search

VITA-Group / TENAS

[ICLR 2021] "Neural Architecture Search on ImageNet in Four GPU Hours: A Theoretically Inspired Perspective" by Wuyang Chen, Xinyu Gong, Zhangyang Wang
MIT License
167 stars 31 forks source link

Linear_Region_Collector #9

Closed Yasaman-Haghighi closed 3 years ago

Yasaman-Haghighi commented 3 years ago

Dear authors,

We're using Linear_Region_Collector class to count the number of linear regions in our network. However, it always returns the same result(batch size * sample_batch). Could be please give us some information about the suitable way of using it?

chenwydj commented 3 years ago

Hi @Yasaman-Haghighi,

Thank you for your interest in our work!

Deep NNs typically have a very large number of linear regions. To see the difference of NNs, you may want to forward a larger number of samples, or use smaller NNs (e.g. reduce #channels).

Hope that helps!