• Search by Module
• Search by Words
• Search Projects

• Java
• Python
• JavaScript
• TypeScript
• C++
• Scala
• Blog

• deep_metric_learning-master
  • evaluation.py
  • n_pair_mc_cars196.yaml
  • main_lifted_struct_loss.py
  • proxy_nca_cars196.yaml
  • LICENSE
  • main_clustering_loss.py
  • lib
    • datasets
      • cub200_2011_converter.py
      • data_provider.py
      • cub200_2011_dataset.py
      • cub200_2011_downloader.py
      • cars196_dataset.py
      • online_products_dataset.py
      • online_products_downloader.py
      • random_fixed_size_crop_mod.py
      • __init__.py
      • cars196_converter.py
      • cars196_downloader.py
      • online_products_converter.py
    • functions
      • proxy_nca_loss.py
      • n_pair_mc_loss.py
      • lifted_struct_loss.py
      • angular_loss.py
      • clustering_loss.py
      • __init__.py
    • models
      • simple_convnet.py
      • googlenet.py
      • modified_googlenet.py
      • __init__.py
    • common
      • __init__.py
      • train_eval.py
      • utils.py
  • main_n_pair_mc.py
  • plot_hyperparameters_cub200_2011_n_pair.py
  • main_angular_loss.py
  • config
  • __init__.py
  • README.md
  • tests
    • test_proxy_nca_loss.py
    • test_clustering_loss.py
    • test_n_pairs_mc_loss.py
    • test_googlenet.py
    • test_data_provider.py
    • __init__.py
  • main_proxy_nca.py
  • n_pair_mc_cub200_2011.yaml
  • .gitignore
  • angular_mc_cub200_2011.yaml

Deep Metric Learning

Implementation of several methods for deep metric learning in Chainer v4.2.0.

• Proxy-NCA: No Fuss Distance Metric Learning using Proxies
• N-pair loss: Improved Deep Metric Learning with Multi-class N-pair Loss Objective
• Lifted structure: Deep Metric Learning via Lifted Structured Feature Embedding
• Clustering loss: Deep Metric Learning via Facility Location
• Angular loss: Deep Metric Learning with Angular Loss

Dependencies

pip install cupy==4.2.0 chainer==4.2.0 fuel==0.2.0 tqdm