search

facebookresearch / moco

PyTorch implementation of MoCo: https://arxiv.org/abs/1911.05722
MIT License
4.82k stars 794 forks source link

maybe wrong optimizer #154

Open poonam2308 opened 3 months ago

poonam2308 commented 3 months ago

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_learningrate(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?

solauky commented 3 months ago

来信收到，谢谢！