FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019

FeatherNets_Face-Anti-spoofing-Attack-Detection-Challenge-CVPR2019 copied to clipboard

smsver2

Pretained model google link is down.

1

I tried to download the preatined model from the google link, but it's look like is down.

darich10

Hello, I am trying to train FeatherNetB model, but I meet a problem. This is the error. Input image size: 224, test size: 224 + Number of FLOPs: 83.05M The...

1303463822

ir效果对比

3

嗨，你好，最近在复现你们的工作，使用depth图的时候，我的最好效果比文章中只用CASIA数据集还要好一点，但是只使用ir时的效果会很差，这是可以理解的，所以想问下，你们用ir单独训练的效果在验证集上的结果。同时，在训练depth和ir中均出现了严重的过拟合，网络会把召回率降为0，但此时查准率就会变差很多，而且不同模型都是这个趋势，请问，有什么思路解决嘛？

riskeverything

测试一张普通照片或者深度图,是否需要把人脸扣出来?

2

CASIA-SURF的数据集图片的人脸有进行抠图, 那么实际测试场景要不要也要对图片人脸进行抠图处理?

yangjian1218

Running  python3 fileList.py Traceback (most recent call last): File "fileList.py", line 78, in for line in fileinput.input("test_private_list.txt"): File "/home/adesoji/viper/envs/feather_env/lib/python3.6/fileinput.py", line 250, in __next__ line = self._readline() File "/home/adesoji/viper/envs/feather_env/lib/python3.6/fileinput.py",...

Adesoji1

not able to access Pretrained models with the given link of Baidu. Please provide GoogleDrive link.

2

Naveen1023

hi, I tried the google drive link, but it says you need access and when I try to request it says couldn't send the request. can anyone email me the...

omid-ahmadieh

ivanfadillahgdp

Aruen24