python - Theano: using dot "T" at the end of a dot product where number of dimensions is greater than one -
i going through lstm code jonathan raiman , encountered line of code in "layer" class
if x.ndim > 1: return t.nnet.sigmoid(t.dot(self.linear_matrix,x.t) + self.bias_matrix[:,none]).t
t
"import theano.tensor t"
x symbolic variable
what x.t do? (return statement).t do??
please help.
x.t
transpose of matrix x
.
.t
notation applies transpose numpy matrices, same numpy.transpose(x)
. should not confused name t
import theano.tensor t
and
(return statement).t
returns transpose of output of sigmoid function applied on parameter: t.dot(self.linear_matrix,x.t) + self.bias_matrix[:,none]
Comments
Post a Comment