wujiyang/Face_Pytorch
face recognition algorithms in pytorch framework, including arcface, cosface, sphereface and so on
PythonApache-2.0
Issues
- 0
Who have CASIA-WebFace-112*112 dataset
#66 opened by aizsa2022 - 0
Softmax Loss 可视化效果图如何绘制
#65 opened by Lin-plax - 0
Problem with datasets
#64 opened by dparreslpb - 11
关于train accuracy
#52 opened by QuasarLight - 3
webface_align_train.list
#58 opened by chidaidai - 3
- 1
train accuracy
#30 opened by luluvi - 0
readme.md 单词怕错误矫正
#62 opened by lying2020 - 0
aligned evaluation dataset with google drive link
#59 opened by ohsai - 2
Visdom successfully connected to server '>' not supported between instances of 'float' and 'NoneType' Traceback (most recent call last): File "e:/AI-pro/Insightface/Face_Pytorch-master/train_my.py", line 263, in <module> train(args) File "e:/AI-pro/Insightface/Face_Pytorch-master/train_my.py", line 155, in train total_loss.backward() File "C:\Users\Administrator\Anaconda3\lib\site-packages\torch\tensor.py", line 107, in backward torch.autograd.backward(self, gradient, retain_graph, create_graph) File "C:\Users\Administrator\Anaconda3\lib\site-packages\torch\autograd\__init__.py", line 93, in backward allow_unreachable=True) # allow_unreachable flag RuntimeError: cuda runtime error (59) : device-side assert triggered at C:/w/1/s/windows/pytorch/aten/src\THC/generic/THCTensorMath.cu:26
#50 opened by smartparrot - 0
How to draw roc?
#61 opened by Wblossom - 13
使用您的代码,我在lfw的得分可以达到99.6,但是实际应用场景会出现大批量的认错
#43 opened by frankqianghe - 0
Pretrainned model download
#60 opened by ld-ma - 4
what is the labels of casia webface dataset
#36 opened by Pattaro - 2
- 1
About the soft margin in the ArcLoss
#44 opened by leon0n - 0
Can you explain What easy_margin means?
#57 opened by kdh4672 - 0
- 0
Improved Residual Bottlenecks
#55 opened by Ontheway361 - 0
CFP-FP Dataset
#54 opened by saadshakeel12345 - 2
- 1
Training epochs for MobileFaceNet
#19 opened by lymanblue - 5
学习率0.00001?是不是有点小啊
#25 opened by ZCCDL - 2
- 1
About megaface performance
#31 opened by renyanfei12321 - 1
How long does it take to train ?
#33 opened by liujianzhao6328057 - 0
How to use sphere face?
#53 opened by sunshiding - 0
- 1
A-softmax loss中,正向传播时W是否需要更新为W = norm(W)?
#38 opened by nbl97 - 2
- 0
ResNet100-based model
#48 opened by naviocean - 0
parameter:scale size
#45 opened by huangzhenjie - 1
How to undersatand the weight?
#41 opened by taylover-pei - 0
Line 52, margin/sphereMarginProduct
#42 opened by neverUseThisName - 0
about attention net result
#40 opened by derronqi - 0
- 0
softmax doesn't work?
#37 opened by pjm19951013 - 0
arcface backbone to tensorrt
#35 opened by guangdongliang - 0
- 1
- 0
How exactly do I implement sphereface?
#29 opened by giuliasilvestro - 0
train.list里面存放的路径到图片那级吗
#27 opened by SenrongJi - 2
关于数据集格式的问题
#26 opened by SenrongJi - 0
学习率是不是有点小啊?0.0000
#24 opened by ZCCDL - 4
What does the 600 means?
#22 opened by JiaquanYe - 2
关于A-softmax的知识点问题
#21 opened by woshildh - 3
The question about DeepGlint MS-Celeb-1M
#20 opened by tangyuanhenyuan - 4
RuntimeError: size mismatch
#17 opened by Sotatek-HoangTran - 7
- 1
Question about training epochs
#16 opened by lymanblue