Tallisgo
Tallisgo
> Look at utils/face_datasets.py line 333. The ignoring small faces is in data preparation. @wjtan99 hello, can you share the value of ignore_small?
Thanks for your reply @VainF. Maybe I just do this. The pipeline is below: 1. train and save a model 2. initial a model with the saved weight 3. use...
> Hello, > > First of all Thank you for this great repository, great work > > And, I could not find the face alignment code and implemented it myself...
改成320 *320的话，anchor size的大小是不是也应该改变
你有找到相关代码吗？如果有的话，能不能分享一下
> 1.类别的起始下标为0不是1，例如单类的话类别下标都为0，多类的话0为起始，例如20类，则.txt中的类别下标为0,1,2,3,...19 2.是的，classes为类别数目 3.训练单类模型cls loss为0是正常的 大佬， 为什么训练单类模型 cls loss 一直是0为啥是正常的呀