关于 Sequence to Sequence CustomHelper 的文档数量有限
helper = tf.contrib.seq2seq.CustomHelper(initialize_fn = initialize_fn,sample_fn = sample_fn, next_inputs_fn = next_inputs_fn)
在张量流中。
有人会根据输入数据解释自定义助手的输入吗
X = tf.placeholder(tf.float32, [batch_size x time_steps x features])
和编码器，
encoder_cell = tf.contrib.rnn.BasicLSTMCell(hidden_size)
initial_state = encoder_cell.zero_state(batch_size, dtype=tf.float32)
和/或可能
rnn_output, rnn_states = tf.nn.dynamic_rnn(encoder_cell, X, dtype=tf.float32)
?