-
Notifications
You must be signed in to change notification settings - Fork 128
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
【深度学习】调参、调优、剪枝、模型压缩、结构设计 #2
Comments
调参【荐】
[6]:
超()参数:
【2】: 作者:autocyz 一、weight decay(权值衰减)的使用既不是为了提高你所说的收敛精确度也不是为了提高收敛速度,其最终目的是防止过拟合。在损失函数中,weight decay是放在正则项(regularization)前面的一个系数,正则项一般指示模型的复杂度,所以weight decay的作用是调节模型复杂度对损失函数的影响,若weight decay很大,则复杂的模型损失函数的值也就大。 二、momentum是梯度下降法中一种常用的加速技术。对于一般的SGD,其表达式为,沿负梯度方向下降。而带momentum项的SGD则写生如下形式:
三、normalization。如果我没有理解错的话,题主的意思应该是batch normalization吧。batch normalization的是指在神经网络中激活函数的前面,将 |
模型压缩
|
No description provided.
The text was updated successfully, but these errors were encountered: