[Bug] ConvNeXtV2 预训练权重加载键值对不匹配

[caixiaoshun]

Branch

main branch (mmpretrain version)

Describe the bug

描述

在使用官网提供的 ConvNeXtV2 预训练权重时，加载过程中出现键值对不匹配的问题。这似乎是因为下载的权重文件格式和项目的加载方式不完全一致。
在加载权重时，使用了以下代码：

model = dict(
    backbone=dict(
        frozen_stages=4,
        init_cfg=dict(
            type="Pretrained",
            checkpoint="checkpoints/converted_convnext-v2-large.pth",
            prefix="backbone",
        ),
    )
)

加载时出现键值对不匹配，导致无法正常加载权重。

解决方法

为了使下载的权重文件格式符合项目的加载要求，可以对权重进行后处理，提取其中的 'state_dict' 字段。具体代码如下：

import torch

# 加载权重文件并提取 state_dict
weight = torch.load("checkpoints/convnext-v2-large.pth", map_location="cpu")['state_dict']

# 打印权重中的键值对
print(weight.keys())

# 将处理后的权重加载到模型
torch.save(weight ,"save_path.pth")

通过上述处理，将权重文件中的 'state_dict' 提取出来，确保模型加载时的键值对匹配，解决了加载失败的问题。

Environment

System environment:
    sys.platform: linux
    Python: 3.8.20 (default, Oct  3 2024, 15:24:27) [GCC 11.2.0]
    CUDA available: True
    MUSA available: False
    numpy_random_seed: 533839887
    GPU 0,1: NVIDIA GeForce RTX 3090
    CUDA_HOME: /usr/local/cuda
    NVCC: Cuda compilation tools, release 12.3, V12.3.107
    GCC: gcc (Ubuntu 11.4.0-1ubuntu1~22.04) 11.4.0
    PyTorch: 2.0.1
    PyTorch compiling details: PyTorch built with:
  - GCC 9.3
  - C++ Version: 201703
  - Intel(R) oneAPI Math Kernel Library Version 2023.1-Product Build 20230303 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 11.8
  - 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_90,code=sm_90;-gencode;arch=compute_37,code=compute_37
  - CuDNN 8.7
  - Magma 2.6.1
  - Build settings: BLAS_INFO=mkl, BUILD_TYPE=Release, CUDA_VERSION=11.8, CUDNN_VERSION=8.7.0, 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=ON, USE_NNPACK=ON, USE_OPENMP=ON, USE_ROCM=OFF, 

    TorchVision: 0.15.2
    OpenCV: 4.10.0
    MMEngine: 0.10.5

Runtime environment:
    cudnn_benchmark: True
    mp_cfg: {'mp_start_method': 'fork', 'opencv_num_threads': 0}
    dist_cfg: {'backend': 'nccl'}
    seed: 533839887
    deterministic: False
    Distributed launcher: pytorch
    Distributed training: True
    GPU number: 2

Other information

No response