Implementation of Center Loss in Chainer
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
img
util
.gitignore
README.md
center_loss.py
model.py
train_mnist.py

README.md

Chainer Center Loss

Implementation of Center Loss in Chainer.

Requirements

  • Python 3.5.1
  • Chainer 2.0.0
  • CuPy 1.0.0 (if use GPU)
  • Matplotlib

How to train

  • with CPU and use center loss
python train_mnist.py --batchsize 32 --epoch 20 --centerloss
  • with GPU and use center loss
python train_mnist.py --batchsize 32 --epoch 20 --gpu 0 --centerloss

Visualize the result

  • MNIST, Softmax Loss + Center Loss
    The white dots denote 10 class centers of deep features.

Figure 1

  • MNIST, only Softmax Loss

Figure 2

Reference