我的代码中有一个问题，我希望在lstm_decoder中共享权重（本质上就是使用一个LSTM）。我知道网上有几个相关资源，但我仍然无法理解为什么以下代码无法共享权重：
initial_input = tf.unstack(tf.zeros(shape=(1,1,hidden_size2)))for index in range(window_size): with tf.variable_scope('lstm_cell_decoder', reuse = index > 0): rnn_decoder_cell = tf.nn.rnn_cell.LSTMCell(hidden_size, state_is_tuple = True) output_decoder, state_decoder = tf.nn.static_rnn(rnn_decoder_cell, initial_input, initial_state=last_encoder_state, dtype=tf.float32) # 计算源输出向量的分数 scores = tf.matmul(concat_lstm_outputs, tf.reshape(output_decoder[-1],(hidden_size,1))) attention_coef = tf.nn.softmax(scores) context_vector = tf.reduce_sum(tf.multiply(concat_lstm_outputs, tf.reshape(attention_coef, (window_size, 1))),0) context_vector = tf.reshape(context_vector, (1,hidden_size)) # 计算隐藏状态的 tilda 版本 \tilde{h}_t=tanh(W[c_t, h_t]+b_t) concat_context = tf.concat([context_vector, output_decoder[-1]], axis = 1) W_tilde = tf.Variable(tf.random_normal(shape = [hidden_size*2, hidden_size2], stddev = 0.1), name = "weights_tilde", trainable = True) b_tilde = tf.Variable(tf.zeros([1, hidden_size2]), name="bias_tilde", trainable = True) hidden_tilde = tf.nn.tanh(tf.matmul(concat_context, W_tilde)+b_tilde) # hidden_tilde 是 [1*64] # 更新到下一个时间步 initial_input = tf.unstack(tf.reshape(hidden_tilde, (1,1,hidden_size2))) last_encoder_state = state_decoder print(initial_input, last_encoder_state) # 预测目标 W_target = tf.Variable(tf.random_normal(shape = [hidden_size2, 1], stddev = 0.1), name = "weights_target", trainable = True) print(W_target) logit = tf.matmul(hidden_tilde, W_target) logits = tf.concat([logits, logit], axis = 0)logits = logits[1:]我想在每次循环迭代中使用同一个LSTM单元和相同的W_target。然而，当window_size = 2时，我在循环中对print(initial_input, last_encoder_state)和print(W_target)得到了以下输出。
[<tf.Tensor 'lstm_cell_decoder/unstack:0' shape=(1, 64) dtype=float32>] LSTMStateTuple(c=<tf.Tensor 'lstm_cell_decoder/rnn/rnn/lstm_cell/lstm_cell/add_1:0' shape=(1, 64) dtype=float32>, h=<tf.Tensor 'lstm_cell_decoder/rnn/rnn/lstm_cell/lstm_cell/mul_2:0' shape=(1, 64) dtype=float32>)<tf.Variable 'lstm_cell_decoder/weights_target:0' shape=(64, 1) dtype=float32_ref>[<tf.Tensor 'lstm_cell_decoder_1/unstack:0' shape=(1, 64) dtype=float32>] LSTMStateTuple(c=<tf.Tensor 'lstm_cell_decoder_1/rnn/rnn/lstm_cell/lstm_cell/add_1:0' shape=(1, 64) dtype=float32>, h=<tf.Tensor 'lstm_cell_decoder_1/rnn/rnn/lstm_cell/lstm_cell/mul_2:0' shape=(1, 64) dtype=float32>)<tf.Variable 'lstm_cell_decoder_1/weights_target:0' shape=(64, 1) dtype=float32_ref>更新：在Maxim的评论后，我尝试了以下语法
for index in range(window_size): with tf.variable_scope('lstm_cell_decoder', reuse = index > 0): rnn_decoder_cell = tf.nn.rnn_cell.LSTMCell(hidden_size,reuse=index > 0) output_decoder, state_decoder = tf.nn.static_rnn(rnn_decoder_cell, ...) W_target = tf.get_variable(...)现在它正确地共享了变量W_target，但共享LSTM单元/权重仍然存在问题：
<tf.Tensor 'lstm_cell_decoder/rnn/rnn/lstm_cell/lstm_cell/mul_2:0' shape=(1, 64) dtype=float32>] LSTMStateTuple(c=<tf.Tensor 'lstm_cell_decoder/rnn/rnn/lstm_cell/lstm_cell/add_1:0' shape=(1, 64) dtype=float32>, h=<tf.Tensor 'lstm_cell_decoder/rnn/rnn/lstm_cell/lstm_cell/mul_2:0' shape=(1, 64) dtype=float32>) <tf.Variable 'lstm_cell_decoder/weights_target:0' shape=(64, 1) dtype=float32_ref> [<tf.Tensor 'lstm_cell_decoder_1/rnn/rnn/lstm_cell/lstm_cell/mul_2:0' shape=(1, 64) dtype=float32>] LSTMStateTuple(c=<tf.Tensor 'lstm_cell_decoder_1/rnn/rnn/lstm_cell/lstm_cell/add_1:0' shape=(1, 64) dtype=float32>, h=<tf.Tensor 'lstm_cell_decoder_1/rnn/rnn/lstm_cell/lstm_cell/mul_2:0' shape=(1, 64) dtype=float32>) <tf.Variable 'lstm_cell_decoder/weights_target:0' shape=(64, 1) dtype=float32_ref>回答：
