mmdetection Problems of AMP Training about Co-DETR Reimplement

Notice

There are several common situations in the reimplementation issues as below

Reimplement a model in the model zoo using the provided configs

Checklist

I have searched related issues but cannot get the expected help.

Describe the issue

Excuese me ,does CO-DETR support AMP training? When I use AMP reimplement Co-DETR, meet the problem " RuntimeError: Index put requires the source and destination dtypes match, got Half for the destination and Float for the source". After I add a type conversion. I meet the other problem "matched_row_inds, matched_col_inds = linear_sum_assignment(cost) ValueError: matrix contains invalid numeric entries" .

Reproduction

What command or script did you run?

bash ./tools/dist_train.sh 'mmdetection/projects/CO-DETR/configs/codino/co_dino_5scale_r50_lsj_8xb2_1x_coco.py' 4 --work-dir 'mmdetection/outputs/codetr_5scale_r50_4xb4_12e_coco_results' --amp --auto-scale-lr --launcher 'pytorch'

What config dir you run?

mmdetection/projects/CO-DETR/configs/codino/co_dino_5scale_r50_lsj_8xb2_1x_coco.py

Did you make any modifications on the code or config? Did you understand what you have modified?

No

What dataset did you use?

COCO

Environment

Please run python mmdet/utils/collect_env.py to collect necessary environment information and paste it here. sys.platform: linux Python: 3.8.18 (default, Sep 11 2023, 13:40:15) [GCC 11.2.0] CUDA available: True numpy_random_seed: 2147483648 GPU 0,1,2,3: NVIDIA GeForce RTX 3090 CUDA_HOME: /usr/local/cuda NVCC: Cuda compilation tools, release 11.4, V11.4.48 GCC: gcc (Ubuntu 7.5.0-3ubuntu1~18.04) 7.5.0 PyTorch: 1.12.1 PyTorch compiling details: PyTorch built with:

GCC 9.3
C++ Version: 201402
Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 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 11.3
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 2.5.2
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= -fabi-version=11 -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=1.12.1, 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: 0.13.1 OpenCV: 4.8.1 MMEngine: 0.10.1 MMDetection: 3.2.0+fe3f809 3. You may add addition that may be helpful for locating the problem, such as

How you installed PyTorch [e.g., pip, conda, source] conda
Other environment variables that may be related (such as $PATH, $LD_LIBRARY_PATH, $PYTHONPATH, etc.)

Results

If applicable, paste the related results here, e.g., what you expect and what you get.

A placeholder for results comparison

Issue fix

If you have already identified the reason, you can provide the information here. If you are willing to create a PR to fix it, please also leave a comment here and that would be much appreciated!

Jan 22 '24 14:01 ysysys666

I'm also having trouble encountering the same Issue.

Jan 26 '24 14:01 Kobamiyannnn

Similar problems happen when use AmpOptimizer in DETR:

  File "/home/louis/miniconda3/envs/mmengine/lib/python3.8/site-packages/mmdet/models/dense_heads/detr_head.py", line 437, in _get_targets_single
    bbox_targets[pos_inds] = pos_gt_bboxes_targets
RuntimeError: Index put requires the source and destination dtypes match, got Half for the destination and Float for the source.