[MAE] RuntimeError: The size of tensor a (1025) must match the size of tensor b (577) at non-singleton dimension 1 Exception in thread Thread-3:

[MIMIWAWA]

Checklist

1. I have searched related issues but cannot get the expected help.
   masked autoencoder customize dataset #1613
   RuntimeError: The size of tensor a (125) must match the size of tensor b (128) at non-singleton dimension 2 #80
   Use of RGB2Gray in train pipeline causes RuntimeError #1706

Describe the bug
RuntimeError: The size of tensor a (1025) must match the size of tensor b (577) at non-singleton dimension 1 Exception in thread Thread-3:

Reproduction

1. What command or script did you run?
   upernet_mae-base_fp16_512x512_160k_ade20k_ms.py

python tools/train.py configs/mae/upernet_mae-base_fp16_512x512_160k_ade20k_ms.py

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

upernet_mae-base_fp16_512x512_160k_ade20k_ms.py
        # img_scale=(2048, 512),
        img_scale=(384, 384),

4. What dataset did you use?
   custom dataset

Environment

sys.platform: linux
Python: 3.8.13 (default, Mar 28 2022, 11:38:47) [GCC 7.5.0]
CUDA available: True
GPU 0: Tesla V100-SXM2-32GB
CUDA_HOME: /usr/local/cuda
NVCC: Cuda compilation tools, release 11.7, V11.7.64
GCC: gcc (Ubuntu 9.4.0-1ubuntu1~20.04.1) 9.4.0
PyTorch: 1.8.0+cu111
PyTorch compiling details: PyTorch built with:
  - GCC 7.3
  - C++ Version: 201402
  - Intel(R) Math Kernel Library Version 2020.0.0 Product Build 20191122 for Intel(R) 64 architecture applications
  - Intel(R) MKL-DNN v1.7.0 (Git Hash 7aed236906b1f7a05c0917e5257a1af05e9ff683)
  - OpenMP 201511 (a.k.a. OpenMP 4.5)
  - NNPACK is enabled
  - CPU capability usage: AVX2
  - CUDA Runtime 11.1
  - 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_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
  - CuDNN 8.0.5
  - Magma 2.5.2
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.1, CUDNN_VERSION=8.0.5, CXX_COMPILER=/opt/rh/devtoolset-7/root/usr/bin/c++, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_KINETO -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -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 -Wno-stringop-overflow, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, TORCH_VERSION=1.8.0, 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, 

TorchVision: 0.9.0+cu111
OpenCV: 4.5.5
MMCV: 1.6.0
MMCV Compiler: GCC 9.4
MMCV CUDA Compiler: 11.7
MMSegmentation: 0.26.0+891448f

Error traceback

2022-07-15 04:30:17,403 - mmseg - INFO - Exp name: upernet_mae-base_fp16_512x512_160k_ade20k_ms.py
2022-07-15 04:30:17,403 - mmseg - INFO - Epoch [1][371/371]     lr: 9.120e-08, eta: 11:51:55, time: 2.282, data_time: 0.083, memory: 28193, decode.loss_ce: 0.3979, decode.acc_seg: 79.8963, aux.loss_ce: 0.1981, aux.acc_seg: 75.4642, loss: 0.5960
[                                                  ] 0/1073, elapsed: 0s, ETA:Traceback (most recent call last):
  File "tools/train.py", line 243, in <module>
    main()
  File "tools/train.py", line 232, in main
    train_segmentor(
  File "/mmsegmentation/mmseg/apis/train.py", line 194, in train_segmentor
    runner.run(data_loaders, cfg.workflow)
  File "/mmcv/mmcv/runner/epoch_based_runner.py", line 136, in run
    epoch_runner(data_loaders[i], **kwargs)
  File "/mmcv/mmcv/runner/epoch_based_runner.py", line 58, in train
    self.call_hook('after_train_epoch')
  File "/mmcv/mmcv/runner/base_runner.py", line 317, in call_hook
    getattr(hook, fn_name)(self)
  File "/mmcv/mmcv/runner/hooks/evaluation.py", line 271, in after_train_epoch
    self._do_evaluate(runner)
  File "/mmsegmentation/mmseg/core/evaluation/eval_hooks.py", line 51, in _do_evaluate
    results = single_gpu_test(
  File "/mmsegmentation/mmseg/apis/test.py", line 91, in single_gpu_test
    result = model(return_loss=False, **data)
  File "/opt/conda/envs/cnx38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/mmcv/mmcv/parallel/data_parallel.py", line 51, in forward
    return super().forward(*inputs, **kwargs)
  File "/opt/conda/envs/cnx38/lib/python3.8/site-packages/torch/nn/parallel/data_parallel.py", line 165, in forward
    return self.module(*inputs[0], **kwargs[0])
  File "/opt/conda/envs/cnx38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/mmcv/mmcv/runner/fp16_utils.py", line 146, in new_func
    output = old_func(*new_args, **new_kwargs)
  File "/mmsegmentation/mmseg/models/segmentors/base.py", line 110, in forward
    return self.forward_test(img, img_metas, **kwargs)
  File "/mmsegmentation/mmseg/models/segmentors/base.py", line 94, in forward_test
    return self.aug_test(imgs, img_metas, **kwargs)
  File "/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 281, in aug_test
    seg_logit = self.inference(imgs[0], img_metas[0], rescale)
  File "/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 245, in inference
    seg_logit = self.slide_inference(img, img_meta, rescale)
  File "/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 179, in slide_inference
    crop_seg_logit = self.encode_decode(crop_img, img_meta)
  File "/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 73, in encode_decode
    x = self.extract_feat(img)
  File "/mmsegmentation/mmseg/models/segmentors/encoder_decoder.py", line 65, in extract_feat
    x = self.backbone(img)
  File "/opt/conda/envs/cnx38/lib/python3.8/site-packages/torch/nn/modules/module.py", line 889, in _call_impl
    result = self.forward(*input, **kwargs)
  File "/mmsegmentation/mmseg/models/backbones/mae.py", line 246, in forward
    x = x + self.pos_embed
RuntimeError: The size of tensor a (1025) must match the size of tensor b (577) at non-singleton dimension 1
Exception in thread Thread-3:
Traceback (most recent call last):
  File "/opt/conda/envs/cnx38/lib/python3.8/threading.py", line 932, in _bootstrap_inner
    self.run()
  File "/opt/conda/envs/cnx38/lib/python3.8/threading.py", line 870, in run
    self._target(*self._args, **self._kwargs)
  File "/opt/conda/envs/cnx38/lib/python3.8/site-packages/torch/utils/data/_utils/pin_memory.py", line 25, in _pin_memory_loop
    r = in_queue.get(timeout=MP_STATUS_CHECK_INTERVAL)
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/queues.py", line 116, in get
    return _ForkingPickler.loads(res)
  File "/opt/conda/envs/cnx38/lib/python3.8/site-packages/torch/multiprocessing/reductions.py", line 282, in rebuild_storage_fd
    fd = df.detach()
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/resource_sharer.py", line 57, in detach
    with _resource_sharer.get_connection(self._id) as conn:
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/resource_sharer.py", line 87, in get_connection
    c = Client(address, authkey=process.current_process().authkey)
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/connection.py", line 508, in Client
    answer_challenge(c, authkey)
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/connection.py", line 752, in answer_challenge
    message = connection.recv_bytes(256)         # reject large message
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/connection.py", line 216, in recv_bytes
    buf = self._recv_bytes(maxlength)
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/connection.py", line 414, in _recv_bytes
    buf = self._recv(4)
  File "/opt/conda/envs/cnx38/lib/python3.8/multiprocessing/connection.py", line 379, in _recv
    chunk = read(handle, remaining)
ConnectionResetError: [Errno 104] Connection reset by peer

[xiexinch]

Hi @MIMIWAWA,
Sorry for the late reply. I'm trying to reproduce this error, if possible, could you provide more details about your custom dataset and config file?

[MIMIWAWA]

Sorry for the late reply.

After receiving permission from the committee, I can reply to the image formats as follows:
The image patch is 24 bits depth with 3-channels of the dimension of 384x384 in TIF format.
The mask is 8 bits depth with 3-channels of the dimension of 384x384 in PNG format.

Any help is appreciated.