RuntimeError: only batches of spatial targets supported (3D tensors) but got targets of size: : [2, 256, 256, 3]

[ShubhamAbhayDeshpande]

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 I am trying to use different segmentation models to segment the freiburg forest dataset. The link to the dataset is given below.

http://deepscene.cs.uni-freiburg.de/segment_random/CITYSCAPES_RGB?dataset=freiburgforest&model=FOREST_RGB

I have made the required config files for mmsegmentation according to the documentation in the link below.

https://github.com/open-mmlab/mmsegmentation/blob/0.x/docs/en/tutorials/config.md

I am getting the following error in the code. And I cannot backtrack this error to its source. Can someone please tell me exactly where the error is originating and how to fix it?

Reproduction

Command/ Script that I ran

  sh tools/dist_train.sh configs/deeplabv3/deeplab_r50-d8_4xb2-40k_freiburgforest-800x400.py 2

Environment

sys.platform: linux
Python: 3.8.16 (default, Mar  2 2023, 03:21:46) [GCC 11.2.0]
CUDA available: True
numpy_random_seed: 2147483648
GPU 0,1,2,3: NVIDIA GeForce RTX 2080 Ti
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.7, V11.7.99
GCC: gcc (Ubuntu 11.3.0-1ubuntu1~22.04.1) 11.3.0
PyTorch: 1.13.0
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 11.7
  - 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 8.5
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.7, CUDNN_VERSION=8.5.0, 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 -Werror=non-virtual-dtor -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_VERSION=1.13.0, 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, 

TorchVision: 0.14.0
OpenCV: 4.7.0
MMEngine: 0.7.3
MMSegmentation: 1.0.0+e64548f

Error traceback

Traceback (most recent call last):
  File "tools/train.py", line 109, in <module>
    main()
  File "tools/train.py", line 105, in main
    runner.train()
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1733, in train
    model = self.train_loop.run()  # type: ignore
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 278, in run
    self.run_iter(data_batch)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 301, in run_iter
    outputs = self.runner.model.train_step(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/model/wrappers/distributed.py", line 121, in train_step
    losses = self._run_forward(data, mode='loss')
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/model/wrappers/distributed.py", line 161, in _run_forward
    results = self(**data, mode=mode)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 1040, in forward
Traceback (most recent call last):
  File "tools/train.py", line 109, in <module>
    output = self._run_ddp_forward(*inputs, **kwargs)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 1000, in _run_ddp_forward
    return module_to_run(*inputs[0], **kwargs[0])
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/segmentors/base.py", line 94, in forward
    main()
  File "tools/train.py", line 105, in main
    return self.loss(inputs, data_samples)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 177, in loss
    runner.train()
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1733, in train
    loss_decode = self._decode_head_forward_train(x, data_samples)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 138, in _decode_head_forward_train
    loss_decode = self.decode_head.loss(inputs, data_samples,
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/decode_heads/decode_head.py", line 262, in loss
    losses = self.loss_by_feat(seg_logits, batch_data_samples)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/decode_heads/decode_head.py", line 324, in loss_by_feat
    loss[loss_decode.loss_name] = loss_decode(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    model = self.train_loop.run()  # type: ignore
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 278, in run
    self.run_iter(data_batch)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/runner/loops.py", line 301, in run_iter
    outputs = self.runner.model.train_step(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/model/wrappers/distributed.py", line 121, in train_step
    return forward_call(*input, **kwargs)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/losses/cross_entropy_loss.py", line 271, in forward
    losses = self._run_forward(data, mode='loss')
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/mmengine/model/wrappers/distributed.py", line 161, in _run_forward
    loss_cls = self.loss_weight * self.cls_criterion(
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/losses/cross_entropy_loss.py", line 45, in cross_entropy
    loss = F.cross_entropy(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/functional.py", line 3026, in cross_entropy
    results = self(**data, mode=mode)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 1040, in forward
    output = self._run_ddp_forward(*inputs, **kwargs)
      File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/parallel/distributed.py", line 1000, in _run_ddp_forward
return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: only batches of spatial targets supported (3D tensors) but got targets of size: : [2, 256, 256, 3]
    return module_to_run(*inputs[0], **kwargs[0])
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/segmentors/base.py", line 94, in forward
    return self.loss(inputs, data_samples)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 177, in loss
    loss_decode = self._decode_head_forward_train(x, data_samples)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 138, in _decode_head_forward_train
    loss_decode = self.decode_head.loss(inputs, data_samples,
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/decode_heads/decode_head.py", line 262, in loss
    losses = self.loss_by_feat(seg_logits, batch_data_samples)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/decode_heads/decode_head.py", line 324, in loss_by_feat
    loss[loss_decode.loss_name] = loss_decode(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1190, in _call_impl
    return forward_call(*input, **kwargs)
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/losses/cross_entropy_loss.py", line 271, in forward
    loss_cls = self.loss_weight * self.cls_criterion(
  File "/home/deshpand/Thesis/semantic_segmentation_network/mmseg_new/mmsegmentation/mmseg/models/losses/cross_entropy_loss.py", line 45, in cross_entropy
    loss = F.cross_entropy(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/nn/functional.py", line 3026, in cross_entropy
    return torch._C._nn.cross_entropy_loss(input, target, weight, _Reduction.get_enum(reduction), ignore_index, label_smoothing)
RuntimeError: only batches of spatial targets supported (3D tensors) but got targets of size: : [2, 256, 256, 3]
ERROR:torch.distributed.elastic.multiprocessing.api:failed (exitcode: 1) local_rank: 0 (pid: 1128219) of binary: /home/deshpand/anaconda3/envs/openmmlab/bin/python
Traceback (most recent call last):
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/distributed/launch.py", line 195, in <module>
    main()
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/distributed/launch.py", line 191, in main
    launch(args)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/distributed/launch.py", line 176, in launch
    run(args)
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/distributed/run.py", line 753, in run
    elastic_launch(
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 132, in __call__
    return launch_agent(self._config, self._entrypoint, list(args))
  File "/home/deshpand/anaconda3/envs/openmmlab/lib/python3.8/site-packages/torch/distributed/launcher/api.py", line 246, in launch_agent
    raise ChildFailedError(
torch.distributed.elastic.multiprocessing.errors.ChildFailedError: 
============================================================
tools/train.py FAILED
------------------------------------------------------------
Failures:
[1]:
  time      : 2023-05-29_10:18:58
  host      : neptun.informatik.uni-kl.de
  rank      : 1 (local_rank: 1)
  exitcode  : 1 (pid: 1128220)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html
------------------------------------------------------------
Root Cause (first observed failure):
[0]:
  time      : 2023-05-29_10:18:58
  host      : neptun.informatik.uni-kl.de
  rank      : 0 (local_rank: 0)
  exitcode  : 1 (pid: 1128219)
  error_file: <N/A>
  traceback : To enable traceback see: https://pytorch.org/docs/stable/elastic/errors.html

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!

[LiJiahang617]

you may forget to add data_preprocessor in your model. I met this issue, too. If it is not get solved, maybe your label don't load appropriately. I make change on my label, it should have only one channel instead of three.

[ShubhamAbhayDeshpande]

@LiJiahang617 Thank you for the suggestion. I am not getting this error after converting the segmentation masks to gray scale images.

[ShubhamAbhayDeshpande]

Closing this issue with above comment.

[lijoe123]

hello, i got the same problem when i train the model, could you tell me how to fix the problem. And my data is: the picture: the label: 0b) thank you so much!!!!

[JonyJiang123]

我也遇到了这个问题 我的标签是0~10像素值的灰度图

[thkelper]

@LiJiahang617 Thank you for the suggestion. I am not getting this error after converting the segmentation masks to gray scale images.

can I ask how to modify the configs to convert the segmentation masks to gray scale images?

[LiJiahang617]

in the resource code，see transform.py

---Original--- From: "kelper @.> Date: Sat, Jan 13, 2024 21:12 PM To: @.>; Cc: @.**@.>; Subject: Re: [open-mmlab/mmsegmentation] RuntimeError: only batches of spatialtargets supported (3D tensors) but got targets of size: : [2, 256, 256, 3](Issue #3055)

@LiJiahang617 Thank you for the suggestion. I am not getting this error after converting the segmentation masks to gray scale images.

can I ask how to modify the configs to convert the segmentation masks to gray scale images?

— Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you were mentioned.Message ID: @.***>