RuntimeError: Expected object of scalar type Long but got scalar type Int for argument #2 'target' in call to _thnn_nll_loss2d_forward

[JackieWang9811]

Thanks for your error report and we appreciate it a lot.

Checklist

1. I have searched related issues but cannot get the expected help.
2. The bug has not been fixed in the latest version.

Describe the bug
RuntimeError: Expected object of scalar type Long but got scalar type Int for argument #2 'target' in call to _thnn_nll_loss2d_forward

Reproduction

1. What command or script did you run?

python tools/train.py configs/pointnet2/pointnet2_msg_16x2_cosine_80e_s3dis_seg-3d-13class.py

2. i modified the code in mmdet3d/datasets/pipelines/loading.py line 521 seg_3d_dtype=np.int64 to seg_3d_dtype=np.int32 because of the error: IndexError: index 12884901891 is out of bounds for axis 0 with size 14, and also i modified the code in tools/create_data.py line 211 mask = np.fromfile(mask, dtype=np.int64) to mask = np.fromfile(mask, dtype=np.int32) because of the similar error like above.

3. I use the S3DIS as the dataset of training model

Environment

fatal: not a git repository (or any of the parent directories): .git
sys.platform: win32
Python: 3.7.12 | packaged by conda-forge | (default, Oct 26 2021, 05:35:01) [MSC v.1916 64 bit (AMD64)]
CUDA available: True
GPU 0: NVIDIA GeForce RTX 3060 Laptop GPU
CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.1
NVCC: Cuda compilation tools, release 11.1, V11.1.74
MSVC: 用于 x64 的 Microsoft (R) C/C++ 优化编译器 19.29.30145 版
GCC: n/a
PyTorch: 1.7.1
PyTorch compiling details: PyTorch built with:

• C++ Version: 199711
• MSVC 192729112
• Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191125 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
• OpenMP 2019
• CPU capability usage: AVX2
• CUDA Runtime 11.0
• 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_37,code=compute_37
• CuDNN 8.0.4
• Magma 2.5.4
• Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -openmp:experimental -DNDEBUG -DUSE_FBGEMM -DUSE_VULKAN_WRAPPER, 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=OFF, USE_NNPACK=OFF, USE_OPENMP=ON,

TorchVision: 0.8.2
OpenCV: 4.6.0
MMCV: 1.5.3
MMCV Compiler: MSVC 192930145
MMCV CUDA Compiler: 11.1
MMDetection: 2.25.0
MMSegmentation: 0.25.0
MMDetection3D: 1.0.0rc2+
spconv2.0: False

Error traceback
If applicable, paste the error trackback here.

Traceback (most recent call last):
  File "D:/mmdetection3d-master/tools/train.py", line 263, in <module>
    main()
  File "D:/mmdetection3d-master/tools/train.py", line 259, in main
    meta=meta)
  File "D:\mmdetection3d-master\mmdet3d\apis\train.py", line 342, in train_model
    meta=meta)
  File "D:\mmdetection3d-master\mmdet3d\apis\train.py", line 177, in train_segmentor
    runner.run(data_loaders, cfg.workflow)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmcv\runner\epoch_based_runner.py", line 130, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmcv\runner\epoch_based_runner.py", line 51, in train
    self.run_iter(data_batch, train_mode=True, **kwargs)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmcv\runner\epoch_based_runner.py", line 30, in run_iter
    **kwargs)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmcv\parallel\data_parallel.py", line 75, in train_step
    return self.module.train_step(*inputs[0], **kwargs[0])
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmseg\models\segmentors\base.py", line 138, in train_step
    losses = self(**data_batch)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmcv\runner\fp16_utils.py", line 116, in new_func
    return old_func(*args, **kwargs)
  File "D:\mmdetection3d-master\mmdet3d\models\segmentors\base.py", line 67, in forward
    return self.forward_train(**kwargs)
  File "D:\mmdetection3d-master\mmdet3d\models\segmentors\encoder_decoder.py", line 168, in forward_train
    pts_semantic_mask_cat)
  File "D:\mmdetection3d-master\mmdet3d\models\segmentors\encoder_decoder.py", line 98, in _decode_head_forward_train
    self.train_cfg)
  File "D:\mmdetection3d-master\mmdet3d\models\decode_heads\decode_head.py", line 87, in forward_train
    losses = self.losses(seg_logits, pts_semantic_mask)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmcv\runner\fp16_utils.py", line 205, in new_func
    return old_func(*args, **kwargs)
  File "D:\mmdetection3d-master\mmdet3d\models\decode_heads\decode_head.py", line 122, in losses
    seg_logit, seg_label, ignore_index=self.ignore_index)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\torch\nn\modules\module.py", line 727, in _call_impl
    result = self.forward(*input, **kwargs)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmseg\models\losses\cross_entropy_loss.py", line 280, in forward
    **kwargs)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\mmseg\models\losses\cross_entropy_loss.py", line 50, in cross_entropy
    ignore_index=ignore_index)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\torch\nn\functional.py", line 2468, in cross_entropy
    return nll_loss(log_softmax(input, 1), target, weight, None, ignore_index, None, reduction)
  File "E:\Anaconda\envs\mmlab\lib\site-packages\torch\nn\functional.py", line 2292, in nll_loss
    input, target, weight, reduction_enum, ignore_index)
RuntimeError: Expected object of scalar type Long but got scalar type Int for argument #2 'target' in call to _thnn_nll_loss2d_forward

Process finished with exit code 1

Bug 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!

[phoenix9668]

I have a similar problem
RuntimeError: expected scalar type Long but found Int
when I run
python tools\train.py configs\pointnet2\pointnet2_msg_16x2_cosine_80e_s3dis_seg-3d-13class.py