search

longcw / pytorch2caffe

Convert PyTorch model to Caffemodel
541 stars 151 forks source link

layer_dict的对应关系 #30

Open as754770178 opened 5 years ago

as754770178 commented 5 years ago 
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。