我想训练两个不同的LSTM,使它们在对话环境中相互作用(即一个产生一个序列,它将用作第二个rnn的上下文,它将回答等等)。但是,我不知道如何在tensorflow上分别进行训练(我认为我没有完全理解tf图的逻辑)。当我执行我的代码时,出现以下错误:如何在同一个tensorflow会话中训练不同的LSTM?
变量rnn/basic_lstm_cell /权重已存在,不允许。你是否想在VarScope中设置reuse = True?
当我创建第二个RNN时发生错误。你知道如何解决这个问题吗?
我的代码如下:
#User LSTM
no_units=100
_seq_user = tf.placeholder(tf.float32, [batch_size, max_length_user, user_inputShapeLen], name='seq')
_seq_length_user = tf.placeholder(tf.int32, [batch_size], name='seq_length')
cell = tf.contrib.rnn.BasicLSTMCell(
no_units)
output_user, hidden_states_user = tf.nn.dynamic_rnn(
cell,
_seq_user,
dtype=tf.float32,
sequence_length=_seq_length_user
)
out2_user = tf.reshape(output_user, shape=[-1, no_units])
out2_user = tf.layers.dense(out2_user, user_outputShapeLen)
out_final_user = tf.reshape(out2_user, shape=[-1, max_length_user, user_outputShapeLen])
y_user_ = tf.placeholder(tf.float32, [None, max_length_user, user_outputShapeLen])
softmax_user = tf.nn.softmax(out_final_user, dim=-1)
loss_user = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out_final_user, labels=y_user_))
optimizer = tf.train.AdamOptimizer(learning_rate=10**-4)
minimize = optimizer.minimize(loss_user)
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init)
for i in range(epoch):
print 'Epoch: ', i
batch_X, batch_Y, batch_sizes = lstm.batching(user_train_X, user_train_Y, sizes_user_train)
for data_, target_, size_ in zip(batch_X, batch_Y, batch_sizes):
sess.run(minimize, {_seq_user:data_, _seq_length_user:size_, y_user_:target_})
#System LSTM
no_units_system=100
_seq_system = tf.placeholder(tf.float32, [batch_size, max_length_system, system_inputShapeLen], name='seq_')
_seq_length_system = tf.placeholder(tf.int32, [batch_size], name='seq_length_')
cell_system = tf.contrib.rnn.BasicLSTMCell(
no_units_system)
output_system, hidden_states_system = tf.nn.dynamic_rnn(
cell_system,
_seq_system,
dtype=tf.float32,
sequence_length=_seq_length_system
)
out2_system = tf.reshape(output_system, shape=[-1, no_units])
out2_system = tf.layers.dense(out2_system, system_outputShapeLen)
out_final_system = tf.reshape(out2_system, shape=[-1, max_length_system, system_outputShapeLen])
y_system_ = tf.placeholder(tf.float32, [None, max_length_system, system_outputShapeLen])
softmax_system = tf.nn.softmax(out_final_system, dim=-1)
loss_system = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=out_final_system, labels=y_system_))
optimizer = tf.train.AdamOptimizer(learning_rate=10**-4)
minimize = optimizer.minimize(loss_system)
for i in range(epoch):
print 'Epoch: ', i
batch_X, batch_Y, batch_sizes = lstm.batching(system_train_X, system_train_Y, sizes_system_train)
for data_, target_, size_ in zip(batch_X, batch_Y, batch_sizes):
sess.run(minimize, {_seq_system:data_, _seq_length_system:size_, y_system_:target_})