图层数组= 1x591“InputLayer”图像输入50 x50x1图片2 Conv1二维卷积64 3 x3x1旋转步[1]和填充[1 1 1 1]3‘ReLU1 ReLU ReLU 4 Conv2二维卷积64 3 x3x64旋转步[1]和填充[1 1 1 1]5‘BNorm2批量标准化批量标准化与64个频道6‘ReLU2 ReLU ReLU 7 Conv3二维卷积64 3 x3x64旋转步[1]和填充(1 1 1)8“BNorm3”批量标准化批量标准化与64个频道9 ReLU3 ReLUReLU 64 3 x3x64 Conv4的二维卷积运算与步幅[1]和填充[1 1 1 1]11的BNorm4批量标准化批量标准化与64个频道12的ReLU4 ReLU ReLU 13 Conv5二维卷积64 3 x3x64旋转步[1]和填充[1 1 1 1]14“BNorm5”批量标准化批量标准化与64个频道15 ' ReLU5 ReLU ReLU 16 Conv6二维卷积64 3 x3x64旋转步[1]和填充[1 1 1 1]17 BNorm6批量标准化批量正常化与64个频道18 ' ReLU6 ReLU ReLU 19 Conv7二维卷积64 3 x3x64旋转步[1]和填充[1 1 1 1]20 ' BNorm7批量标准化批量标准化与64个频道21 ' ReLU7 ReLU ReLU 22“Conv8”二维卷积64 3 x3x64旋转步[1]和填充[1 1 1 1]23 BNorm8的批量标准化批量标准化与64个频道24的ReLU8 ReLU ReLU 25 Conv9二维卷积64 3 x3x64旋转与步幅[1]和填充[1 1 11] 26 'BNorm9'批归一化64通道批归一化27 'ReLU9' ReLU ReLU 28 'Conv10'二维卷积64 3x3x64卷积，stride[1 1]和填充[1 11 1]29 'BNorm10'批归一化64通道批归一化30 'ReLU10' ReLU ReLU 31 'Conv11'二维卷积64 3x3x64卷积，stride[1 1]和填充[1 11 11]32 'BNorm11'批归一化64通道批归一化33 'ReLU11' ReLU ReLU 34 'Conv12'二维卷积64 3x3x64旋转步[1]和填充[1 1 1 1]35 BNorm12的批量标准化批量标准化与64个频道36“ReLU12”ReLU ReLU 37 Conv13二维卷积64 3 x3x64旋转步[1]和填充[1 1 1 1]38“BNorm13”批量标准化批量标准化与64个频道39的ReLU13 ReLU ReLU 40 Conv14二维卷积64 3 x3x64旋转步[1]和填充(1 1 1)41 ' BNorm14批量标准化批量标准化与64个频道42“ReLU14”ReLU ReLU 43 'Conv15' 2-D Convolution 64 3x3x64 convolutions with stride [1 1] and padding [1 1 1 1] 44 'BNorm15' Batch Normalization Batch normalization with 64 channels 45 'ReLU15' ReLU ReLU 46 'Conv16' 2-D Convolution 64 3x3x64 convolutions with stride [1 1] and padding [1 1 1 1] 47 'BNorm16' Batch Normalization Batch normalization with 64 channels 48 'ReLU16' ReLU ReLU 49 'Conv17' 2-D Convolution 64 3x3x64 convolutions with stride [1 1] and padding [1 1 1 1] 50 'BNorm17' Batch Normalization Batch normalization with 64 channels 51 'ReLU17' ReLU ReLU 52 'Conv18' 2-D Convolution 64 3x3x64 convolutions with stride [1 1] and padding [1 1 1 1] 53 'BNorm18' Batch Normalization Batch normalization with 64 channels 54 'ReLU18' ReLU ReLU 55 'Conv19' 2-D Convolution 64 3x3x64 convolutions with stride [1 1] and padding [1 1 1 1] 56 'BNorm19' Batch Normalization Batch normalization with 64 channels 57 'ReLU19' ReLU ReLU 58 'Conv20' 2-D Convolution 1 3x3x64 convolutions with stride [1 1] and padding [1 1 1 1] 59 'FinalRegressionLayer' Regression Output mean-squared-error