why decay lr when epoch is 9

chenyuntc / simple-faster-rcnn-pytorch

A simplified implemention of Faster R-CNN that replicate performance from origin paper

Other

3.99k stars 1.14k forks source link

Closed chenerg closed 5 years ago

chenerg commented 5 years ago

The following is in train.py if epoch == 9: trainer.load(best_path) trainer.faster_rcnn.scale_lr(opt.lr_decay) lr_ = lr_ * opt.lr_decay

chenyuntc commented 5 years ago

It's just following the implementation from origin paper