chainer.functions.squeeze

chainer.functions.squeeze(x, axis=None)[source]

Remove dimensions of size one from the shape of a ndarray.

Parameters
  • x (Variable or N-dimensional array) – Input variable. A \((s_1, s_2, ..., s_N)\) -shaped float array.

  • axis (None or int or tuple of ints) – A subset of the single-dimensional entries in the shape to remove. If None is supplied, all of them are removed. The dimension index starts at zero. If an axis with dimension greater than one is selected, an error is raised.

Returns

Variable whose dimensions of size 1 are removed.

Return type

Variable

Example

>>> x = np.array([[[[0, 1, 2]]], [[[3, 4, 5]]]], np.float32)
>>> x.shape
(2, 1, 1, 3)
>>> y = F.squeeze(x)
>>> y.shape
(2, 3)
>>> y.array
array([[0., 1., 2.],
       [3., 4., 5.]], dtype=float32)
>>> y = F.squeeze(x, axis=1)
>>> y.shape
(2, 1, 3)
>>> y.array
array([[[0., 1., 2.]],

       [[3., 4., 5.]]], dtype=float32)
>>> y = F.squeeze(x, axis=(1, 2))
>>> y.shape
(2, 3)
>>> y.array
array([[0., 1., 2.],
       [3., 4., 5.]], dtype=float32)