TensorFlow Sequence Classification

blog_tensorflow_sequence_classification.py

# Example for my blog post at:
# https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/
import functools
import sets
import tensorflow as tf


def lazy_property(function):
    attribute = '_' + function.__name__

    @property
    @functools.wraps(function)
    def wrapper(self):
        if not hasattr(self, attribute):
            setattr(self, attribute, function(self))
        return getattr(self, attribute)
    return wrapper


class SequenceClassification:

    def __init__(self, data, target, dropout, num_hidden=200, num_layers=3):
        self.data = data
        self.target = target
        self.dropout = dropout
        self._num_hidden = num_hidden
        self._num_layers = num_layers
        self.prediction
        self.error
        self.optimize

    @lazy_property
    def prediction(self):
        # Recurrent network.
        network = tf.contrib.rnn.GRUCell(self._num_hidden)
        network = tf.contrib.rnn.DropoutWrapper(
            network, output_keep_prob=self.dropout)
        network = tf.contrib.rnn.MultiRNNCell([network] * self._num_layers)
        output, _ = tf.nn.dynamic_rnn(network, self.data, dtype=tf.float32)
        # Select last output.
        output = tf.transpose(output, [1, 0, 2])
        last = tf.gather(output, int(output.get_shape()[0]) - 1)
        # Softmax layer.
        weight, bias = self._weight_and_bias(
            self._num_hidden, int(self.target.get_shape()[1]))
        prediction = tf.nn.softmax(tf.matmul(last, weight) + bias)
        return prediction

    @lazy_property
    def cost(self):
        cross_entropy = -tf.reduce_sum(self.target * tf.log(self.prediction))
        return cross_entropy

    @lazy_property
    def optimize(self):
        learning_rate = 0.003
        optimizer = tf.train.RMSPropOptimizer(learning_rate)
        return optimizer.minimize(self.cost)

    @lazy_property
    def error(self):
        mistakes = tf.not_equal(
            tf.argmax(self.target, 1), tf.argmax(self.prediction, 1))
        return tf.reduce_mean(tf.cast(mistakes, tf.float32))

    @staticmethod
    def _weight_and_bias(in_size, out_size):
        weight = tf.truncated_normal([in_size, out_size], stddev=0.01)
        bias = tf.constant(0.1, shape=[out_size])
        return tf.Variable(weight), tf.Variable(bias)


def main():
    # We treat images as sequences of pixel rows.
    train, test = sets.Mnist()
    _, rows, row_size = train.data.shape
    num_classes = train.target.shape[1]
    data = tf.placeholder(tf.float32, [None, rows, row_size])
    target = tf.placeholder(tf.float32, [None, num_classes])
    dropout = tf.placeholder(tf.float32)
    model = SequenceClassification(data, target, dropout)
    sess = tf.Session()
    sess.run(tf.global_variables_initializer())
    for epoch in range(10):
        for _ in range(100):
            batch = train.sample(10)
            sess.run(model.optimize, {
                data: batch.data, target: batch.target, dropout: 0.5})
        error = sess.run(model.error, {
            data: test.data, target: test.target, dropout: 1})
        print('Epoch {:2d} error {:3.1f}%'.format(epoch + 1, 100 * error))


if __name__ == '__main__':
    main()

I'm trying to learn tensorflow and am running version 1.2.1. Every time I try to run any example with a construction like:
network = tf.contrib.rnn.GRUCell(self._num_hidden)
network = tf.contrib.rnn.DropoutWrapper(
network, output_keep_prob=self.dropout)
network = tf.contrib.rnn.MultiRNNCell([network] * self._num_layers)

I get an error like:
ValueError: Trying to share variable rnn/multi_rnn_cell/cell_0/gru_cell/gates/kernel, but specified shape (400, 400) and found shape (228, 400).

If I remove the DropoutWrapper() call, everything is fine. I can't seem to find any example that doesn't do this, so I'm having trouble learning how to construct a cell with dropout.

hey Joelkr Instead of using
network = tf.contrib.rnn.GRUCell(self._num_hidden)
network = tf.contrib.rnn.DropoutWrapper(
network, output_keep_prob=self.dropout)
network = tf.contrib.rnn.MultiRNNCell([network] * self._num_layers)

define each cell separately and then join them together so they dont share variables like the following :
cells = []
for _ in range(self._num_layers):
cell = tf.contrib.rnn.GRUCell(self._num_hidden) # Or LSTMCell(num_units)
cell = tf.contrib.rnn.DropoutWrapper(
cell, output_keep_prob=1.0 - self.dropout)
cells.append(cell)
network = tf.contrib.rnn.MultiRNNCell(cells)

Link is dead ?
https://danijar.com/introduction-to-recurrent-networks-in-tensorflow/

Hey guys, i saw last return zero tensor, not real last hidden.

        output, _ = tf.nn.dynamic_rnn(network, self.data, dtype=tf.float32)
        # Select last output.
        output = tf.transpose(output, [1, 0, 2])
        last = tf.gather(output, int(output.get_shape()[0]) - 1)

@danijar

I have two more questions about this project, hoping that someone who's still reading this blog would be able to answer.

1. For a while I was sure about this, but now I'm a bit worried: do I understand it correctly, that one "row" in data represent a feature vector at time t, and the next row represents a feature vector at time t+1?
2. Would it be possible to include an embedding layer below the GRU layers that would transform rows of binaries with high dimensionality (size) to a lower dimensionality, and if so, how?

Thank you in advance for any help.