Using a Multi-GPU node to accelerate the training of Pix2Pix neural networks

Generative adversarial networks are gaining importance in problems such as image conversion, cross-domain translation and fast styling. However, the training of these networks remains unclear because it often results in unexpected behavior caused by non-convergence, model collapse or overly long training, causing the training task to have to be supervised by the user and vary with each dataset. To increase the speed of training in Pix2Pix (image-to-image translation) networks, this work incorporates multi-GPU training using mixed precision, along with optimizations in the GPU image input process. In addition, in order to make the training unsupervised and to terminate it when the best transformations are performed, an early stopping method using the peak signal noise ratio (PSNR) metric is proposed.