask2former/mask2former_r50_lsj_8x2_50e_coco.py work_dirs/mask2former/iter_737500.pth --launcher pytorch

I encounter the below erro：

Traceback (most recent call last):
  File "/root/miniconda3/envs/mmdet-mask2former/lib/python3.7/site-packages/mmcv/utils/registry.py", line 52, in build_from_cfg
    return obj_cls(**args)
TypeError: __init__() got an unexpected keyword argument 'pretrained'

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "tools/analysis_tools/benchmark.py", line 195, in <module>
    main()
  File "tools/analysis_tools/benchmark.py", line 191, in main
    args.repeat_num)
  File "tools/analysis_tools/benchmark.py", line 152, in repeat_measure_inference_speed
    is_fuse_conv_bn))
  File "tools/analysis_tools/benchmark.py", line 85, in measure_inference_speed
    model = build_detector(cfg.model, test_cfg=cfg.get('test_cfg'))
  File "/home/lwt/code/mask2former_all/mmdet/models/builder.py", line 59, in build_detector
    cfg, default_args=dict(train_cfg=train_cfg, test_cfg=test_cfg))
  File "/root/miniconda3/envs/mmdet-mask2former/lib/python3.7/site-packages/mmcv/utils/registry.py", line 215, in build
    return self.build_func(*args, **kwargs, registry=self)
  File "/root/miniconda3/envs/mmdet-mask2former/lib/python3.7/site-packages/mmcv/cnn/builder.py", line 27, in build_model_from_cfg
    return build_from_cfg(cfg, registry, default_args)
  File "/root/miniconda3/envs/mmdet-mask2former/lib/python3.7/site-packages/mmcv/utils/registry.py", line 55, in build_from_cfg
    raise type(e)(f'{obj_cls.__name__}: {e}')
TypeError: Mask2Former: __init__() got an unexpected keyword argument 'pretrained'

However， I run the test.py as below, it can work well without this error.

python tools/test.py configs/mask2former/mask2former_r50_lsj_8x2_50e_coco.py work_dirs/mask2former/iter_737500.pth --eval segm

Look forward to the reply. Thanks!

Environment

sys.platform: linux Python: 3.7.13 (default, Mar 29 2022, 02:18:16) [GCC 7.5.0] CUDA available: True GPU 0,1,2,3,4,5,6,7: Tesla V100-SXM2-32GB CUDA_HOME: /usr/local/cuda-11.4 NVCC: Cuda compilation tools, release 11.4, V11.4.152 GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 PyTorch: 1.7.1+cu101 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 v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
OpenMP 201511 (a.k.a. OpenMP 4.5)
NNPACK is enabled
CPU capability usage: AVX2
CUDA Runtime 10.1
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
CuDNN 7.6.3
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-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, 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,

TorchVision: 0.8.2+cu101 OpenCV: 4.6.0 MMCV: 1.5.0 MMCV Compiler: GCC 7.3 MMCV CUDA Compiler: 10.1 MMDetection: 2.25.0+

Additional information

No response

LiWentomng commented 2 years ago

Additional information: The script tools/analysis_tools/benchmark.py to FPS can run well on other models, like Mask R-CNN and SOLO.

LiWentomng commented 2 years ago

The tools/analysis_tools/benchmark.py need to be refined.

The above error can be resolved by

replacing

cfg.model.pretrained = None (line 64)

to

 if 'pretrained' in cfg.model:
     cfg.model.pretrained = None
 elif 'init_cfg' in cfg.model.backbone:
     cfg.model.backbone.init_cfg = None

open-mmlab / mmdetection