The suitable lr for mobilenet_v2 and efficientNet
Closed this issue · 1 comments
detectRecog commented
Hello, thank you for your amazing work! In practice, I find that the lr for mobilenet_v1 in the demo training command is not suitable for mobilenet_v2 and efficientNet, resulting in unstable training. Could you provide your lr choices for other backbones?
Thanks in advance.
haihabi commented
Hi, thanks for your comments.
The hyperparameters are shown in the paper https://www.ecva.net/papers/eccv_2020/papers_ECCV/html/5414_ECCV_2020_paper.php
Is that helpful?