tbmoon / facenet Goto Github PK

View Code? Open in Web Editor NEW

244.0 244.0 67.0 161.1 MB

FaceNet for face recognition using pytorch

License: MIT License

Python 0.50% Jupyter Notebook 99.50%

facenet's People

Contributors

Stargazers

Watchers

Forkers

yosubjeong nigahae suqiu666 hbhinsang zoombapup ngxbac kunsuoh kimsunhwa1 helenligit victoriaqiu qhsoft wanglawrence9995 yumantha sddai benardmulilo noploop lucksong natanielruiz roymor1 yan0409 autohe jarygrace khrlimam washizzle janetakanashi eplatero97 santhosh-ks tyutguolei alice-ren yong6600 chuanxinlan tan1p0p nguyenvq toandaominh1997 kingwpf ojhyun ahmedbesbes gavinic prantik1998 xinranguo xiaonanchong sunshiding kirilcvetkov92 khawar-islam gokulsg taaewoo roberto7766 zjucsxxd lufeng22 55renchen zakerifahimeh mahima8178 hiroforyou chensi521 khd325 paranoidrabbid beyza-yildirim mhrahimzadeh1374 uditanshu23 afaqsaeed sravit1 hassan-ashfaq valerich95 faizkhan49 wumuyu9 luyou-2023

facenet's Issues

Pretrained Model on vggface2

Hello,
I am looking to train this model on my own dataset for which I require a pretrained model on VGGFace2. Can you please make available the pretrained model on the repo?
Thanks

why accuracy of the model is less than 99%?

I wonder why the accuracy of the trained model does not reach 99% described in the paper.
Is it because you chose offline instead of online when choosing hard triplet?

Hi @tbmoon, thank you for providing this codebase. I have spent almost a month trying to reproduce the accuracy on LFW, but with fail. I am using CASIA to train which is smaller than VGGFace2, but other repos claim equally good accuracy even by training with CASIA. So, there is something I am definitely doing wrong. Can you please let me know what hyperparameters you used to train your model?

Thanks.

Line 50 in 4be8e17

res = self.model.classifier(features)

but there is no classifier in resnet34 model on torchvision 0.6.0. What should I write there instead?

Evaluation

please i need to understand the meaning of evaluation metrics calculate_roc calculate accuracy

Why use " labels.append(np.ones(dists.size(0)))" in training? and

    dists = l2_dist.forward(embed_anchor, embed_pos)
    distances.append(dists.data.cpu().numpy())
    labels.append(np.ones(dists.size(0)))
    
    dists = l2_dist.forward(embed_anchor, embed_neg)
    distances.append(dists.data.cpu().numpy())
    labels.append(np.zeros(dists.size(0)))

can you exlpain the code ? what's for?

tbmoon / facenet Goto Github PK

facenet's People

Contributors

Stargazers

Watchers

Forkers

facenet's Issues

Pretrained Model on vggface2

why accuracy of the model is less than 99%?

Accuracy on LFW stuck at 75%

what's the difference between this TripletLoss and pytorch predefined Torch.nn.TripletMarginLoss()

hello，how can i train the facenet in my dataset?could you provide a guide?thank you

Is there pretrained weights available?

No `resnet34.classifier` in torchvision 0.6.0

Evaluation

Why use " labels.append(np.ones(dists.size(0)))" in training? and

Recommend Projects

React

Vue.js

Typescript

TensorFlow

Django

Laravel

D3

Recommend Topics

javascript

web

server

Machine learning

Visualization

Game

Recommend Org

Facebook

Microsoft

Google

Alibaba

D3

Tencent