deepcam-cn / Face-Anti-spoofing.pytorch

Train code of face anti-spoofing with a single RGB frame

Home Page:https://deepcam.com/

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

安卓demo 和训练的模型的效果好像不一样啊

smartwell opened this issue · comments

首先非常非常感谢,作者的开源精神,再次感谢.
我运行了安卓的demo,效果是很好的,也看了一下输出的信息,想不明白为何要keep static 呢? 感觉安卓demo和训练的模型运行机制不一样啊,
我训练了模型,也理解了作者的意图,引入了depth 信息,但是测试的时候效果不及安卓demo,还请大佬指点一下

是不是multi frame 模式

Android demo中的模型是使用更多的数据训练出来的模型

The model in the Android demo is a model trained with more data

How many samples did you train the model?

@smartwell did you train successfully with the model?

yes, no problem

@smartwell did you train successfully with the model?

the face samples cames from author. i can train this model.