A trusty face recognition research platform developed by Tencent Youtu Lab

Thanks for the CIFP work on CVPR2021, it's very impressive! I'd like to check about the hyper-parameter setting. As mentioned in the paper, ru+ is set to be 1e-4 according to the experiment. However, in the code of cifp.py, I didn't find any definition of it. Could you please offer some instruction on this?

Hi, first of all, thanks for your work.

I decided to test it with pre-trained model and some own real images. I run eval.py demo to check it out. But I am confused with the results of quality scores.

1. What ranges of quality score values can be considered as low, medium, high for SDD_FIQA_checkpoints_r50.pth model?

Referring to the paper, Fig3, I can guess the following value [low: 0 - 35, medium: 36 - 48, high: 49 - 100]. So I wonder to hear your suggestion about it.

2. Do these ranges depend on the model? It seems that yes, but correct me if I am wrong.

3. Did you performed experiments with face occlusion, how its robust on it?

IMHO, there is no rough thresholds which separate low vs medium vs high sub-ranges, there are some overlaps between them. And these overlaps make me feeling that there is not clear enough quality scores dependency between low, medium and high quality face images.

Thanks~

Thank you very much for this work！

Inconsistent quantities caused the loading to fail. Do you know why? Thanks~

• tasks/distfc/README.md IR101 pretrained model: OrderedDict len is 672
• torchkit/backbone/model_irse.py IR101：OrderedDict len is 917

Im very interested in your project. So can you share with me a sample or structure about the dataset. I don't know how to created it. Thank you so much!

sh ./train.sh -1 "/home/adesoji/tfaceenv/TFace-master/security/tasks/Face-Anti-Spoofing/DCN/configs" 5000

Running this command below resulted intoAssertion Error, how do i correct this? /home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/launch.py:178: FutureWarning: The module torch.distributed.launch is deprecated and will be removed in future. Use torchrun. Note that --use_env is set by default in torchrun. If your script expects --local_rank argument to be set, please change it to read from os.environ['LOCAL_RANK'] instead. See https://pytorch.org/docs/stable/distributed.html#launch-utility for further instructions

warnings.warn( Traceback (most recent call last): File "/usr/lib/python3.10/runpy.py", line 196, in _run_module_as_main return _run_code(code, main_globals, None, File "/usr/lib/python3.10/runpy.py", line 86, in _run_code exec(code, run_globals) File "/home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/launch.py", line 193, in main() File "/home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/launch.py", line 189, in main launch(args) File "/home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/launch.py", line 174, in launch run(args) File "/home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/run.py", line 752, in run elastic_launch( File "/home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 131, in call return launch_agent(self._config, self._entrypoint, list(args)) File "/home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/launcher/api.py", line 214, in launch_agent spec = WorkerSpec( File "", line 15, in init File "/home/adesoji/tfaceenv/lib/python3.10/site-packages/torch/distributed/elastic/agent/server/api.py", line 87, in post_init assert self.local_world_size > 0 AssertionError

Running the train.py script ion ubuntu 20.04, python 3.8, i have this error written below

FileNotFoundError: [Errno 2] No such file or directory: '/home/adesoji/TFace-master/TFace-master/security/tasks/Face-Anti-Spoofing/ANRL/configs/train.yaml'

Kindly provide this config file

Recently, I am reproducing your paper--ANRL. I have four datasets(I&C&M&O), and train a model based on your source code. In I&C&m to O task, the EER of O is above 0.3, while in the training dataset, the EER is very low, below 0.001. I don't know why. Can you provide me a pretrained model.

I train models in multi-GPUs(4 gpus here) behavior. But once I tried to load pretrained model, the nvidia-smi shown that another 4 redundant processes(8 processes in total) occupied the GPU 0, while not loading pretrained model those processes disappeared(4 process in total). Those redundant processes increase along with the GPU numbers you use, and due to small number of batch size in sum. And could you let me known how to keep redundant processes from appearing when train using multi-GPUs and loading pretrained model?

