Skip to content

layer_dict的对应关系 #30

Description

@as754770178
layer_dict = {'ConvNdBackward': 'Convolution',
              'ThresholdBackward': 'ReLU',
              'MaxPool2dBackward': 'Pooling',
              'AvgPool2dBackward': 'Pooling',
              'DropoutBackward': 'Dropout',
              'AddmmBackward': 'InnerProduct',
              'BatchNormBackward': 'BatchNorm',
              'AddBackward': 'Eltwise',
              'ViewBackward': 'Reshape',
              'ConcatBackward': 'Concat',
              'UpsamplingNearest2d': 'Deconvolution',
              'UpsamplingBilinear2d': 'Deconvolution',
              'SigmoidBackward': 'Sigmoid',
              'LeakyReLUBackward': 'ReLU',
              'NegateBackward': 'Power',
              'MulBackward': 'Eltwise',
              'SpatialCrossMapLRNFunc': 'LRN'}

我想知道 layer_dict的对应关系是如何确定的?

我看了pytorch的代码torch/nn/_functions/thnn/auto.py会读取C代码的头文件,加载类。

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions