MCPcopy Create free account
hub / github.com/apache/singa / conv2d

Function conv2d

python/singa/autograd.py:1721–1737  ·  view source on GitHub ↗

Conv 2d operator Args: handle (object): ConvHandle for cpu or CudnnConvHandle for gpu x (Tensor): input W (Tensor): weight b (Tensor): bias odd_padding (tuple of four ints):, the odd paddding is the value that cannot be handled by the tupl

(handle, x, W, b=None, odd_padding=(0, 0, 0, 0))

Source from the content-addressed store, hash-verified

1719
1720
1721def conv2d(handle, x, W, b=None, odd_padding=(0, 0, 0, 0)):
1722 """
1723 Conv 2d operator
1724 Args:
1725 handle (object): ConvHandle for cpu or CudnnConvHandle for gpu
1726 x (Tensor): input
1727 W (Tensor): weight
1728 b (Tensor): bias
1729 odd_padding (tuple of four ints):, the odd paddding is the value
1730 that cannot be handled by the tuple padding (w, h) mode so
1731 we need to firstly handle the input, then use the nomal padding
1732 method.
1733 """
1734 if b is None:
1735 return _Conv2d(handle, odd_padding)(x, W)[0]
1736 else:
1737 return _Conv2d(handle, odd_padding)(x, W, b)[0]
1738
1739
1740class _BatchNorm2d(Operator):

Callers

nothing calls this directly

Calls 1

_Conv2dClass · 0.85

Tested by

no test coverage detected