ndim (int) – Number of spatial dimensions.
in_channels (int) – Number of channels of input arrays.
None, parameter initialization will be deferred until the
first forward data pass at which time the size will be determined.
out_channels (int) – Number of channels of output arrays.
ksize (int or tuple of ints) – Size of filters (a.k.a. kernels).
ksize=(k, k, ..., k) are equivalent.
stride (int or tuple of ints) – Stride of filter application.
stride=(s, s, ..., s) are equivalent.
pad (int or tuple of ints) – Spatial padding width for input arrays.
pad=(p, p, ..., p) are equivalent.
nobias (bool) – If
True, then this function does not use the bias.
initialW (initializer) – Initializer to
initialize the weight. When it is
ndim should be \(n+2\) where \(n\) is
the number of spatial dimensions.
initial_bias (initializer) – Initializer to
initialize the bias. If
None, the bias will be initialized to
zero. When it is
ndim should 1.
cover_all (bool) – If
True, all spatial locations are convoluted
into some output pixels. It may make the output size larger.
cover_all needs to be
False if you want to use cuDNN.
int s) – Dilation factor of filter applications.
dilate=(d, d, ..., d) are equivalent.
int) – The number of groups to use grouped convolution.
The default is one, where grouped convolution is not used.