Fig 4 - uploaded by Dirk Hölscher
Content may be subject to copyright.
Source publication
![Fig. 1: cGAN Architecture in Pix2Pix [3]](profile/Dirk-Hoelscher-2/publication/377285055/figure/fig1/AS:11431281234114034@1712221141850/cGAN-Architecture-in-Pix2Pix-3_Q320.jpg)
Generative models and their possible applications are almost limitless. But there are still problems that such models have. On one hand, the models are difficult to train. Stability in training, mode collapse or non convergence, together with the huge parameter space make it extremely costly and difficult to train and optimize generative models. Th...
Context in source publication
Context 1
... the first conducted experiment was to look for an early indication if a combination of parameters is good or not and if there is a breaking point. Figure 4 shows the results of the standard parameter pair of Pix2Pix2 to highlight the training process over the first 5 epochs. With the trails run we determined a good starting point with measurable good an stable results 5 epochs are good stop to evaluate model performance till this point. ...
Citations
... This data was used to train a Pix2Pix GAN which was trained to create exact copies [10] of the scans. Based on our previous work [11], [12] and [13] we optimised Pix2Pix to create high quality samples using the evaluation of the Universal Quality Index Metric (UIQ) [14] to optimise the generated images towards an ideal UIQ score by using hyperparameter tuning and then evaluating the results using UIQ. In addition, we created, based on our experiments a prediction network which is able to predict if a hyperparameter combination is able to generate better results or not. ...
