- 本项目设计了一个简单的神经网络模型来对CIFAR10数据集进行分类
- 神经网络共有三层卷积层,使用Relu作为激活函数
- 使用交叉熵损失函数,用随机梯度下降方法
- 学习率设为0.002,并在训练时更新学习率
- 用训练了150次,最终在测试集上分类的准确率为70.280%
-
Notifications
You must be signed in to change notification settings - Fork 0
GHxdc/CIFAR-10
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
No description, website, or topics provided.
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published