有关序列到序列CustomHelper的文档数量有限
Delegate
在Tensorflow中。
任何人都可以根据输入数据来解释Custom-helper的输入
helper = tf.contrib.seq2seq.CustomHelper(initialize_fn = initialize_fn,sample_fn = sample_fn, next_inputs_fn = next_inputs_fn)
和编码器
X = tf.placeholder(tf.float32, [batch_size x time_steps x features])
encoder_cell = tf.contrib.rnn.BasicLSTMCell(hidden_size)
和/或可能
initial_state = encoder_cell.zero_state(batch_size, dtype=tf.float32)
？