Tensorflow: Slicing a Tensor into overlapping blocks

Question

I have a 1D tensor that I wish to partition into overlapping blocks. I\'m thinking of something like: tensor = tf.constant([1, 2, 3, 4, 5, 6, 7])

Answer 1

If you're looking for a way to get each rolling window as an individual tensor (i.e. each time you call window.eval() your window moves one over. You can use tf.FIFOQueue as well as tf.train.range_input_producer to make a queue that does this:

EDIT: updated to work with variable length tensors as requested in your original answer

def window_input_producer(tensor, window_size, capacity=32, num_epochs=None):
  num_windows = tf.shape(tensor)[0] - window_size
  range_queue = tf.train.range_input_producer(
      num_windows,
      shuffle=False,
      capacity=capacity,
      num_epochs=num_epochs
  )
  index = range_queue.dequeue()
  window = tensor[index:index + window_size]
  queue = tf.FIFOQueue(capacity=capacity,
                       dtypes=[tensor.dtype.base_dtype],
                       shapes=[window_size])

  enq = queue.enqueue(window)
  tf.train.add_queue_runner(
      tf.train.QueueRunner(queue, [enq])
  )

  return queue.dequeue()