Question

我已经在Kreas中实现了变体自动编码器。代码如下所示。运行它时，出现以下错误消息：

ValueError：操作具有None用于渐变。请确定您所有的操作都定义了渐变（即可区分的）。不带渐变的常见操作：K.argmax，K.round，埃瓦尔。

问题是BatchNormalization。当我从各个部分移除x = BatchNormalization()(x)时，一切都很好。

BatchNormalization对我的影响是什么？

编辑：我发现了自己的错误。我必须添加轴参数，即x = BatchNormalization(axis=2)(x)。 axis=2是否正确？我想我最后有数据格式频道。

编辑2 ：我仍然很困惑。我的数据如下（样本，宽度，高度，通道），因为我正在使用tensorflow后端。但是，当我使用x = BatchNormalization(axis=3)(x)时，会遇到与上述相同的错误。只有axis=1和axis=2在起作用。

import keras
from keras import backend as K
from keras.layers import (Dense, Input, Flatten)
from keras.layers import Lambda, Conv2D, Activation, Dropout
from keras.models import Model
from keras.layers import Reshape, Conv2DTranspose
from keras.losses import mse
from keras.layers.normalization import BatchNormalization

def sampling(args):
    z_mean, z_log_var = args
    batch = K.shape(z_mean)[0]
    dim = K.int_shape(z_mean)[1]
    epsilon = K.random_normal(shape=(batch, dim))
    return z_mean + K.exp(0.5 * z_log_var) * epsilon

inner_dim = 16
latent_dim = 6

image_size = (64,78,1)
inputs = Input(shape=image_size, name='encoder_input')
x = inputs

x = Conv2D(32, 3, strides=2, padding='same')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.25)(x)
x = Conv2D(64, 3, strides=2, padding='same')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.25)(x)

# shape info needed to build decoder model
shape = K.int_shape(x)

# generate latent vector Q(z|X)
x = Flatten()(x)
x = Dense(inner_dim, activation='relu')(x)
z_mean = Dense(latent_dim, name='z_mean')(x)
z_log_var = Dense(latent_dim, name='z_log_var')(x)

z = Lambda(sampling, output_shape=(latent_dim,), name='z')([z_mean, z_log_var])

# instantiate encoder model
encoder = Model(inputs, [z_mean, z_log_var, z], name='encoder')

# build decoder model
latent_inputs = Input(shape=(latent_dim,), name='z_sampling')
x = Dense(inner_dim, activation='relu')(latent_inputs)
x = Dense(shape[1] * shape[2] * shape[3], activation='relu')(x)
x = Reshape((shape[1], shape[2], shape[3]))(x)

x = Conv2DTranspose(64, 3, strides=2, padding='same')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.25)(x)
x = Conv2DTranspose(32, 3, strides=2, padding='same')(x)
x = BatchNormalization()(x)
x = Activation('relu')(x)
x = Dropout(0.25)(x)

outputs = Conv2DTranspose(filters=1, kernel_size=3, activation='sigmoid', padding='same', name='decoder_output')(x)

# instantiate decoder model
decoder = Model(latent_inputs, outputs, name='decoder')

# instantiate VAE model
outputs = decoder(encoder(inputs)[2])
vae = Model(inputs, outputs, name='vae')

def vae_loss(x, x_decoded_mean):
    reconstruction_loss = mse(K.flatten(x), K.flatten(x_decoded_mean))
    reconstruction_loss *= image_size[0] * image_size[1]
    kl_loss = 1 + z_log_var - K.square(z_mean) - K.exp(z_log_var)
    kl_loss = K.sum(kl_loss, axis=-1)
    kl_loss *= -0.5
    vae_loss = K.mean(reconstruction_loss + kl_loss)
    return vae_loss

optimizer = keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.000)
vae.compile(loss=vae_loss, optimizer=optimizer)
vae.fit(train_X, train_X,
        epochs=500,
        batch_size=128,
        verbose=1,
        shuffle=True,
        validation_data=(valid_X, valid_X))

使用BatchNormalization会导致错误

0 个答案: