https://github.com/nachiket273/one_cycle_policy

Pytorch notebook with One Cycle Policy implementation (https://arxiv.org/abs/1803.09820)
https://github.com/nachiket273/one_cycle_policy

cyclic-learning-rates deep-learning machine-learning notebook notebook-jupyter numpy one-cycle-policy python3 pytorch resnet

Last synced: about 1 year ago
JSON representation

Pytorch notebook with One Cycle Policy implementation (https://arxiv.org/abs/1803.09820)

• Host: GitHub
• URL: https://github.com/nachiket273/one_cycle_policy
• Owner: nachiket273
• Created: 2018-06-24T08:51:00.000Z (almost 8 years ago)
• Default Branch: master
• Last Pushed: 2022-06-25T17:59:50.000Z (almost 4 years ago)
• Last Synced: 2025-03-22T01:25:03.639Z (about 1 year ago)
• Topics: cyclic-learning-rates, deep-learning, machine-learning, notebook, notebook-jupyter, numpy, one-cycle-policy, python3, pytorch, resnet
• Language: Jupyter Notebook
• Homepage:
• Size: 456 KB
• Stars: 74
• Watchers: 3
• Forks: 13
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • Funding: .github/FUNDING.yml

Awesome Lists containing this 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](https://arxiv.org/pdf/1506.01186.pdf) and [A disciplined approach to neural network hyper-parameters: Part 1 - learning rate, batch size, momentum, and weight decay](https://arxiv.org/abs/1803.09820). My blog related to the same can be found [here](https://medium.com/@nachiket.tanksale/finding-good-learning-rate-and-the-one-cycle-policy-7159fe1db5d6)

This notebook works with:

1) Python 3.6+

2) Pytorch 0.3.x