3800多参赛队 第50名
需要gpu加速 速率会快很多
tf官方教程的识别网络结构是一开始全部对图片碾平成一维, 之后过两个全连接层.
我的改进是首先将数据reshape成四维, [batch, h,w,c]. CNN1+dropout+CNN2 256全连接 dropout 0.2 128全连接 68全连接 dropout0.2 10全连接
准确率可以提升从0.86提升到0.91
-
Notifications
You must be signed in to change notification settings - Fork 13
naginoa/Data-mining
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
| Name | Name | Last commit message | Last commit date | |
|---|---|---|---|---|
Repository files navigation
About
机器学习 数据挖掘 案例和竞赛 代码
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published