Hands-On Transfer Learning with Python

Constructing a custom optimizer

The objective is to iteratively minimize the overall loss with the help of an optimization algorithm. In the paper by Gatys et al., optimization was done using the L-BFGS algorithm, which is an optimization algorithm based on Quasi-Newton methods, which are popularly used for solving non-linear optimization problems and parameter estimation. This method usually converges faster than standard gradient descent.

SciPy has an implementation available in scipy.optimize.fmin_l_bfgs_b(); however, limitations include the function being applicable only to flat one-dimensional vectors, unlike three-dimensional image matrices that we are dealing with, and the fact that the value of loss function and gradients need to ...