buildingBlocks.py 文件源码

def block_deepFlavourBTVConvolutions(charged,vertices,dropoutRate,active=True,batchnorm=False,batchmomentum=0.6):
    '''
    deep Flavour convolution part. 
    '''
    cpf=charged
    if active:
        cpf  = Convolution1D(64, 1, kernel_initializer='lecun_uniform',  activation='relu', name='cpf_conv0')(cpf)
        if batchnorm:
            cpf = BatchNormalization(momentum=batchmomentum ,name='cpf_batchnorm0')(cpf)
        cpf = Dropout(dropoutRate,name='cpf_dropout0')(cpf)                                                   
        cpf  = Convolution1D(32, 1, kernel_initializer='lecun_uniform',  activation='relu', name='cpf_conv1')(cpf)
        if batchnorm:
            cpf = BatchNormalization(momentum=batchmomentum,name='cpf_batchnorm1')(cpf)
        cpf = Dropout(dropoutRate,name='cpf_dropout1')(cpf)                                                   
        cpf  = Convolution1D(32, 1, kernel_initializer='lecun_uniform',  activation='relu', name='cpf_conv2')(cpf)
        if batchnorm:
            cpf = BatchNormalization(momentum=batchmomentum,name='cpf_batchnorm2')(cpf)
        cpf = Dropout(dropoutRate,name='cpf_dropout2')(cpf)                                                   
        cpf  = Convolution1D(8, 1, kernel_initializer='lecun_uniform',  activation='relu' , name='cpf_conv3')(cpf)
    else:
        cpf = Convolution1D(1,1, kernel_initializer='zeros',trainable=False)(cpf)

    vtx = vertices
    if active:
        vtx = Convolution1D(64, 1, kernel_initializer='lecun_uniform',  activation='relu', name='vtx_conv0')(vtx)
        if batchnorm:
            vtx = BatchNormalization(momentum=batchmomentum,name='vtx_batchnorm0')(vtx)
        vtx = Dropout(dropoutRate,name='vtx_dropout0')(vtx) 
        vtx = Convolution1D(32, 1, kernel_initializer='lecun_uniform',  activation='relu', name='vtx_conv1')(vtx)
        if batchnorm:
            vtx = BatchNormalization(momentum=batchmomentum,name='vtx_batchnorm1')(vtx)
        vtx = Dropout(dropoutRate,name='vtx_dropout1')(vtx)
        vtx = Convolution1D(32, 1, kernel_initializer='lecun_uniform',  activation='relu', name='vtx_conv2')(vtx)
        if batchnorm:
            vtx = BatchNormalization(momentum=batchmomentum,name='vtx_batchnorm2')(vtx)
        vtx = Dropout(dropoutRate,name='vtx_dropout2')(vtx)
        vtx = Convolution1D(8, 1, kernel_initializer='lecun_uniform',  activation='relu', name='vtx_conv3')(vtx)
    else:
        vtx = Convolution1D(1,1, kernel_initializer='zeros',trainable=False)(vtx)

    return cpf,vtx