图层= 1x59层阵列与图层：1'InputLayer'图像输入50x50x1图像2'Conv1'卷积64 3x3x1卷绕卷曲[1 1]和填充[1 1 1 1] 3'Relu1'Relu Relu 4'Conv2'卷积643x3x64卷曲的卷发[1 1]和填充[1 1 1 1] 5'BNORM2'批量归一化批量标准化，64个通道6'Relu2'Relu Relu 7'Conv3'卷积64 3x3x64卷积与步幅[1 1]和填充[1 11 1 1] 8'BNORM3'批量归一化批量归一化与64通道9'Relu3'Relu 10'Conv4'卷积64 3x3x64卷绕卷曲[111]和填充[1 1 1 1] 11'Bnorm4'批量归一化批量归一化与64通道12'Relu4'Relu Relu 13'Conv5'卷积64 3x3x64卷积与步幅[11]和填充[111 1] 14'BNORM5'批量归一化批量归一化与64通道15'Relu5'Relu Relu16'CONV6'卷积64 3x3x64卷曲的卷程[1 1]和填充[1 1 1 1] 17'BNORM6'批量标准化批量归一化与64通道18'Relu6'Relu 19'Crom7'卷积64 3x3x64卷积与步幅[11]和填充[111 1] 20'Bnorm7'批量归一化批量归一化与64通道21'Relu7'Relu Relu22'CONV8'卷积64 3x3x64卷曲有步部[11]和填充[1 1 1 1] 23'BNORM8'批量归一化批量归一批，具有64个通道24'Relu8'Relu Relu 25'Conv9'卷积64 3x3x64卷积与步幅[1 1]和填充[111 1] 26'Bnorm9'批量归一化批量归一化，64个通道27'Relu9'Relu Relu 28'Conv10'卷积64 3x3x64卷绕卷曲[111]和填充[1 1 1]29'BNORM10'批量归一化批量归一化与64个通道30'relu10'Relu 31'Conv11'卷积64 3×3x64卷积与步幅[11]和填充[1 1 1 1] 32'Bnorm11'批量归一化批量标准化，具有64个通道33'Relu11'Relu Relu 34'Conv12'卷积64 3x3x64与str的卷曲IDE [11]和填充[111 1] 35'BNORM12'批量归一化批量归一化与64通道36'Relu12'Relu Relu 37'Conv13'卷积64 3x3x64卷绕卷曲[1 1]和填充[1 1 11] 38'BNORM13'批量归一化批量归一化与64通道39'Relu13'Relu Relu 44'Conv14'卷积64 3x3x64卷积与步幅[11]和填充[111 1] 41'Bnorm14'批量归一化批量归一化 64 channels 42 'ReLU14' ReLU ReLU 43 'Conv15' 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' 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' 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' 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' 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' Convolution 1 3x3x64 convolutions with stride [1 1] and padding [1 1 1 1] 59 'FinalRegressionLayer' Regression Output mean-squared-error