nasnet.py 文件源码

def _adjust_block(p, ip, filters, weight_decay=5e-5, id=None):
    '''
    Adjusts the input `p` to match the shape of the `input`
    or situations where the output number of filters needs to
    be changed

    # Arguments:
        p: input tensor which needs to be modified
        ip: input tensor whose shape needs to be matched
        filters: number of output filters to be matched
        weight_decay: l2 regularization weight
        id: string id

    # Returns:
        an adjusted Keras tensor
    '''
    channel_dim = 1 if K.image_data_format() == 'channels_first' else -1
    img_dim = 2 if K.image_data_format() == 'channels_first' else -2

    with K.name_scope('adjust_block'):
        if p is None:
            p = ip

        elif p._keras_shape[img_dim] != ip._keras_shape[img_dim]:
            with K.name_scope('adjust_reduction_block_%s' % id):
                p = Activation('relu', name='adjust_relu_1_%s' % id)(p)

                p1 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool_1_%s' % id)(p)
                p1 = Conv2D(filters // 2, (1, 1), padding='same', use_bias=False, kernel_regularizer=l2(weight_decay),
                            name='adjust_conv_1_%s' % id, kernel_initializer='he_normal')(p1)

                p2 = ZeroPadding2D(padding=((0, 1), (0, 1)))(p)
                p2 = Cropping2D(cropping=((1, 0), (1, 0)))(p2)
                p2 = AveragePooling2D((1, 1), strides=(2, 2), padding='valid', name='adjust_avg_pool_2_%s' % id)(p2)
                p2 = Conv2D(filters // 2, (1, 1), padding='same', use_bias=False, kernel_regularizer=l2(weight_decay),
                            name='adjust_conv_2_%s' % id, kernel_initializer='he_normal')(p2)

                p = concatenate([p1, p2], axis=channel_dim)
                p = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
                                       name='adjust_bn_%s' % id)(p)

        elif p._keras_shape[channel_dim] != filters:
            with K.name_scope('adjust_projection_block_%s' % id):
                p = Activation('relu')(p)
                p = Conv2D(filters, (1, 1), strides=(1, 1), padding='same', name='adjust_conv_projection_%s' % id,
                           use_bias=False, kernel_regularizer=l2(weight_decay), kernel_initializer='he_normal')(p)
                p = BatchNormalization(axis=channel_dim, momentum=_BN_DECAY, epsilon=_BN_EPSILON,
                                       name='adjust_bn_%s' % id)(p)
    return p