Thank you for perfect repository <3

• I see that you implemented many papers in task directory. I see training code but I cannot see any example code to run that model
• Can you show me how to run with pre-trained model in TFace/tasks/cifp/ ? (Extract feature + verify)
• Thank you so much

When I run local_train.sh, it returns the error below:

Traceback (most recent call last):
  File "./tasks/cifp/train_cifp.py", line 9, in <module>
    from ..localfc.train_localfc import TrainTask
ImportError: attempted relative import with no known parent package
Traceback (most recent call last):
  File "./tasks/cifp/train_cifp.py", line 9, in <module>
    from ..localfc.train_localfc import TrainTask
ImportError: attempted relative import with no known parent package
Traceback (most recent call last):
  File "./tasks/cifp/train_cifp.py", line 9, in <module>
    from ..localfc.train_localfc import TrainTask
ImportError: attempted relative import with no known parent package
Traceback (most recent call last):
  File "/root/miniconda3/lib/python3.8/runpy.py", line 194, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/root/miniconda3/lib/python3.8/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 260, in <module>
    main()
  File "/root/miniconda3/lib/python3.8/site-packages/torch/distributed/launch.py", line 255, in main
    raise subprocess.CalledProcessError(returncode=process.returncode,
subprocess.CalledProcessError: Command '['/root/miniconda3/bin/python', '-u', './tasks/cifp/train_cifp.py', '--local_rank=7']' returned non-zero exit status 1.

The content of my local_train.sh is:

#!/bin/bash

if [ ! -d "logs" ]; then
    mkdir logs
fi
export CUDA_VISIBLE_DEVICES='2'
nohup python -u -m torch.distributed.launch --nproc_per_node=8 --nnodes=1 ./tasks/cifp/train_cifp.py > logs/$(date +%F-%H-%M-%S).log 2>&1 &

复现时出现如下问题，可否提供一下celedf的目录结构呢？ 按原始版本celedf-v2的目录结构会出现确认错误的问题

自己按每个文件名建立文件夹再放进去后不会再报这个确认的错，但是会在下面标签的地方报错

应该是目录结构和作者不匹配，望有大佬能告知如何处置

另外请问下这个代码好像不用自己抽帧吧？

您好，因为git中未公开教师模型IR50的权重，所以我在其他的git上面找了一个测试结果差不多的权重，在基于mobilefacenet复现结果时，发现结果无法对齐，在CFP和CPLFW两个测试集上差距较大，CFP复现结果为91.97%，CPLFW复现结果为86.6%，都与论文给出的结果相差2%以上？请问是什么原因呢？ 另外，我发现论文中的一些超参数和代码中默认的超参数并未完全一致，如： epoch数（论文中为28，代码中为26） learning rate schedule（论文中为10,18,24；代码中为10,18,22） margin m（论文中为0.5；代码中为0.4）

我分别使用了论文中的超参数和代码中的超参数训练后，发现结果还是无法对齐，请问可能是什么原因呢

很感谢你们的开源代码，但是我在复现dctdp这篇文章的时候发现，代码里面对于图像加的噪声十分小，然后，我对他进行了逆DCT变换，结果发现加入的噪声对于最终图像基本没有影响，另外，由于设备的原因，我无法完全重现论文中的实验过程，但是，我用相同的方法在另一个小型的数据集上进行了实验，发现，如果去除了图像的DC通道，将会对实验结果有着非常严重的影响，我想知道，噪声加入的那么小是否合适？另外，去除DC通道是只有在人脸图像上才有效果吗？

您好，想请问一下

1. train.py是用TFace/recognition下面的，还是TFace/recognition/tasks/ekd，因为我看好像TFace/recognition/tasks/ekd/train.py并不支持一些功能，比如混合精度
2. dataloader的sampler采用了BalancedBatchSampler，并不是DistributedSampler，而且里面也没有类似分布式的操作，这样意味着每个worker读的数据都是一样的吗