深度学习超参数设置技巧:(论文 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. You could also use the hyperparameters from paper Regularizing Neural Networks by Penalizing Confident Output Distributions and Random Erasing Data Augmentation, which is initial lr = 0.1, lr divied by 10 at 150th and 225th epochs, and training for 300 epochs with batchsize 128, this is more commonly used. You could decrese the batchsize to 64 or whatever suits you, if you dont have enough gpu memory.
数据集增强技巧之一:用训练好的模型,进行筛选其他效果不好的数据集的图片,筛选之后再次加入训练集,以扩充训练集。
查看效果时,可以看总体平均效果,分类时,可以看哪一类错误率最高,以找出原因