One Cycle Policy Save
Pytorch notebook with One Cycle Policy implementation (https://arxiv.org/abs/1803.09820)
Project README
Cyclic Learning Rates and One Cycle Policy.
This notebook contains some of the experiments mentioned in papers Cyclical Learning Rates for Training Neural Networks and A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay. My blog related to the same can be found here
This notebook works with:
- Python 3.6+
- Pytorch 0.3.x
Open Source Agenda is not affiliated with "One Cycle Policy" Project. README Source: nachiket273/One_Cycle_Policy
Stars
73
Open Issues
0
Last Commit
1 year ago
Repository
Open Source Agenda Badge
