tf.contrib.rnn

• Class tf.contrib.rnn.BasicLSTMCell
• Class tf.nn.rnn_cell.BasicLSTMCell
• 其实两个是等价的，只是版本的问题，表示定义一个LSTM结构，所使用的变量会自动进行声明。

Args:

• num_units: int, The number of units in the LSTM cell.神经元数量
• forget_bias: float, The bias added to forget gates (see above). Must set to 0.0 manually when restoring from CudnnLSTM-trained checkpoints.  遗忘的偏置是0-1的数，1全记得，0全忘记
• state_is_tuple: If True, accepted and returned states are 2-tuples of the c_state and m_state. If False, they are concatenated along the column axis. The latter behavior will soon be deprecated.最好是true,返回元祖。
• activation: Activation function of the inner states. Default: tanh.    激活函数，默认tanh
• reuse: (optional) Python boolean describing whether to reuse variables in an existing scope. If not True, and the existing scope already has the given variables, an error is raised.    重使用已存在的变量

• name: String, the name of the layer. Layers with the same name will share weights, but to avoid mistakes we require reuse=True in such cases.

  When restoring from CudnnLSTM-trained checkpoints, must use CudnnCompatibleLSTMCell instead.

 

• tf.contrib.rnn.MultiRNNCell()
• 表示使用MultiRNNCell类实现深层循环网络中每一个时刻的前向传播。