Tensorflow：从还原的RNN撤回隐藏状态

Question

I'd like to restore an RNN and get the hidden state.

I do something like that to save the RNN:

loc="path/to/save/rnn"
with tf.variable_scope("lstm") as scope:
    outputs, state = tf.nn.dynamic_rnn(..)
sess = tf.Session()
sess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
save_path = saver.save(sess,loc)

Now I want to retreive state .

graph = tf.Graph()
sess = tf.Session(graph=graph)
with graph.as_default():
      saver = tf.train.import_meta_graph(loc + '.meta', clear_devices=True)
      saver.restore(sess, loc)
      state= ...

Answer 1

You can add the state tensor to a graph collection , which is basically a key value store to track tensors, using tf.add_to_collection and retrieve it later using tf.get_collection . For example:

loc="path/to/save/rnn"
with tf.variable_scope("lstm") as scope:
    outputs, state = tf.nn.dynamic_rnn(..)
    tf.add_to_collection('state', state)


graph = tf.Graph()
with graph.as_default():
      saver = tf.train.import_meta_graph(loc + '.meta', clear_devices=True)
      state = tf.get_collection('state')[0]  # Note: tf.get_collection returns a list.