def model(self, x, is_training):
op = ops.get_n_hidden_layers(x,
self.hidden_layer_list,
self.activation_list,
initializer='xavier')
return ops.get_hidden_layer(op,
'output_layer',
self.no_of_classes,
'none',
initializer='xavier')
def get_model(self, x, is_training):
if isinstance(self.cell_size, list):
rnn_layers = [
tf.nn.rnn_cell.LSTMCell(self.cell_size[i], name=str(i))
for i in range(len(self.cell_size))
]
multi_rnn_cell = tf.nn.rnn_cell.MultiRNNCell(rnn_layers)
elif isinstance(self.cell_size, int):
rnn_layers = [
tf.nn.rnn_cell.LSTMCell(self.cell_size, name=str(i))
for i in range(self.no_of_cell)
]
multi_rnn_cell = tf.nn.rnn_cell.MultiRNNCell(rnn_layers)
outputs, states = tf.nn.dynamic_rnn(cell=multi_rnn_cell,
inputs=x,
dtype=tf.float32)
op = tf.gather(outputs, int(outputs.get_shape()[1]) - 1, axis=1)
op = ops.get_n_hidden_layers(op, '', self.hidden_layers,
self.activation_list)
return ops.get_hidden_layer(op, 'output_layer', 1, 'none')
def get_decoder(self,x,is_training):
return ops.get_n_hidden_layers(x,'decoder',self.decoder_hidden_layers+[self.no_of_features],self.decoder_activation_list+['none'],'xavier')
def get_encoder(self,x,is_training):
return ops.get_n_hidden_layers(x,'encoder',self.encoder_hidden_layers,self.encoder_activation_list,'xavier')
def get_model(self,x,is_training):
op=ops.get_n_hidden_layers(x,'',self.hidden_layers,self.activation_list)
return ops.get_hidden_layer(op,'output_layer',1,'none')