pytorch插值函数interpolate——图像上采样-下采样，scipy插值函数zoom

在训练过程中，需要对图像数据进行插值，如果此时数据是numpy数据，那么可以使用scipy中的zoom函数：

from scipy.ndimage.interpolation import zoom

def zoom(input, zoom, output=None, order=3, mode='constant', cval=0.0,
         prefilter=True):
    """
    Zoom an array.

    The array is zoomed using spline interpolation of the requested order.

    Parameters
    ----------
    %(input)s
    zoom : float or sequence
        The zoom factor along the axes. If a float, `zoom` is the same for each
        axis. If a sequence, `zoom` should contain one value for each axis.
    %(output)s
    order : int, optional
        The order of the spline interpolation, default is 3.
        The order has to be in the range 0-5.
    %(mode)s
    %(cval)s
    %(prefilter)s

    Returns
    -------
    zoom : ndarray
        The zoomed input.

    Examples
    --------
    >>> from scipy import ndimage, misc
    >>> import matplotlib.pyplot as plt

    >>> fig = plt.figure()
    >>> ax1 = fig.add_subplot(121)  # left side
    >>> ax2 = fig.add_subplot(122)  # right side
    >>> ascent = misc.ascent()
    >>> result = ndimage.zoom(ascent, 3.0)
    >>> ax1.imshow(ascent)
    >>> ax2.imshow(result)
    >>> plt.show()

    >>> print(ascent.shape)
    (512, 512)

    >>> print(result.shape)
    (1536, 1536)
    """
    if order < 0 or order > 5:
        raise RuntimeError('spline order not supported')
    input = numpy.asarray(input)
    if numpy.iscomplexobj(input):
        raise TypeError('Complex type not supported')
    if input.ndim < 1:
        raise RuntimeError('input and output rank must be > 0')
    mode = _ni_support._extend_mode_to_code(mode)
    if prefilter and order > 1:
        filtered = spline_filter(input, order, output=numpy.float64)
    else:
        filtered = input
    zoom = _ni_support._normalize_sequence(zoom, input.ndim)
    output_shape = tuple(
            [int(round(ii * jj)) for ii, jj in zip(input.shape, zoom)])

    output_shape_old = tuple(
            [int(ii * jj) for ii, jj in zip(input.shape, zoom)])
    if output_shape != output_shape_old:
        warnings.warn(
                "From scipy 0.13.0, the output shape of zoom() is calculated "
                "with round() instead of int() - for these inputs the size of "
                "the returned array has changed.", UserWarning)

    zoom_div = numpy.array(output_shape, float) - 1
    # Zooming to infinite values is unpredictable, so just choose
    # zoom factor 1 instead
    zoom = numpy.divide(numpy.array(input.shape) - 1, zoom_div,
                        out=numpy.ones_like(input.shape, dtype=numpy.float64),
                        where=zoom_div != 0)

    output = _ni_support._get_output(output, input,
                                                   shape=output_shape)
    zoom = numpy.ascontiguousarray(zoom)
    _nd_image.zoom_shift(filtered, zoom, None, output, order, mode, cval)
    return output

 

中的zoom函数进行插值，

但是，如果此时的数据是tensor（张量）的时候，使用zoom函数的时候需要将tensor数据转为numpy，将GPU数据转换为CPU数据等，过程比较繁琐，可以使用pytorch自带的函数进行插值操作，interpolate函数有几个参数：size表示输出大小，scale_factor表示缩放倍数，mode表示插值方式，align_corners是bool类型，表示输入和输出中心是否对齐：

from torch.nn.functional import interpolate

def interpolate(input, size=None, scale_factor=None, mode='nearest', align_corners=None):
    r"""Down/up samples the input to either the given :attr:`size` or the given
    :attr:`scale_factor`

    The algorithm used for interpolation is determined by :attr:`mode`.

    Currently temporal, spatial and volumetric sampling are supported, i.e.
    expected inputs are 3-D, 4-D or 5-D in shape.

    The input dimensions are interpreted in the form:
    `mini-batch x channels x [optional depth] x [optional height] x width`.

    The modes available for resizing are: `nearest`, `linear` (3D-only),
    `bilinear`, `bicubic` (4D-only), `trilinear` (5D-only), `area`

    Args:
        input (Tensor): the input tensor
        size (int or Tuple[int] or Tuple[int, int] or Tuple[int, int, int]):
            output spatial size.
        scale_factor (float or Tuple[float]): multiplier for spatial size. Has to match input size if it is a tuple.
        mode (str): algorithm used for upsampling:
            ``'nearest'`` | ``'linear'`` | ``'bilinear'`` | ``'bicubic'`` |
            ``'trilinear'`` | ``'area'``. Default: ``'nearest'``
        align_corners (bool, optional): Geometrically, we consider the pixels of the
            input and output as squares rather than points.
            If set to ``True``, the input and output tensors are aligned by the
            center points of their corner pixels. If set to ``False``, the input and
            output tensors are aligned by the corner points of their corner
            pixels, and the interpolation uses edge value padding for out-of-boundary values.
            This only has effect when :attr:`mode` is ``'linear'``,
            ``'bilinear'``, ``'bicubic'``, or ``'trilinear'``.
            Default: ``False``

