OWM (Orthogonal Weights Modification)

• Code for paper Continual Learning of Context-dependent Processing in Neural Networks. You can also get the free version from https://rdcu.be/bOaa3

There is a new version based on TF2 https://github.com/xuejianyong/OWM-tf2 provided by Dr. Jianyong Xue, and it basically reproduces our work. Thanks to all researchers who care about and support our work!

Requirements

If the environment configurations are different, the results may vary greatly or even failing to work properly. You may need to adjust the code details according to your needs.

• Linux: Ubuntu 16.04

• cuda9.0 & cudnn6.0

• Python 3.5.4

• torch 0.3.0 (pytorch)

• tensorflow 1.5.0

• tensorflow-gpu 1.4.0

• torchvision 0.2.0

• numpy 1.15.1

• scipy 1.0.0

Acknowledgement

• CAB

• CASIA Chinese Handwriting Databases

• CelebA

• Pytorch

• ResNet

• Tensorflow

• Tensorflow and Chinese Handwritten Chinese Character Recognition