提交 d25dac2b authored 作者: Iban Harlouchet's avatar Iban Harlouchet

Small fixes in extra_ops.py, Conv3D.py and conv3d2d.py

上级 b61e972f
......@@ -546,6 +546,8 @@ def squeeze(x):
broadcastable dimensions removed. This is
always `x` itself or a view into `x`.
.. versionadded:: 0.6
Parameters
----------
x
......@@ -553,10 +555,9 @@ def squeeze(x):
Returns
-------
object
`x` without its broadcastable dimensions.
.. versionadded:: 0.6
"""
view = x.dimshuffle([i for i in range(x.ndim)
if not x.broadcastable[i]])
......@@ -1064,6 +1065,7 @@ def to_one_hot(y, nb_class, dtype=None):
Returns
-------
object
A matrix of shape (y.shape[0], nb_class), where each row ``i`` is
the one hot encoding of the corresponding ``y[i]`` value.
......
......@@ -582,8 +582,7 @@ def conv3D(V, W, b, d):
--------
Someone made a script that shows how to swap the axes
between both 3d convolution implementations in Theano. See
the last `attachment
<https://groups.google.com/d/msg/theano-users/1S9_bZgHxVw/0cQR9a4riFUJ>`_.
the last `attachment <https://groups.google.com/d/msg/theano-users/1S9_bZgHxVw/0cQR9a4riFUJ>`_
"""
return _conv3D(V, W, b, d)
......
......@@ -202,7 +202,7 @@ def conv3d(signals, filters,
--------
Someone made a script that shows how to swap the axes between
both 3d convolution implementations in Theano. See the last
`attachment <https://groups.google.com/d/msg/theano-users/1S9_bZgHxVw/0cQR9a4riFUJ>`_.
`attachment <https://groups.google.com/d/msg/theano-users/1S9_bZgHxVw/0cQR9a4riFUJ>`_
"""
......
Markdown 格式
0%
您添加了 0 到此讨论。请谨慎行事。
请先完成此评论的编辑!
注册 或者 后发表评论