tbmoon / facenet Goto Github PK
View Code? Open in Web Editor NEWFaceNet for face recognition using pytorch
License: MIT License
FaceNet for face recognition using pytorch
License: MIT License
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
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.
what's the difference between this TripletLoss and pytorch predefined Torch.nn.TripletMarginLoss()
In following line you've written:
Line 50 in 4be8e17
torchvision 0.6.0
. What should I write there instead?please i need to understand the meaning of evaluation metrics calculate_roc calculate accuracy
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?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.