问题描述
这是一个可变自动编码器网络,我必须定义一种采样方法来生成潜伏z,我认为这可能是有问题的.这个py文件正在训练中,另一个py文件正在进行在线预测,因此我需要保存keras模型,保存模型没有任何问题,但是当我从"h5"文件加载模型时,它显示了错误:
This is a variational autoencoder network, I have to define a sampling method to generate latent z, I thinks it might be something wrong with this. This py file is doing training, the other py file is doing predicting online, so I need to save the keras model, there is nothing wrong with saving model, but when I load model from 'h5' file, it shows an error:
NameError: name 'latent_dim' is not defined
以下是代码:
df_test = df[df['label']==cluster_num].iloc[:,:data_num.shape[1]]
data_scale_ = preprocessing.StandardScaler().fit(df_test.values)
data_num_ = data_scale.transform(df_test.values)
models_deep_learning_scaler.append(data_scale_)
batch_size = data_num_.shape[0]//10
original_dim = data_num_.shape[1]
latent_dim = data_num_.shape[1]*2
intermediate_dim = data_num_.shape[1]*10
nb_epoch = 1
epsilon_std = 0.001
x = Input(shape=(original_dim,))
init_drop = Dropout(0.2, input_shape=(original_dim,))(x)
h = Dense(intermediate_dim, activation='relu')(init_drop)
z_mean = Dense(latent_dim)(h)
z_log_var = Dense(latent_dim)(h)
def sampling(args):
z_mean, z_log_var = args
epsilon = K.random_normal(shape=(latent_dim,), mean=0.,
std=epsilon_std)
return z_mean + K.exp(z_log_var / 2) * epsilon
# note that "output_shape" isn't necessary with the TensorFlow backend
z = Lambda(sampling, output_shape=(latent_dim,))([z_mean, z_log_var])
# we instantiate these layers separately so as to reuse them later
decoder_h = Dense(intermediate_dim, activation='relu')
decoder_mean = Dense(original_dim, activation='linear')
h_decoded = decoder_h(z)
x_decoded_mean = decoder_mean(h_decoded)
def vae_loss(x, x_decoded_mean):
xent_loss = original_dim * objectives.mae(x, x_decoded_mean)
kl_loss = - 0.5 * K.sum(1 + z_log_var - K.square(z_mean) - K.exp(z_log_var), axis=-1)
return xent_loss + kl_loss
vae = Model(x, x_decoded_mean)
vae.compile(optimizer=Adam(lr=0.01), loss=vae_loss)
train_ratio = 0.95
train_num = int(data_num_.shape[0]*train_ratio)
x_train = data_num_[:train_num,:]
x_test = data_num_[train_num:,:]
vae.fit(x_train, x_train,
shuffle=True,
nb_epoch=nb_epoch,
batch_size=batch_size,
validation_data=(x_test, x_test))
vae.save('./models/deep_learning_'+str(cluster_num)+'.h5')
del vae
from keras.models import load_model
vae = load_model('./models/deep_learning_'+str(cluster_num)+'.h5')
它显示错误:NameError: name 'latent_dim' is not defined
推荐答案
对于变分损失,您使用的是Keras模块未知的许多变量.您需要通过load_model
函数的custom_objects
参数传递它们.
For variational loss you are using many variable not known by Keras module. You need to pass them through custom_objects
param of load_model
function.
在您的情况下:
vae.save('./vae_'+str(cluster_num)+'.h5')
vae.summary()
del vae
from keras.models import load_model
vae = load_model('./vae_'+str(cluster_num)+'.h5', custom_objects={'latent_dim': latent_dim, 'epsilon_std': epsilon_std, 'vae_loss': vae_loss})
vae.summary()
这篇关于Keras保存模型问题的文章就介绍到这了,希望我们推荐的答案对大家有所帮助,也希望大家多多支持!