google-deepmind / google-deepmind/deepmind-research
Intuitions regarding setting up number of epochs when training on a novel dataset
Open
- Dominant language
- Jupyter Notebook
- Stars
- 15.2k
- Forks
- 2.9k
- PR merge metrics
- No merged PRs in 30d
Description
Hello,
This is more like a question to understand the working of byol in general. Lets say if I am training the model on a personal image dataset, what would be the best way to decide the number of epochs ?
Any input would be great!
Thanks!
Contributor guide
Assessment
This issue has not been assessed yet.