Tensorflow dynamic_rnn TypeError: Tensor object is not iterable

Question

I am trying to get a basic LSTM working in TensorFlow. I get the following error:

TypeError: 'Tensor' object is not iterable.

Violation line:

rnn_outputs, final_state = tf.nn.dynamic_rnn(cell, x, sequence_length=seqlen,
                                            initial_state=init_state,)`  

I am using version 1.0.1 for Windows 7. My logins and tags have the following forms

x_shape = (50, 40, 18), y_shape = (50, 40)

Where:

• lot size = 50
• sequence length = 40
• input vector length at each step = 18

I build my schedule as follows

def build_graph(learn_rate, seq_len, state_size=32, batch_size=5):

    # use a fixed sequence length
    seqlen = tf.constant(seq_len, shape=[batch_size],dtype=tf.int32)

    # Placeholders
    x = tf.placeholder(tf.float32, [batch_size, None, 18])
    y = tf.placeholder(tf.float32, [batch_size, None])
    keep_prob = tf.constant(1.0)

    # RNN
    cell = tf.contrib.rnn.LSTMCell(state_size)
    init_state = tf.get_variable('init_state', [1, state_size],
                                initializer=tf.constant_initializer(0.0))
    init_state = tf.tile(init_state, [batch_size, 1])
    rnn_outputs, final_state = tf.nn.dynamic_rnn(cell, x, sequence_length=seqlen,
                                                initial_state=init_state,)

    # Add dropout, as the model otherwise quickly overfits
    rnn_outputs = tf.nn.dropout(rnn_outputs, keep_prob)

    # Prediction layer
    with tf.variable_scope('prediction'):
        W = tf.get_variable('W', [state_size, num_classes])
        b = tf.get_variable('b', [num_classes], initializer=tf.constant_initializer(0.0))

    preds = tf.tanh(tf.matmul(rnn_outputs, W) + b)

    # MSE
    loss = tf.square(tf.subtract(y, preds))

    # loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits, y))
    train_step = tf.train.AdamOptimizer(learn_rate).minimize(loss)

Can someone tell me what I am missing?

Answer 1

, . , . sequence length = 40 . , 10 , 13 18, [10, 13, 18]. RNN TensorFlow , ( , ).