Error encountered when using swin-transformer to inference

[ktasha45]

ERROR : CascadeRCNN: SwinTransformer: init() got an unexpected keyword argument 'embed_dim'

• https://colab.research.google.com/drive/1LsmGgR7ZAcc_1cu1UMdN1tA-a6eWjzho#scrollTo=rltO1wsMaYDh
• The one above is the colab link, and if you make a copy of it and run it the same way, you will probably get the same error I got before.
  There seems to be something wrong with the config file.
  I used the mask rcnn in the same way and it worked well. So I don't think it's a version problem.

Environment

• It is colab

No CUDA runtime is found, using CUDA_HOME='/usr/local/cuda' fatal: not a git repository (or any of the parent directories): .git sys.platform: linux Python: 3.7.13 (default, Apr 24 2022, 01:04:09) [GCC 7.5.0] CUDA available: False GCC: x86_64-linux-gnu-gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.12.0+cu113 PyTorch compiling details: PyTorch built with:

• GCC 9.3
• 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 v2.6.0 (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
• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, 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+cu113 OpenCV: 4.6.0 MMCV: 1.6.1 MMCV Compiler: GCC 9.3 MMCV CUDA Compiler: 11.3 MMDetection: 2.25.1+

Error traceback

TypeError: __init__() got an unexpected keyword argument 'embed_dim'

During handling of the above exception, another exception occurred:

The rest of the contents were omitted because they were too long. You can check it in the colab link.

[ktasha45]

• !pip install -v -e .

I tried to install mmdet with this, but the same error was printed.

[ktasha45]

https://velog.io/@khjgmdwns/SwinTransformerSwin-Object-Detection-%EA%B0%9C%EB%B0%9C%ED%99%98%EA%B2%BD-%EC%84%A4%EC%A0%95CUDA-11.0

I referred to 3. in this blog and solved the problem.