padded.py 文件源码

python
阅读 22 收藏 0 点赞 0 评论 0

项目:reseg 作者: fvisin 项目源码 文件源码
def __init__(self, incoming, pool_size, stride=None, pad=(0, 0),
                 ignore_border=True, centered=True, **kwargs):
        """A padded pooling layer

        Parameters
        ----------
        incoming : lasagne.layers.Layer
            The input layer
        pool_size : int
            The size of the pooling
        stride : int or iterable of int
            The stride or subsampling of the convolution
        pad :  int, iterable of int, ``full``, ``same`` or ``valid``
            **Ignored!** Kept for compatibility with the
            :class:``lasagne.layers.Pool2DLayer``
        ignore_border : bool
            See :class:``lasagne.layers.Pool2DLayer``
        centered : bool
            If True, the padding will be added on both sides. If False
            the zero padding will be applied on the upper left side.
        **kwargs
            Any additional keyword arguments are passed to the Layer
            superclass
        """
        self.centered = centered
        if pad not in [0, (0, 0), [0, 0]]:
            warnings.warn('The specified padding will be ignored',
                          RuntimeWarning)
        super(PaddedPool2DLayer, self).__init__(incoming,
                                                pool_size,
                                                stride,
                                                pad,
                                                ignore_border,
                                                **kwargs)
        if self.input_shape[2:] != (None, None):
            warnings.warn('This Layer should only be used when the size of '
                          'the image is not known', RuntimeWarning)
评论列表
文章目录


问题


面经


文章

微信
公众号

扫码关注公众号