[Bug] Centerformer with MultiFrameDeformableDecoderRPN doesn't seems to work

[ClementLeBihan]

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• I have read the FAQ documentation but cannot get the expected help.
• The bug has not been fixed in the latest version (dev-1.x) or latest version (dev-1.0).

Task

I'm using the official example scripts/configs for the officially supported tasks/models/datasets.

Branch

main branch https://github.com/open-mmlab/mmdetection3d

Environment

sys.platform: linux
Python: 3.11.9 (main, Apr 19 2024, 16:48:06) [GCC 11.2.0]
CUDA available: True
MUSA available: False
numpy_random_seed: 2147483648
GPU 0: NVIDIA RTX A3000 Laptop GPU
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.8, V11.8.89
GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
PyTorch: 2.4.0
PyTorch compiling details: 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 v3.4.2 (Git Hash 1137e04ec0b5251ca2b4400a4fd3c667ce843d67)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - LAPACK is enabled (usually provided by MKL)
  - NNPACK is enabled
  - CPU capability usage: AVX512
  - CUDA Runtime 11.8
  - NVCC architecture flags: -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=sm_37;-gencode;arch=compute_90,code=sm_90;-gencode;arch=compute_37,code=compute_37
  - CuDNN 90.1
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=9.1.0, CXX_COMPILER=/opt/rh/devtoolset-9/root/usr/bin/c++, CXX_FLAGS= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -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 -Wno-unused-parameter -Wno-unused-function -Wno-unused-result -Wno-strict-overflow -Wno-strict-aliasing -Wno-stringop-overflow -Wsuggest-override -Wno-psabi -Wno-error=pedantic -Wno-error=old-style-cast -Wno-missing-braces -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=2.4.0, USE_CUDA=ON, USE_CUDNN=ON, USE_CUSPARSELT=1, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_GLOO=ON, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, USE_ROCM_KERNEL_ASSERT=OFF, 

TorchVision: 0.19.0
OpenCV: 4.10.0
MMEngine: 0.10.5
MMDetection: 3.3.0
MMDetection3D: 1.4.0+unknown
spconv2.0: False

Reproduces the problem - code sample

Using MultiFrameDeformableDecoderRPN in https://github.com/open-mmlab/mmdetection3d/blob/fe25f7a51d36e3702f961e198894580d83c4387b/projects/CenterFormer/configs/centerformer_voxel01_second-attn_secfpn-attn_4xb4-cyclic-20e_waymoD5-3d-3class.py

Reproduces the problem - command or script

python tools/train.py configs/easymile/ms3d/centerformer_multiframes.py

Reproduces the problem - error message

  File "/home/mmdetection3d/mmdet3d/projects/centerformer/centerformer_backbone.py", line 878, in forward
    x_up_fuse = torch.cat((x_up, x_prev_cat), dim=1) + self.time_embedding(example['times'][:, :, None].to(x_up)).reshape(x_up.shape[0], -1, 1, 1)
                                                                           ~~~~~~~^^^^^^^^^
TypeError: list indices must be integers or slices, not str

Additional information

Hi,
I wanted to try Centerformer with MultiFrameDeformableDecoderRPN with the Spatial-aware Fusion. I used it as the backbone and added LoadPointsFromMultiSweeps in the pipeline.

Unfortunately, I think things are missing. In the forward function of MultiFrameDeformableDecoderRPN, it uses example['times'], example['ind'] and example['mask'] that are empty. I can't find code in mmdetection that fill these values.

I'm trying to understand original repo, but wondering how it is suppose to work in mmdetection3D ? Maybe @JingweiZhang12 may help ?

Thank you,
Clément