Yang Yang

Samples of eval always be —— pixAcc: 100.000, mIoU: 50.000

6


Train Parameters

7

你好，我想请问一下具体是在多少个epoch后做finetune的呢，finetune的学习率和步长具体是多少呢？ 我在640 * 640的输入上做训练，使用lr_step为90、120，lr为5e-4，batch_size为8。之后将140的epoch取出，送入第二步做finetune，输入尺寸为800 * 800，使用lr_step为30、60，lr为5e-4，batch_size为8。 训练结果为  1.First train with the size of 640×640/514×514 2.Then fine tune with the size of 800×800 3.For the easy and hard part, s...

https://github.com/lbin/Retinaface_Detectron2/blob/579e500b35efac6afc389dfc9bbea0b129e91ba6/mmdet/modeling/meta_arch/retinaface.py#L16

RuntimeError: Error building extension '_prroi_pooling'

1

Thanks for your great work. I want to know what version your CUDA and Torch versions are. When I used torch1.9 with cuda 11.1, error shows "subprocess.CalledProcessError: Command '['ninja', '-v']'...