huguesva/face-anti-spoofing-neural-network

Implementation of "Learning Deep Models for Face Anti-Spoofing: Binary or Auxiliary Supervision" in PyTorch.

face-anti-spoofing-neural-network's Issues

Where can I call gen_anchor function? Thanks for reading issues

Why have we chosen 850 as an offset. ('#We will take 850 as offset')

I am obtaining the offset values between '85 to 115' for live and fake images. What possibly could be the reason behind it? Also, why have we selected 850 as our offset value?

Can you share the pretrained network?

Hi there

I wonder if you can share the pretrained network with me @huguesva ?

I need to validate my results with benchmarks provided in this paper.

Can you share with me the Oulu-NPU dataset?

Could you please share your OULU dataset?

I've required the OULU dataset for over a month without any reply. Could you please share your OULU dataset? Thank you very much.
My email : [email protected]

Cannot find gen_anchor() function in utils.paf of 3DDFA

I haven't found gen_anchor() function in this file utils.paf (https://github.com/cleardusk/3DDFA/blob/master/utils/paf.py). @huguesva Can you please help me?

Face-Anti-Spoofing-Neural-Network/data_processing/data_process2.py

Line 139 in b1cb3a3

Anchor = gen_anchor(param=param,kernel_size=args.paf_size)

README

@huguesva Can you update READMEand upload models and dataset if possible ? Also provide info on accuracy

Depth Image Obtained From Spoof Images

Hello,

I would like to ask you about the depth images.

At the first glance, I've tested the depth images which is generated from this repo. https://github.com/cleardusk/3DDFA.

It's obvious that the model performs can generate the depth map for every case including genuine/spoof images.

Do we need do apply further post-processing to obtain the 3D-shape images for real and non 3D-shape images for spoof?

Thank you in advanced.

Question about package utils

Thanks for sharing this. But where is the package utils?

The parameter 'net' isn't defined

Thank you for sharing your work.But the parameter 'net' (in Project_Spoofing ) isn't defined.Could you please help me with this?