    .. warning::
        With ``align_corners = True``, the linearly interpolating modes
        (`linear`, `bilinear`, and `trilinear`) don't proportionally align the
        output and input pixels, and thus the output values can depend on the
        input size. This was the default behavior for these modes up to version
        0.3.1. Since then, the default behavior is ``align_corners = False``.
        See :class:`~torch.nn.Upsample` for concrete examples on how this
        affects the outputs.

    .. include:: cuda_deterministic_backward.rst
    """
    from .modules.utils import _ntuple

    def _check_size_scale_factor(dim):
        if size is None and scale_factor is None:
            raise ValueError('either size or scale_factor should be defined')
        if size is not None and scale_factor is not None:
            raise ValueError('only one of size or scale_factor should be defined')
        if scale_factor is not None and isinstance(scale_factor, tuple)\
                and len(scale_factor) != dim:
            raise ValueError('scale_factor shape must match input shape. '
                             'Input is {}D, scale_factor size is {}'.format(dim, len(scale_factor)))

    def _output_size(dim):
        _check_size_scale_factor(dim)
        if size is not None:
            return size
        scale_factors = _ntuple(dim)(scale_factor)
        # math.floor might return float in py2.7

        # make scale_factor a tensor in tracing so constant doesn't get baked in
        if torch._C._get_tracing_state():
            return [(torch.floor(input.size(i + 2) * torch.tensor(float(scale_factors[i])))) for i in range(dim)]
        else:
            return [int(math.floor(int(input.size(i + 2)) * scale_factors[i])) for i in range(dim)]

    if mode in ('nearest', 'area'):
        if align_corners is not None:
            raise ValueError("align_corners option can only be set with the "
                             "interpolating modes: linear | bilinear | bicubic | trilinear")
    else:
        if align_corners is None:
            warnings.warn("Default upsampling behavior when mode={} is changed "
                          "to align_corners=False since 0.4.0. Please specify "
                          "align_corners=True if the old behavior is desired. "
                          "See the documentation of nn.Upsample for details.".format(mode))
            align_corners = False

    if input.dim() == 3 and mode == 'nearest':
        return torch._C._nn.upsample_nearest1d(input, _output_size(1))
    elif input.dim() == 4 and mode == 'nearest':
        return torch._C._nn.upsample_nearest2d(input, _output_size(2))
    elif input.dim() == 5 and mode == 'nearest':
        return torch._C._nn.upsample_nearest3d(input, _output_size(3))
    elif input.dim() == 3 and mode == 'area':
        return adaptive_avg_pool1d(input, _output_size(1))
    elif input.dim() == 4 and mode == 'area':
        return adaptive_avg_pool2d(input, _output_size(2))
    elif input.dim() == 5 and mode == 'area':
        return adaptive_avg_pool3d(input, _output_size(3))
    elif input.dim() == 3 and mode == 'linear':
        return torch._C._nn.upsample_linear1d(input, _output_size(1), align_corners)
    elif input.dim() == 3 and mode == 'bilinear':
        raise NotImplementedError("Got 3D input, but bilinear mode needs 4D input")
    elif input.dim() == 3 and mode == 'trilinear':
        raise NotImplementedError("Got 3D input, but trilinear mode needs 5D input")
    elif input.dim() == 4 and mode == 'linear':
        raise NotImplementedError("Got 4D input, but linear mode needs 3D input")
    elif input.dim() == 4 and mode == 'bilinear':
        return torch._C._nn.upsample_bilinear2d(input, _output_size(2), align_corners)
    elif input.dim() == 4 and mode == 'trilinear':
        raise NotImplementedError("Got 4D input, but trilinear mode needs 5D input")
    elif input.dim() == 5 and mode == 'linear':
        raise NotImplementedError("Got 5D input, but linear mode needs 3D input")
    elif input.dim() == 5 and mode == 'bilinear':
        raise NotImplementedError("Got 5D input, but bilinear mode needs 4D input")
    elif input.dim() == 5 and mode == 'trilinear':
        return torch._C._nn.upsample_trilinear3d(input, _output_size(3), align_corners)
    elif input.dim() == 4 and mode == 'bicubic':
        return torch._C._nn.upsample_bicubic2d(input, _output_size(2), align_corners)
    else:
        raise NotImplementedError("Input Error: Only 3D, 4D and 5D input Tensors supported"
                                  " (got {}D) for the modes: nearest | linear | bilinear | bicubic | trilinear"
                                  " (got {})".format(input.dim(), mode))