search

wangchen1801 / FPD

Official code of the paper "Fine-Grained Prototypes Distillation for Few-Shot Object Detection (AAAI 2024)"
https://arxiv.org/pdf/2401.07629.pdf
27 stars 4 forks source link

lr error nan #12

Closed goodgoodlearndaydayup closed 4 months ago

goodgoodlearndaydayup commented 5 months ago

Good job! Hello friend, I would like to ask if I can use a single 3090GPU to learn with a learning rate of 0.0025. Sometimes, suddenly, there is an issue. I noticed that the code you provided is 2 * 3090 with an lr of 0.005, while the one provided in the paper is 0.004. May I ask which specific lr you implemented.

wangchen1801 commented 5 months ago

Hello, please use the same configuration as in this repository to reproduce the result, otherwise it may not achieve the reported accuracy. And the learning rate should also following the code. Thanks~

goodgoodlearndaydayup commented 5 months ago

您好，请使用与此存储库中相同的配置来重现结果，否则可能无法达到报告的准确性。并且学习率也应该遵循代码。谢谢~

Thanks for your reply!