I have to write a Theano custom operator which return a matrix class MyOp(tt.Op): itypes = [tt.dscalar, tt.dscalar, tt.dscalar] otypes = [tt.dmatrix] def perform(self, node, inputs, outputs): c11, c12, c22 = inputs outputs[0][0] = np.array([[c11,c12],[c12,c22]]) Sa…

Gradient of a Theano custom operator returning a matrix

junpenglao November 18, 2018, 7:36am 2

Is your grad operation performed on matrix? I am a bit confuse - why not take gradient of each input directly?

Topic		Replies	Views
Create theano custom operation with [tt.dmatrix, tt.dmatrix] input Questions	3	927	May 6, 2019
Defining custom multivariate Distribution with gradients Questions theano	5	1605	August 24, 2018
Deterministic Theano Op - Gradient Questions theano	4	843	May 26, 2019
Connecting PyMC3 to external code - help with understanding Theano custom Ops Questions theano	20	4288	December 9, 2021
Defining grad() for custom Theano Op that solves nonlinear system of equations Questions theano	1	529	October 26, 2021