这篇教程cnn超级参数设置Training Details写得很实用，希望能帮到您。
Training Detailshttps://github.com/weiaicunzai/pytorch-cifar100
I didn't use any training tricks to improve accuray, if you want to learn more about training tricks, please refer to my another repo, contains various common training tricks and their pytorch implementations.
I follow the hyperparameter settings in paper Improved Regularization of Convolutional Neural Networks with Cutout, which is init lr = 0.1 divide by 5 at 60th, 120th, 160th epochs, train for 200 epochs with batchsize 128 and weight decay 5e-4, Nesterov momentum of 0.9.
联合模型适应小数据集的深度学习模型：Union-net: A deep neural network model adapted to small data sets
识别率cifar100Pytorch-cifar100 cifar100精度排行榜cifar100 |
