Tensorflow 2 version of unfold in Torch - 컴퓨터

def unfold(tensor, kernel_size, dilation=1, padding=0, stride=1):
  """
      Tensorflow 2 version of unfold in Torch (1.2)
      Thanks to tf.image.extract_patches,
      we just need to reshape, pad, and transpose before and after the operation.

      tensor: [b, channel, width, height], float
      kernel_size: [], int
      dilation: [], int
      padding: [], int
      stride: [], int
      * The four scalars above are broadcast to width and height
  """
  if dilation != 1:
    print("WARNING!!: dilation != 1 might work not as intended.")

  b, c, _, _ = tf.shape(tensor)
  # tensor: from [b, channel, width, height]
  #           to [b, channel, width, channel]
  tensor = tf.transpose(tensor, [0, 2, 3, 1])
  # tensor: from [b, channel, width, channel]
  #           to [b, channel + padding * 2, width + padding * 2, channel]
  tensor = tf.keras.layers.ZeroPadding2D(padding=padding)(tensor)
  # this implementation is tf.image.extract_patches
  kernel_size = [1, kernel_size, kernel_size, 1]
  stride = [1, stride, stride, 1]
  dilation = [1, dilation, dilation, 1]
  tensor = tf.image.extract_patches(images=tensor, sizes=kernel_size,
                                    strides=stride, rates=dilation,
                                    padding='VALID')
  # it needs to be refactored
  w = tf.shape(tensor)[1]
  h = tf.shape(tensor)[2]
  tensor = tf.reshape(tensor, [b, w, h, -1, c])
  tensor = tf.transpose(tensor, [0, 1, 2, 4, 3])
  tensor = tf.reshape(tensor, [b, w * h, -1])
  tensor = tf.transpose(tensor, [0, 2, 1])

  return tensor

pytorch 1.2.0, pillow version - 컴퓨터

if you see "ImportError: cannot import name 'PILLOW_VERSION'" during running PyTorch 1.2.0 scripts then downgrade pillow to 6.2.1.

ref: https://github.com/python-pillow/Pillow/issues/4130

mist vs vague - 영어공부

Finding tight clusters of high-dimensional votes that agree in a mist of irrelevant votes is one way of solving the problem of assigning parts to wholes.

from Hinton, G., Sabour, S., Frosst, N., 2018. Matrix capsules with em routing. In: ICLR, pp. 1–15. https://doi.org/10.2514/6.2003-4412