[Bug] cyclegan:UnboundLocalError: local variable 'init_info' referenced before assignment

[xvjiawen]

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 (main) or latest version (0.x).

Task

I have modified the scripts/configs, or I'm working on my own tasks/models/datasets.

Branch

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

Environment

System environment:
sys.platform: linux
Python: 3.8.17 (default, Jul 5 2023, 21:04:15) [GCC 11.2.0]
CUDA available: True
numpy_random_seed: 2022
GPU 0,1,2,3,4,5,6,7,8,9: NVIDIA GeForce RTX 2080 Ti
CUDA_HOME: /usr/local/cuda-11.7
NVCC: Cuda compilation tools, release 11.7, V11.7.99
GCC: gcc (Ubuntu 11.3.0-1ubuntu1~22.04.1) 11.3.0
PyTorch: 2.0.1+cu117
PyTorch compiling details: PyTorch built with:

• GCC 9.3

• C++ Version: 201703

• Intel(R) oneAPI Math Kernel Library Version 2022.2-Product Build 20220804 for Intel(R) 64 architecture applications

• Intel(R) MKL-DNN v2.7.3 (Git Hash 6dbeffbae1f23cbbeae17adb7b5b13f1f37c080e)

• 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_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 8.5

• 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= -D_GLIBCXX_USE_CXX11_ABI=0 -fabi-version=11 -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -DNDEBUG -DUSE_KINETO -DLIBKINETO_NOROCTRACER -DUSE_FBGEMM -DUSE_QNNPACK -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 -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_DISABLE_GPU_ASSERTS=ON, TORCH_VERSION=2.0.1, 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=1, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF,

  TorchVision: 0.15.2+cu117
  OpenCV: 4.8.1
  MMEngine: 0.8.4

Runtime environment:
cudnn_benchmark: True
mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
dist_cfg: {'backend': 'nccl'}
seed: 2022
diff_rank_seed: True
Distributed launcher: none
Distributed training: False
GPU number: 1

Reproduces the problem - code sample

def init_func(m):
    """Initialization function.

    Args:
        m (nn.Module): Module to be initialized.
    """
    classname = m.__class__.__name__
    if hasattr(m, 'weight') and (classname.find('Conv') != -1
                                 or classname.find('Linear') != -1):
        if init_type == 'normal':
            normal_init(m, 0.0, init_gain)
        elif init_type == 'xavier':
            xavier_init(m, gain=init_gain, distribution='normal')
        elif init_type == 'kaiming':
            kaiming_init(
                m,
                a=0,
                mode='fan_in',
                nonlinearity='leaky_relu',
                distribution='normal')
        elif init_type == 'orthogonal':
            init.orthogonal_(m.weight, gain=init_gain)
            init.constant_(m.bias.data, 0.0)
        else:
            raise NotImplementedError(
                f"Initialization method '{init_type}' is not implemented")
        init_info = (f'Initialize {m.__class__.__name__} by \'init_type\' '
                     f'{init_type}.')
    elif classname.find('BatchNorm2d') != -1:
        # BatchNorm Layer's weight is not a matrix;
        # only normal distribution applies.
        normal_init(m, 1.0, init_gain)
        init_info = (f'{m.__class__.__name__} is BatchNorm2d, initialize '
                     'by Norm initialization with mean=1, '
                     f'std={init_gain}')

    if hasattr(m, '_params_init_info'):
        update_init_info(module, init_info)

module.apply(init_func)

Reproduces the problem - command or script

./tools/dist_train.sh ./configs/cyclegan/cyclegan_lsgan-id0-resnet-in_1xb1-270kiters_hk2flir.py 8 --work-dir ./work_dirs/demo

Reproduces the problem - error message

Traceback (most recent call last):
File "/data/xjw/share/projects/mmagic/tools/train.py", line 114, in
main()
File "/data/xjw/share/projects/mmagic/tools/train.py", line 107, in main
runner.train()
File "/root/miniconda3/lib/python3.8/site-packages/mmengine/runner/runner.py", line 1723, in train
self._init_model_weights()
File "/root/miniconda3/lib/python3.8/site-packages/mmengine/runner/runner.py", line 906, in _init_model_weights
model.init_weights()
File "/data/xjw/share/projects/mmagic/mmagic/models/base_models/base_translation_model.py", line 110, in init_weights
gen.init_weights()
File "/data/xjw/share/projects/mmagic/mmagic/models/editors/cyclegan/cyclegan_generator.py", line 139, in init_weights
generation_init_weights(
File "/data/xjw/share/projects/mmagic/mmagic/models/utils/model_utils.py", line 146, in generation_init_weights
module.apply(init_func)
File "/root/miniconda3/lib/python3.8/site-packages/torch/nn/modules/module.py", line 885, in apply
fn(self)
File "/data/xjw/share/projects/mmagic/mmagic/models/utils/model_utils.py", line 144, in init_func
update_init_info(module, init_info)
UnboundLocalError: local variable 'init_info' referenced before assignment

Additional information

I ONLY modify the dataset which the format is the same as hourse2zerba

[zhangliukun]

I have the same errors, it seems like the "if elif" not run leading to the problem.

[fsbarros98]

any updates on this? this seems to work with MMGeneration repository...