如何在 Tensorflow/keras 上添加 InstanceNormalization

Question

我是 TensorFlow 和 Keras 的新手，我一直在制作扩展的 resnet，并想在层上添加实例标准化，但我不能，因为它不断抛出错误。

我使用的是tensorflow 1.15和keras 2.1。我注释掉了有效的 BatchNormalization 部分，我尝试添加实例标准化，但它找不到该模块。

非常感谢您的建议

from keras.layers import Conv2D
from keras.layers.normalization import BatchNormalization
from keras.optimizers import Nadam, Adam
from keras.layers import Input, Dense, Reshape, Activation, Flatten, Embedding, Dropout, Lambda, add, concatenate, Concatenate, ConvLSTM2D, LSTM, average, MaxPooling2D, multiply, MaxPooling3D
from keras.layers import GlobalAveragePooling2D, Permute
from keras.layers.advanced_activations import LeakyReLU, PReLU
from keras.layers.convolutional import UpSampling2D, Conv2D, Conv1D
from keras.models import Sequential, Model
from keras.utils import multi_gpu_model
from keras.utils.generic_utils import Progbar
from keras.constraints import maxnorm
from keras.activations import tanh, softmax
from keras import metrics, initializers, utils, regularizers
import tensorflow as tf
import numpy as np
import math
import os
import sys
import random
import keras.backend as K
epsilon = K.epsilon()


def basic_block_conv2D_norm_elu(filters, kernel_size, kernel_regularizer=regularizers.l2(1e-4),act_func="elu", normalize="Instance",   dropout='0.15',
                                strides=1,use_bias = True,kernel_initializer = "he_normal",_dilation_rate=0):
    def f(input):
        if kernel_regularizer == None:
                if _dilation_rate == 0:
                    conv = Conv2D(filters=filters, kernel_size=kernel_size, strides=strides,
                                   padding="same",    use_bias=use_bias)(input)
                else:
                    conv = Conv2D(filters=filters, kernel_size=kernel_size, strides=strides,
                                  padding="same", use_bias=use_bias,dilation_rate=_dilation_rate)(input)
        else:
            if _dilation_rate == 0:
                conv = Conv2D(filters=filters, kernel_size=kernel_size, strides=strides,
                              kernel_initializer=kernel_initializer, padding="same", use_bias=use_bias,
                              kernel_regularizer=kernel_regularizer)(input)
            else:
                conv = Conv2D(filters=filters, kernel_size=kernel_size, strides=strides,
                              kernel_initializer=kernel_initializer, padding="same", use_bias=use_bias,
                              kernel_regularizer=kernel_regularizer, dilation_rate=_dilation_rate)(input)
        if dropout != None:
            dropout_layer = Dropout(0.15)(conv)

        if normalize == None and dropout != None:
            norm_layer = conv(dropout_layer)
        else:
            norm_layer = InstanceNormalization()(dropout_layer)
#            norm_layer = BatchNormalization()(dropout_layer)
        return Activation(act_func)(norm_layer)
    return f

Answer 1

不存在这样的事情InstanceNormalization()。在 Keras 中，您没有单独的层InstanceNormalisation。（这并不意味着您不能申请InstanceNormalisation）

在 Keras 中，我们有tf.keras.layers.BatchNormalization可用于应用任何类型的标准化的层。

该层有以下参数：

    axis=-1,
    momentum=0.99,
    epsilon=0.001,
    center=True,
    scale=True,
    beta_initializer="zeros",
    gamma_initializer="ones",
    moving_mean_initializer="zeros",
    moving_variance_initializer="ones",
    beta_regularizer=None,
    gamma_regularizer=None,
    beta_constraint=None,
    gamma_constraint=None,
    **kwargs
)

现在您可以更改axis参数来生成Instance normalisation图层或任何其他类型的标准化。

BatchNormalization 和 Instance Normalization 的公式如下：

现在，让我们假设您有通道第一个实现，即[B,C,H,W]如果您想计算 BatchNormalization，那么您需要将通道轴指定为 BatchNormalization() 层中的轴。在这种情况下，它将计算C平均值和标准差

BatchNormalization 层：tf.keras.layers.BatchNormalization(axis=1)

如果你想计算 InstanceNormalization，那么只需将你的轴设置为 Batch 和 Channel 的轴即可。在这种情况下，它将计算B*C平均值和标准差

实例标准化层：tf.keras.layers.BatchNormalization(axis=[0,1])

更新1

使用批量归一化时，training =1 如果您想将其用作InstanceNormalisation

更新2

您可以直接使用内置的，InstanceNormalisation 如下所示

https://www.tensorflow.org/addons/api_docs/python/tfa/layers/InstanceNormalization