Applies a linear transformation to the incoming data:
y
=
x
A
T
+
b
y = xA^T + b
y=xAT+b
This module supports TensorFloat32.
On certain ROCm devices, when using float16 inputs this module will use different precision for backward.
Parameters
in_features – size of each input sample
out_features – size of each output sample
bias – If set to False, the layer will not learn an additive bias. Default: True
Shape:
Input:
(
∗
,
H
i
n
)
(*, H_{in})
(∗,Hin), where * means any number of dimensions including none and
H
i
n
=
in_features
H_{in} = \text{in\_features}
Hin=in_features
Output:
(
∗
,
H
o
u
t
)
(*, H_{out})
(∗,Hout), where all but the last dimension are the same shape as the input and
H
o
u
t
=
out_features
H_{out} = \text{out\_features}
Hout=out_features
2. Tensor.masked_fill
Tensor.masked_fill_(mask, value)
Fills elements of self tensor with value where mask is True. The shape of mask must be broadcastable with the shape of the underlying tensor.