Tensorflow: next_batch function of np array

Question

I have train data as

xTrain = numpy.asarray([100, 1, 5, 6 ...])
yTrain = numpy.asarray([200, 2, 10, 12 ...])

How to define next_batch(size) method to get size number of random elements from the train data.

Vijayachandran Mariappan · Accepted Answer · 2017-07-14 19:52:38Z

1

You can use this as your next batch function:

def batch_data(source, target, batch_size):

   # Shuffle data
   shuffle_indices = np.random.permutation(np.arange(len(target)))
   source = source[shuffle_indices]
   target = target[shuffle_indices]

   for batch_i in range(0, len(source)//batch_size):
      start_i = batch_i * batch_size
      source_batch = source[start_i:start_i + batch_size]
      target_batch = target[start_i:start_i + batch_size]

      yield np.array(source_batch), np.array(target_batch)

answered Jul 14, 2017 at 19:52

Vijayachandran Mariappan

17.2k3 gold badges43 silver badges60 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Sreeragh A R Over a year ago

ValueError: too many values to unpack When I gave batch_size greater than size if source.

Vijayachandran Mariappan Over a year ago

you want batch_size > source size?. why? then its no longer a batch. Can you edit your question of what functionality you actually want?

Collectives™ on Stack Overflow

Tensorflow: next_batch function of np array

1 Answer 1

2 Comments

Your Answer

Linked

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Linked

Related