python – Tensorflow变量重用

发布时间：2020-12-20 12:13:07 所属栏目：Python 来源：网络整理

导读：我已经建立了我的LSTM模型.理想情况下,我希望稍后使用重用变量来定义测试LSTM模型. with tf.variable_scope('lstm_model') as scope: # Define LSTM Model lstm_model = LSTM_Model(rnn_size,batch_size,learning_rate,training_seq_len,vocab_size) scope.r

我已经建立了我的LSTM模型.理想情况下,我希望稍后使用重用变量来定义测试LSTM模型.

with tf.variable_scope('lstm_model') as scope:
    # Define LSTM Model
    lstm_model = LSTM_Model(rnn_size,batch_size,learning_rate,training_seq_len,vocab_size)
    scope.reuse_variables()
    test_lstm_model = LSTM_Model(rnn_size,vocab_size,infer=True)

上面的代码给了我一个错误

Variable lstm_model/lstm_vars/W already exists,disallowed. Did you mean to set reuse=True in VarScope?

如果我设置了reuse = True,如下面的代码块所示

with tf.variable_scope('lstm_model',reuse=True) as scope:

我得到了一个不同的错误

Variable lstm_model/lstm_model/lstm_vars/W/Adam/ does not exist,or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

作为参考,我在下面附上了相关的型号代码. LSTM模型中的相应部分,我有权重

with tf.variable_scope('lstm_vars'):
    # Softmax Output Weights
    W = tf.get_variable('W',[self.rnn_size,self.vocab_size],tf.float32,tf.random_normal_initializer())

我有Adam优化器的相应部分：

optimizer = tf.train.AdamOptimizer(self.learning_rate)

解决方法

它似乎不是：

with tf.variable_scope('lstm_model') as scope:
    # Define LSTM Model
    lstm_model = LSTM_Model(rnn_size,vocab_size)
    scope.reuse_variables()    
    test_lstm_model = LSTM_Model(rnn_size,infer_sample=True)

这解决了这个问题

# Define LSTM Model
lstm_model = LSTM_Model(rnn_size,vocab_size)

# Tell TensorFlow we are reusing the scope for the testing
with tf.variable_scope(tf.get_variable_scope(),reuse=True):
    test_lstm_model = LSTM_Model(rnn_size,infer_sample=True)

（编辑：李大同）

【声明】本站内容均来自网络，其相关言论仅代表作者个人观点，不代表本站立场。若无意侵犯到您的权利，请及时与联系站长删除相关内容!