Zero reproducibility of results presented here

[svobora]

Hey, as you have already noticed based on many of your articles, there is basically zero reproducibility of your results based on the network models only. The accuracies very much depend also on the training parameters as on the model, which showed up for example in your MobileNetV1 investigation.

Based on that argument, I do not follow why you do not publish also the training setup for each experiment (together with versions of all libraries used), such that your results can be reproduced.