facebookresearch / facebookresearch/moco

maybe wrong optimizer

Open
#154 1 comment 0 reactions 0 assignees View on GitHub
Dominant language
No language data
Stars
5.1k
Forks
802
PR merge metrics
No merged PRs in 30d

Description

**https://github.com/facebookresearch/moco/blob/colab-notebook/colab/moco_cifar10_demo.ipynb**

_def train(net, data_loader, train_optimizer, epoch, args):
net.train()
adjust_learning_rate(optimizer, epoch, args)_

adjust_learning_rate is called inside train method and therefore it should make use of the same train_optimizer.
Could this training in the notebook be with wrong results?

Contributor guide

Open the contributing guide

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.