tf.data with multiple inputs / outputs in Keras

by

I’m not using Keras but I would go with an tf.data.Dataset.from_generator() – like:

def _input_fn():
  sent1 = np.array([1, 2, 3, 4, 5, 6, 7, 8], dtype=np.int64)
  sent2 = np.array([20, 25, 35, 40, 600, 30, 20, 30], dtype=np.int64)
  sent1 = np.reshape(sent1, (8, 1, 1))
  sent2 = np.reshape(sent2, (8, 1, 1))

  labels = np.array([40, 30, 20, 10, 80, 70, 50, 60], dtype=np.int64)
  labels = np.reshape(labels, (8, 1))

  def generator():
    for s1, s2, l in zip(sent1, sent2, labels):
      yield {"input_1": s1, "input_2": s2}, l

  dataset = tf.data.Dataset.from_generator(generator, output_types=({"input_1": tf.int64, "input_2": tf.int64}, tf.int64))
  dataset = dataset.batch(2)
  return dataset

...

model.fit(_input_fn(), epochs=10, steps_per_epoch=4)

This generator can iterate over your e.g text-files / numpy arrays and yield on every call a example.
In this example, I assume that the word of the sentences are already converted to the indices in the vocabulary.

Edit:
Since OP asked, it should be also possible with Dataset.from_tensor_slices():

def _input_fn():
  sent1 = np.array([1, 2, 3, 4, 5, 6, 7, 8], dtype=np.int64)
  sent2 = np.array([20, 25, 35, 40, 600, 30, 20, 30], dtype=np.int64)
  sent1 = np.reshape(sent1, (8, 1))
  sent2 = np.reshape(sent2, (8, 1))

  labels = np.array([40, 30, 20, 10, 80, 70, 50, 60], dtype=np.int64)
  labels = np.reshape(labels, (8))

  dataset = tf.data.Dataset.from_tensor_slices(({"input_1": sent1, "input_2": sent2}, labels))
  dataset = dataset.batch(2, drop_remainder=True)
  return dataset

More Related Contents:

  1. TensorFlow and person recognition in video stream
  2. Keras : How should I prepare input data for RNN?
  3. Meaning of buffer_size in Dataset.map , Dataset.prefetch and Dataset.shuffle
  4. How to Properly Combine TensorFlow’s Dataset API and Keras?
  5. What is the meaning of the “None” in model.summary of KERAS?
  6. How do I split Tensorflow datasets?
  7. Multivariate LSTM with missing values
  8. Specify connections in NN (in keras)
  9. What are the differences between all these cross-entropy losses in Keras and TensorFlow?
  10. Split a dataset created by Tensorflow dataset API in to Train and Test?
  11. Does model.compile() initialize all the weights and biases in Keras (tensorflow backend)?
  12. Keras Loss Function with Additional Dynamic Parameter
  13. Using Gensim Fasttext model with LSTM nn in keras
  14. Create keras callback to save model predictions and targets for each batch during training
  15. How to extract data/labels back from TensorFlow dataset
  16. Obtaining output of an Intermediate layer in TensorFlow/Keras
  17. Tensorflow : logits and labels must have the same first dimension
  18. ValueError: Shapes (None, 1) and (None, 2) are incompatible
  19. Keras split train test set when using ImageDataGenerator
  20. In Keras, what exactly am I configuring when I create a stateful `LSTM` layer with N `units`?
  21. Confusion about keras Model: __call__ vs. call vs. predict methods
  22. How can I convert a trained Tensorflow model to Keras?
  23. How to display custom images in TensorBoard using Keras?
  24. What is the difference between keras and tf.keras?
  25. Checkpointing keras model: TypeError: can’t pickle _thread.lock objects
  26. How to replace (or insert) intermediate layer in Keras model?
  27. parallelising tf.data.Dataset.from_generator
  28. Choosing number of Steps per Epoch
  29. Parallelism isn’t reducing the time in dataset map
  30. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?

Leave a Comment