JY00002 / keras-nas-pgrl

Neural Architecture Search (NAS) using policy gradient Reinforcement Learning (RL)

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

keras-nas-pgrl

Neural Architecture Search (NAS) using policy gradient Reinforcement Learning (RL)

There is only one NAS cell type in this implementation, with a fixed exit flow as: dropout -> dense ->softmax.

About

Neural Architecture Search (NAS) using policy gradient Reinforcement Learning (RL)


Languages

Language:Python 100.0%