doantienthongbku / implementation-patchnet Goto Github PK

It seems like the original authors have abandoned this codebase. I'm working on improving this code in my fork https://github.com/filonenkoa/fas-patchnet. Feel free to request features there. The code is not backwards compatible with the current repo. The main goal of the fork is to make this code work on multiple GPUs and with multiple datasets at once.

Improvements to the original repository

• More augmentations (torchvision ➞ albumentations)
• TurboJPEG support for faster image decoding
• DDP support
• Multiple datasets training
• Utility to convert datasets
• Compute FAS-related metrics (ACER, etc.)
• Incorporate loss into a model (the whole inference can be exported to a single ONNX file)
• Telegram reports
• Compute metrics for each val dataset separately
• Split validation into miltiple GPUs
• Balanced sampler suitable for DDP
• Conversion to ONNX

Hi,

Do you have the datasets that authors used in their paper. Particularly OULU-NPU and Idiap Replay-Attack datasets, since the owners of these datasets may no long maintain their website. It would be nice if you can share them!

Thanks

Thanks for Great code.

I found some errors. After inference network, shape is not matched with fc layer in loss. In loss func, fc layer need 1024 in features, but shape is not 1024. Can you check it?? Thx

Hi all, I can not understand why for each frame of a video we do redundant transformation (3 times)?

                    for i in range(3):
                        image = cv2.cvtColor(src, cv2.COLOR_BGR2RGB)
                        image = transform(image)
                        image = image.unsqueeze(0)
                        feature = network.forward(image)
                        feature = F.normalize(feature, dim=1)
                        score = F.softmax(loss.amsm_loss.s * loss.amsm_loss.fc(feature.squeeze()), dim=0)
                        score_lst.append(score)

the score_lst is always the same at the end of the loop. I don't know why? please could you explain it?

Hello! thanks for the great code and I have a question:
did you do the same test (Intra-Dataset Testing or Cross-Dataset Testing ) as the original paper did? And did you get similar testing result as the result in the paper? Thanks a lot!