Hardness-Aware Deep Metric Learning (CVPR2019) in pytorch
License: MIT License
This is an unofficial implementation of "Hardness-Aware Deep Metric Learning" (CVPR 2019 Oral) in Pytorch.
cd pytorch-hdml
pip install pipenv
pipenv install
cd data
python cars196_downloader.py
python cars196_converter.py
Execute a training script. When executed, the tensorboard log is saved.
pipenv shell
python train_triplet.py
Official tensorflow implementation https://github.com/wzzheng/HDML
Reconstruction loss is calculated between the embeddings (embedding_yp - embedding_y_orig).pow(2).sum()) which are the output of FC layers. Should the embeddings not be normalized before calculating the loss? I am getting very high reconstruction loss and nans.
In the file HDML.py line 71, according to the equation in the paper and the official implementation (https://github.com/wzzheng/HDML/blob/master/lib/HDML.py), the entire numerator should be divided by dist_neg.
Please correct me if I am wrong.
Thank you for your work！What's the result you can reproduce? Can you achieve the results in the paper?
React
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
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
Django
The Web framework for perfectionists with deadlines.
Laravel
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.
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft
Open source projects and samples from Microsoft.
Google
Google ❤️ Open Source for everyone.
Alibaba
Alibaba Open Source for everyone
D3
Data-Driven Documents codes.
Tencent
China tencent open source team.