Minghao Guo comments

Results 6 comments of


Minghao Guo

How to calculate the number of MAC, the number of layers and the model size of the network?

I have just tried the repo [here](https://github.com/Lyken17/pytorch-OpCounter), and it works fine. Make sure you follow the instruction at [`README`](https://github.com/gmh14/RobNets/blob/master/README.md#use-robnet-architectures) and REMEMBER to copy the corresponding parameters to the function `models.robnet()`....

How big is the difference in training time and memory consumption between using and not using adversarial training in the search network process？

I am sorry I have no experience in running the search algorithm w/o adversarial training with the current pipeline, but I can provide the training cost w/ adversarial training for...

How big is the difference in training time and memory consumption between using and not using adversarial training in the search network process？

You are correct. The adversarial training itself costs times of additional memory consumption and the super-net structure even exacerbates the situation.

Minghao Guo

How to calculate the number of MAC, the number of layers and the model size of the network?

How big is the difference in training time and memory consumption between using and not using adversarial training in the search network process？

How big is the difference in training time and memory consumption between using and not using adversarial training in the search network process？

why not use the torchvision dataset for SVHN?

How to do archchtecture search on supernet?

Inability to process SMILES with certain SMILES characters