Loading checkpoint for ViTDet raises another shape mismatch warning

[treeman2000]

I installed Detectron2 and attempted to use the ViTDet base model from the documentation provided here: https://github.com/facebookresearch/detectron2/tree/main/projects/ViTDet

Instructions To Reproduce the Issue:

1. I have made no changes to the configs, or any other files.

2. What exact command you run:

python tools/lazyconfig_train_net.py --config-file projects/ViTDet/configs/COCO/mask_rcnn_vitdet_b_100ep.py --eval-only train.init_checkpoint=model_final_5251c5.pkl

3. Full logs or other relevant observations:

[08/25 10:58:42 fvcore.common.checkpoint]: Reading a file from 'Detectron2 ViTDet Model Zoo'
WARNING [08/25 10:58:42 fvcore.common.checkpoint]: Skip loading parameter 'roi_heads.box_predictor.cls_score.weight' to the model due to incompatible shapes: (1204, 1024) in the checkpoint but (81, 1024) in the model! You might want to double check if this is expected.
WARNING [08/25 10:58:42 fvcore.common.checkpoint]: Skip loading parameter 'roi_heads.box_predictor.cls_score.bias' to the model due to incompatible shapes: (1204,) in the checkpoint but (81,) in the model! You might want to double check if this is expected.
WARNING [08/25 10:58:42 fvcore.common.checkpoint]: Skip loading parameter 'roi_heads.box_predictor.bbox_pred.weight' to the model due to incompatible shapes: (4812, 1024) in the checkpoint but (320, 1024) in the model! You might want to double check if this is expected.
WARNING [08/25 10:58:42 fvcore.common.checkpoint]: Skip loading parameter 'roi_heads.box_predictor.bbox_pred.bias' to the model due to incompatible shapes: (4812,) in the checkpoint but (320,) in the model! You might want to double check if this is expected.
WARNING [08/25 10:58:42 fvcore.common.checkpoint]: Skip loading parameter 'roi_heads.mask_head.predictor.weight' to the model due to incompatible shapes: (1203, 256, 1, 1) in the checkpoint but (80, 256, 1, 1) in the model! You might want to double check if this is expected.
WARNING [08/25 10:58:42 fvcore.common.checkpoint]: Skip loading parameter 'roi_heads.mask_head.predictor.bias' to the model due to incompatible shapes: (1203,) in the checkpoint but (80,) in the model! You might want to double check if this is expected.
WARNING [08/25 10:58:42 fvcore.common.checkpoint]: Some model parameters or buffers are not found in the checkpoint:
roi_heads.box_predictor.bbox_pred.{bias, weight}
roi_heads.box_predictor.cls_score.{bias, weight}
roi_heads.mask_head.predictor.{bias, weight}

Expected behavior:

all weights are successfully matched

Environment:

----------------------  -----------------------------------------------------------------------------
sys.platform            linux
Python                  3.11.3 (main, Apr 19 2023, 23:54:32) [GCC 11.2.0]
numpy                   1.24.3
detectron2              0.6 @/vhome/code/detectron2/detectron2
Compiler                GCC 11.4
CUDA compiler           not available
DETECTRON2_ENV_MODULE   <not set>
PyTorch                 2.0.1 @/vhome/anaconda3/lib/python3.11/site-packages/torch
PyTorch debug build     False
GPU available           Yes
GPU 0                   NVIDIA GeForce RTX 3090 (arch=8.6)
Driver version          535.54.03
CUDA_HOME               /share/apps/cuda/12.2
Pillow                  9.4.0
torchvision             0.15.2 @/vhome/anaconda3/lib/python3.11/site-packages/torchvision
torchvision arch flags  3.5, 5.0, 6.0, 7.0, 7.5, 8.0, 8.6
fvcore                  0.1.5.post20221221
iopath                  0.1.9
cv2                     4.8.0
----------------------  -----------------------------------------------------------------------------
PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.8
  - 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_90,code=sm_90;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.7
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -O2 -fPIC -Wall -Wextra -Werror=return-type -Werror=non-virtual-dtor -Werror=bool-operation -Wnarrowing -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wunused-local-typedefs -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -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_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.1, USE_CUDA=ON, USE_CUDNN=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, USE_ROCM=OFF,

Did some modifications in common configuration affect the configuration of ViTDet？