好久没有冒泡了,哈哈。
plateau lr policy来自于PVANET: Deep but Lightweight Neural Networks for Real-time Object Detection这篇论文。
这里从issue里面整理出来的,欢迎大家指点,以及如果你用了plateau lr policy来做实验,是否可以告知下效果如何?
issues:
The Mean AP is 0.7190 when I test the model trained by example_train_