Question

ST（空间变换）有两个输入。第一个是Fi，它是固定的。另一个是M，它根据最后一个LSTM的输出而变化。 LTSM的输入取决于ST的输出和最后LSTM的状态。

Answer 1

最简单的方法可能是编写自己的RNN单元。另一种方法是使用var id = 3; var obj = {"comments":{"commentedBy":"test","date":"","comment":"Hello world","subComments":{"commentedBy":"jaril 2","date":"","comment":"Hello world inside dark","subComments":{"commentedBy":"jaril 3","date":"","comment":"wow working great","subComments":{"commentedBy":"jaril 4","date":"","comment":"wow working great","commentId":4},"commentId":3},"commentId":2},"commentId":1},"dueDate":"","createdDate":"","lastUpdated":"","checkList":[],"position":2,"status":"active"} function deleteCommentId(comments, id) { if (comments.subComments) { if (comments.subComments.commentId === id) { delete comments.subComments; } else { deleteCommentId(comments.subComments, id); } } } deleteCommentId(obj.comments, id); console.log("final object==>",obj); var expectedJSON = {"comments":{"commentedBy":"test","date":"","comment":"Hello world","subComments":{"commentedBy":"jaril 2","date":"","comment":"Hello world inside dark","commentId":2},"commentId":1},"dueDate":"","createdDate":"","lastUpdated":"","checkList":[],"position":2,"status":"active"} console.log("Output match: ",JSON.stringify(obj) == JSON.stringify(expectedJSON));。签出this post或此excellent article。

Answer 2

实际上，我按如下方式实现网络：

  def build_model(self):

    lstm_cell = tf.contrib.rnn.BasicLSTMCell(
        num_units=self.config.num_lstm_units, state_is_tuple=True, reuse=True)
    if self.mode == "train":
      lstm_cell = tf.contrib.rnn.DropoutWrapper(
          lstm_cell,
          input_keep_prob=self.config.lstm_dropout_keep_prob,
          output_keep_prob=self.config.lstm_dropout_keep_prob)

    with tf.variable_scope("lstm", initializer=self.initializer) as lstm_scope:

      zero_state = lstm_cell.zero_state(
          batch_size=self.image_embeddings.get_shape()[0], dtype=tf.float32)

      K = 5
      C = 80

      scores = tf.Variable(tf.random_normal(shape=[K, self.config.batch_size, C]), name="scores")

      M = tf.Variable(tf.random_normal(shape=[K+1, self.config.batch_size, 2, 3]), name="M")
      tf.assign(M[0], tf.convert_to_tensor([[1., 0., 0.], [0., 1., 0.]]))

      lstm_input_size = 14
      zk_size = 4096

      hidden = zero_state

      for k in range(0, K+1):
          # Allow the LSTM variables to be reused.
          if k > 0:
              lstm_scope.reuse_variables()
          f_k = spatial_transformer_network.spatial_transformer_network(self.image_embeddings, M[k])

          f_k = tf.nn.max_pool(f_k, [1,2,2,1], [1,1,1,1], padding='VALID')

          f_k = tf.layers.dense(tf.reshape(f_k, [self.config.batch_size, int(lstm_input_size * lstm_input_size / 4 * 512)]), 4096)

          lstm_outputs, hidden = lstm_cell(f_k, hidden)

          z_k = tf.layers.dense(hidden[0], zk_size, activation=tf.nn.relu)

          if k != 0:
              tf.assign(scores[k - 1], (tf.layers.dense(z_k, C)))

          if k != K:
              tf.assign(M[k + 1], (tf.reshape(tf.layers.dense(z_k, 6), [self.config.batch_size, 2, 3])))
              tf.assign(M[k + 1, :, 0, 1], (tf.convert_to_tensor(0.)))
              tf.assign(M[k + 1, :, 1, 0], (tf.convert_to_tensor(0.)))

但是运行时会抛出错误

lstm_outputs, hidden = lstm_cell(f_k, hidden).

错误信息是： ValueError：变量lstm / basic_lstm_cell / kernel不存在，或者不是使用tf.get_variable（）创建的。您是要在VarScope中设置复用= tf.AUTO_REUSE吗？

那是什么问题？

如何实现时序如下图所示

2 个答案: