I am trying to add a gradient norm penalty to a loss function similar to WGAN-GP ( [1704.00028] Improved Training of Wasserstein GANs , Alg 1, Lines 7-9). However, I am running into problems with mutation. Is there another way to do this, or does something have to change in Zygote to accomodate this u…

How to add norm of gradient to a loss function?

ToucheSir October 27, 2021, 12:07am 13

As always, please include a full stacktrace along with your MWE.

Topic		Replies	Views
How to use gradient of neural network as the loss function? Machine Learning question	13	2770	March 23, 2021
Gradient penalty problems with relu Machine Learning zygote	0	509	February 4, 2021
Unrecognized gradient using Zygote for AD with Universal Differential Equations General Usage differentiation , pde , zygote	30	2475	October 13, 2021
Gradient of gradient Machine Learning	9	1287	November 6, 2020
Flux differentiation error Machine Learning zygote	19	1714	November 19, 2020