Implementation of Center Loss in Chainer.

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

• 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

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

• MNIST, only Softmax Loss

• Wen, Yandong, et al. "A discriminative feature learning approach for deep face recognition." European Conference on Computer Vision. Springer International Publishing, 2016.