Skip to content

Instantly share code, notes, and snippets.

What would you like to do?
TensorFlow Sequence Labelling
# Example for my blog post at:
import functools
import sets
import tensorflow as tf
def lazy_property(function):
attribute = '_' + function.__name__
def wrapper(self):
if not hasattr(self, attribute):
setattr(self, attribute, function(self))
return getattr(self, attribute)
return wrapper
class SequenceLabelling:
def __init__(self, data, target, dropout, num_hidden=200, num_layers=3): = data = target
self.dropout = dropout
self._num_hidden = num_hidden
self._num_layers = num_layers
def prediction(self):
# Recurrent network.
network = tf.nn.rnn_cell.GRUCell(self._num_hidden)
network = tf.nn.rnn_cell.DropoutWrapper(
network, output_keep_prob=self.dropout)
network = tf.nn.rnn_cell.MultiRNNCell([network] * self._num_layers)
output, _ = tf.nn.dynamic_rnn(network, data, dtype=tf.float32)
# Softmax layer.
max_length = int([1])
num_classes = int([2])
weight, bias = self._weight_and_bias(self._num_hidden, num_classes)
# Flatten to apply same weights to all time steps.
output = tf.reshape(output, [-1, self._num_hidden])
prediction = tf.nn.softmax(tf.matmul(output, weight) + bias)
prediction = tf.reshape(prediction, [-1, max_length, num_classes])
return prediction
def cost(self):
cross_entropy = -tf.reduce_sum( * tf.log(self.prediction), [1, 2])
cross_entropy = tf.reduce_mean(cross_entropy)
return cross_entropy
def optimize(self):
learning_rate = 0.003
optimizer = tf.train.RMSPropOptimizer(learning_rate)
return optimizer.minimize(self.cost)
def error(self):
mistakes = tf.not_equal(
tf.argmax(, 2), tf.argmax(self.prediction, 2))
return tf.reduce_mean(tf.cast(mistakes, tf.float32))
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 read_dataset():
dataset = sets.Ocr()
dataset = sets.OneHot(, depth=2)(dataset, columns=['target'])
dataset['data'] =[:-2] + (-1,)).astype(float)
train, test = sets.Split(0.66)(dataset)
return train, test
if __name__ == '__main__':
train, test = read_dataset()
_, length, image_size =
num_classes =[2]
data = tf.placeholder(tf.float32, [None, length, image_size])
target = tf.placeholder(tf.float32, [None, length, num_classes])
dropout = tf.placeholder(tf.float32)
model = SequenceLabelling(data, target, dropout)
sess = tf.Session()
for epoch in range(10):
for _ in range(100):
batch = train.sample(10), {
data:, target:, dropout: 0.5})
error =, {
data:, target:, dropout: 1})
print('Epoch {:2d} error {:3.1f}%'.format(epoch + 1, 100 * error))
Copy link

excuse me,i 'm a new hand in tensorflow, thanks for your bolg which helps me a lot. And i just want to know how can i save the model i trained and use it in another job? looking forward to your reply!

Copy link

wirth6 commented Jan 5, 2017

@YiruS: I find this a bit confusing, as the description of the softmax_cross_entropy_with_logits function states "This op expects unscaled logits, since it performs a softmax on logits internally for efficiency. Do not call this op with the output of softmax, as it will produce incorrect results." and here self.prediction is the output of a softmax, so according to the documentation we shouldn't use this function here.

Copy link

chhung3 commented Apr 22, 2017

Hi, Thanks very much for the example. It helps me a lot for creating my own training model.
I don't fully understand the setting of weight and bias. Is that only 1 weight and 1 bias are needed even for multiple layers network?

Copy link

QoT commented Aug 12, 2017

@adelsalehali1982 You may want to install [sets] like this:

$ pip install -e git+

Now, [AttributeError: 'module' object has no attribute 'Ocr'] problem should disappear.

Copy link

Thank you for the post.
I am learning RNN but I have a ValueError when I run this code:

I have a hard time to debug this. Could you please help with it?

ValueError: Dimensions must be equal, but are 400 and 328 for 'rnn/while/rnn/multi_rnn_cell/cell_0/cell_0/gru_cell/MatMul_2' (op: 'MatMul') with input shapes: [?,400], [328,400].

Copy link

@zdarktknight try the below. I refactored the original implementation and commented heavily for easy understanding. Danijar's sets library makes the job super easy as allows us to focus purely on understanding the algorithm. Good luck.

Copy link

carusyte commented Feb 2, 2018

@QoT, @adelsalehali1982 I suspect it is due to the name shadowing issue with the standard python library. I'm facing the same problem here. No idea how every other guys run the code successfully...I'm using python 2.7.13, and virtualenv, in a virtual environment dedicated for tensorflow. Running the following command tries to compile danijar's sets library from the source, am I guessing right?

$ pip install -e git+

Frustratingly, it gives me the following error:

      File "/Users/jx/ProgramData/tensorflow/src/sets/", line 94, in finalize_options
    TypeError: super() takes at least 1 argument (0 given)
  Rolling back uninstall of sets
Command "/Users/jx/ProgramData/tensorflow/bin/python2.7 -c "import setuptools, 
tokenize;__file__='/Users/jx/ProgramData/tensorflow/src/sets/';f=getattr(tokenize, 'open', open)
(__file__);'\r\n', '\n');f.close();exec(compile(code, __file__, 'exec'))" develop --no-deps" failed with error code 1 in 

Copy link

rolanvc commented Aug 6, 2018

@sufertas, What you did is awesome. Thank you!!

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment