Question

我是Tensorflow的新手，我正在尝试使用tensorflow从头开始实现LSTM编码器 - 解码器，根据这篇博文： https://medium.com/@shiyan/understanding-lstm-and-its-diagrams-37e2f46f1714

这是编码器的代码（使用tf.while_loop）

def decode_timestep(self, context, max_dec, result, C_t_d, H_t_d, current_index):
    with tf.variable_scope('decode_scope', reuse=True):

        W_f_d = tf.get_variable('W_f_d', (self.n_dim, self.n_dim), tf.float32)
        U_f_d = tf.get_variable('U_f_d', (self.n_dim, self.n_dim), tf.float32)
        # ...

    # Decoder
    # Forget Gate
    f_t_d = tf.nn.sigmoid(
        tf.add(tf.reduce_sum(tf.add(tf.matmul(context, W_f_d), tf.matmul(H_t_d, U_f_d))), b_f_d))

    C_t_d_f = tf.multiply(C_t_d, f_t_d)

    # Input Gate
    # Part 1. New Memory Impaction

    i_t_d = tf.nn.sigmoid(
        tf.add(tf.reduce_sum(tf.add(tf.matmul(context, W_i_d), tf.matmul(H_t_d, U_i_d))), b_i_d))

    # Part 2. Calculate New Memory

    c_d_new = tf.nn.tanh(tf.add(tf.reduce_sum(tf.add(tf.matmul(context, W_c_d), tf.matmul(H_t_d, U_c_d))), b_c_d))

    # Part 3. Update old Memory

    C_t_d_i = tf.add(C_t_d_f, tf.multiply(i_t_d, c_d_new))

    # Output Gate

    o_t_d = tf.nn.sigmoid(
        tf.add(tf.reduce_sum(tf.add(tf.matmul(context, W_o_d), tf.matmul(H_t_d, U_o_d))), b_o_d))

    # Calculate new H_t

    H_t_d_new = tf.multiply(o_t_d, tf.nn.tanh(C_t_d))

    # Write the result of this timestep to the tensor array at pos current_index
    result.write(tf.subtract(tf.subtract(max_dec, 1), current_index), H_t_d_new)

    # Decrement the current_index by 1
    index_next = tf.subtract(current_index, 1)

    return context, max_dec, result, C_t_d_i, H_t_d_new, index_next

这是解码器的代码：

def decode_timestep(self, context, max_dec, result, C_t_d, H_t_d, current_index):
    # Same as above

    # Calculate new H_t

    H_t_d_new = tf.multiply(o_t_d, tf.nn.tanh(C_t_d))

    # Write the result of this timestep to the tensor array at pos current_index
    result.write(tf.subtract(tf.subtract(max_dec, 1), current_index), H_t_d_new)

    # Decrement the current_index by 1
    index_next = tf.subtract(current_index, 1)

    return context, max_dec, result, C_t_d_i, H_t_d_new, index_next

这是会话的代码：

    with tf.variable_scope('encode_scope', reuse=True):
        H_t_e = tf.get_variable('H_t_e')
        C_t_e = tf.get_variable('C_t_e')

    with tf.variable_scope('global_scope', reuse=True):
        current_index = tf.get_variable('current_index', dtype=tf.int32)

    context, _, C_t_e, H_t_e, current_index  = tf.while_loop(self.encode_timestep_cond, self.encode_timestep,
                               [X_Sent, max_enc, C_t_e, H_t_e, current_index])

    result = tf.TensorArray(tf.float32, size=max_dec)
    _,_,result, C_t_e, H_t_e, current_index = tf.while_loop(self.decode_timestep_cond, self.decode_timestep,
                            [context, max_dec, result, C_t_e, H_t_e, current_index])

    loss = tf.reduce_sum(tf.sqrt(tf.reduce_sum(tf.square(tf.subtract(result.concat(), Y_Sent)), reduction_indices=1)))

    train_step = tf.train.AdamOptimizer().minimize(loss)

错误是：

ValueError：没有为任何变量提供渐变，请检查图形对于不支持渐变的ops，在变量之间 [“”，......

请帮忙！这是我认为应该在我阅读并理解该帖子之后的实现。谢谢你，抱歉我的英文！

Tensorflow没有为任何变量LSTM编码器 - 解码器提供渐变

0 个答案: