摘要: 1. start small 2. gradually increase the model size 3. small parameter, deep is better than wider; deep network is hard to optimize, 使用resnet的思想进行优化 4 阅读全文
posted @ 2019-01-23 10:07 pprp 阅读(1939) 评论(0) 推荐(0) 编辑