This is a reimplementation of Exploring Randomly Wired Neural Networks for Image Recognition

• Python 3.5
• PyTorch==1.0.0
• sklearn, tensorboardX, numpy

ws: python graph/ws.py -k -p
er: python graph/er.py -p
ba: python graph/ba.py -m

python train.py --data <path to ImageNet>  
                --regime <small is True, regular is False>  
                --base_channels <78, 109, 154>

python eval.py --data <path to ImageNet>  
               --regime <small is True, regular is False>  
               --base_channels <78, 109, 154>  
               --model_path <path to trained path

Validation result on Imagenet(ILSVRC2012) dataset:

Xie S, Kirillov A, Girshick R, et al. Exploring randomly wired neural networks for image recognition[J]. arXiv preprint arXiv:1904.01569, 2019.
Seungwon Park