![](/img/trans.png)
[英]Tensorflow Keras LSTM not training - affected by number_of_epochs, optimizer adam
[英]Keras: Wrong Number of Training Epochs
我正在尝试建立一个类来快速初始化和训练用于快速原型制作的自动编码器。 我想做的一件事是迅速调整训练的时期数。 但是,无论我做什么,该模型都将每层训练100个时代! 我正在使用tensorflow后端。
这是两个令人反感的方法的代码。
def pretrain(self, X_train, nb_epoch = 10):
data = X_train
for ae in self.pretrains:
ae.fit(data, data, nb_epoch = nb_epoch)
ae.layers[0].output_reconstruction = False
ae.compile(optimizer='sgd', loss='mse')
data = ae.predict(data)
.........
def fine_train(self, X_train, nb_epoch):
weights = [ae.layers[0].get_weights() for ae in self.pretrains]
dims = self.dims
encoder = containers.Sequential()
decoder = containers.Sequential()
## add special input encoder
encoder.add(Dense(output_dim = dims[1], input_dim = dims[0],
weights = weights[0][0:2], activation = 'linear'))
## add the rest of the encoders
for i in range(1, len(dims) - 1):
encoder.add(Dense(output_dim = dims[i+1],
weights = weights[i][0:2], activation = self.act))
## add the decoders from the end
decoder.add(Dense(output_dim = dims[len(dims) - 2], input_dim = dims[len(dims) - 1],
weights = weights[len(dims) - 2][2:4], activation = self.act))
for i in range(len(dims) - 2, 1, -1):
decoder.add(Dense(output_dim = dims[i - 1],
weights = weights[i-1][2:4], activation = self.act))
## add the output layer decoder
decoder.add(Dense(output_dim = dims[0],
weights = weights[0][2:4], activation = 'linear'))
masterAE = AutoEncoder(encoder = encoder, decoder = decoder)
masterModel = models.Sequential()
masterModel.add(masterAE)
masterModel.compile(optimizer = 'sgd', loss = 'mse')
masterModel.fit(X_train, X_train, nb_epoch = nb_epoch)
self.model = masterModel
任何有关如何解决该问题的建议,将不胜感激。 我最初的怀疑是这与张量流有关,因此我尝试使用theano后端运行,但遇到了相同的问题。
这里是完整程序的链接。
根据Keras文档 , fit
方法使用默认的100个训练纪元( nb_epoch=100
):
fit(X, y, batch_size=128, nb_epoch=100, verbose=1, callbacks=[], validation_split=0.0, validation_data=None, shuffle=True, show_accuracy=False, class_weight=None, sample_weight=None)
我确定您是如何运行这些方法的,但是按照原始代码中的“典型用法”,您应该可以运行类似的命令(根据需要调整变量num_epoch
):
#Typical usage:
num_epoch = 10
ae = JPAutoEncoder(dims)
ae.pretrain(X_train, nb_epoch = num_epoch)
ae.train(X_train, nb_epoch = num_epoch)
ae.predict(X_val)
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.