[Bug] RuntimeError: Calculated padded input size per channel: (1 x 70). Kernel size: (2 x 2). Kernel size can't be greater than actual input size

[fat-921]

Prerequisite

• I have searched Issues and Discussions but cannot get the expected help.
• The bug has not been fixed in the latest version (0.x) or latest version (1.x).

Task

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

Branch

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

Environment

sys.platform: win32
Python: 3.8.13 (default, Mar 28 2022, 06:59:08) [MSC v.1916 64 bit (AMD64)]
CUDA available: True
numpy_random_seed: 2147483648
GPU 0: NVIDIA GeForce RTX 3060 Ti
CUDA_HOME: C:\Program Files\NVIDIA GPU Computing Toolkit\CUDA\v11.3
NVCC: Cuda compilation tools, release 11.3, V11.3.58
MSVC: 用于 x64 的 Microsoft (R) C/C++ 优化编译器 19.29.30146 版
GCC: n/a
PyTorch: 1.11.0+cu113
PyTorch compiling details: PyTorch built with:

• C++ Version: 199711
• MSVC 192829337
• Intel(R) Math Kernel Library Version 2020.0.2 Product Build 20200624 for Intel(R) 64 ar
  chitecture applications
• Intel(R) MKL-DNN v2.5.2 (Git Hash a9302535553c73243c632ad3c4c80beec3d19a1e)
• OpenMP 2019
• LAPACK is enabled (usually provided by MKL)
• CPU capability usage: AVX2
• CUDA Runtime 11.3
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,c
  ode=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,cod
  e=sm_80;-gencode;arch=compute_86,code=sm_86;-gencode;arch=compute_37,code=compute_37
• CuDNN 8.2
• Magma 2.5.4
• Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.3, CUDNN_VERSION=8.2
  .0, CXX_COMPILER=C:/actions-runner/_work/pytorch/pytorch/builder/windows/tmp_bin/sccache-cl
  .exe, CXX_FLAGS=/DWIN32 /D_WINDOWS /GR /EHsc /w /bigobj -DUSE_PTHREADPOOL -openmp:experimen
  tal -IC:/actions-runner/_work/pytorch/pytorch/builder/windows/mkl/include -DNDEBUG -DUSE_KI
  NETO -DLIBKINETO_NOCUPTI -DUSE_FBGEMM -DUSE_XNNPACK -DSYMBOLICATE_MOBILE_DEBUG_HANDLE -DEDG
  E_PROFILER_USE_KINETO, LAPACK_INFO=mkl, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512
  =1, TORCH_VERSION=1.11.0, USE_CUDA=ON, USE_CUDNN=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, U
  SE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=OFF, USE_MPI=OFF, USE_NCCL=OFF, USE_NNPACK=OFF, USE_OPE
  NMP=ON, USE_ROCM=OFF,

TorchVision: 0.12.0+cu113
OpenCV: 4.6.0
MMEngine: 0.7.1
MMOCR: 1.0.0+

Reproduces the problem - code sample

when i run python tools/train.py configs/textrecog/crnn/crnn_mini-vgg_5e_toy.py with my self-datasets,
I set train_dataloader = dict(batch_size=4, num_workers=2) and val_dataloader = dict(batch_size=4,num_workers=2) ，
or I set batch_size <= 16，similar problems occur；but set batch_size >16 or more，it becomes normal.
How is it that I want to train with a small batch size ???

Reproduces the problem - command or script

python tools/train.py configs/textrecog/crnn/crnn_mini-vgg_5e_toy.py
train_dataloader = dict(batch_size=4, num_workers=2) and val_dataloader = dict(batch_size=4,num_workers=2)

Reproduces the problem - error message

Traceback (most recent call last):
File "D:\software\Anaconda3\envs\openmmlab\lib\contextlib.py", line 131, in exit
self.gen.throw(type, value, traceback)
File "D:\mmengine\optim\optimizer\optimizer_wrapper.py", line 351, in optim_context
yield
File "D:\mmengine\model\base_model\base_model.py", line 114, in train_step
losses = self._run_forward(data, mode='loss') # type: ignore
File "D:\mmengine\model\base_model\base_model.py", line 326, in _run_forward
results = self(**data, mode=mode)
File "D:\software\Anaconda3\envs\openmmlab\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "D:\mmocr\models\textrecog\recognizers\base.py", line 88, in forward
return self.loss(inputs, data_samples, **kwargs)
File "D:\software\Anaconda3\envs\openmmlab\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "D:\software\Anaconda3\envs\openmmlab\lib\site-packages\torch\nn\modules\container.py", line 141, in forward
input = module(input)
File "D:\software\Anaconda3\envs\openmmlab\lib\site-packages\torch\nn\modules\module.py", line 1110, in _call_impl
return forward_call(*input, **kwargs)
File "D:\software\Anaconda3\envs\openmmlab\lib\site-packages\torch\nn\modules\conv.py", line 447, in forward
return self._conv_forward(input, self.weight, self.bias)
File "D:\software\Anaconda3\envs\openmmlab\lib\site-packages\torch\nn\modules\conv.py", line 443, in _conv_forward
return F.conv2d(input, weight, bias, self.stride,
RuntimeError: Calculated padded input size per channel: (1 x 70). Kernel size: (2 x 2). Kernel size can't be greater than actual input size

Additional information

How to solve this problem?? I want to use a small batch_size...