Home

Awesome

Mxnet-version batch hard triplet loss

Based on <In defense of triplet loss> (https://arxiv.org/abs/1703.07737)

Based on some tricks from omoindrot's repository. (https://github.com/omoindrot/tensorflow-triplet-loss)

Introduction

Architecture

  1. Using resnetV2 to get 128-dimension embeddings
  2. Using triplet loss to train embeddings
  3. the network is defined in resnet.py

Requirements

The code has been tested with CUDA 8.0 and ubuntu 16.04.

how to train:
See parsers in train.py. Then Set your dataset path and some params of based resnet network.
The network has been defined in resnet.py.Batch_hard.py now has been deprecated.