提交 c65ce7cb 编写于 作者: L liaogang

Update

上级 7288e3ed
......@@ -341,8 +341,9 @@ parameters = paddle.parameters.create(cost)
### Construct Trainer
Before jumping into creating a training module, algorithm setting which is defined as `paddle.optimizer` is also necessary.
Here we specified `Momentum` optimization algorithm and its batch size, learning rate, momentum and L2 regularization.
Before jumping into creating a training module, algorithm setting is also necessary.
Here we specified `Momentum` optimization algorithm and its batch size, learning rate, momentum and L2 regularization
via `paddle.optimizer`.
```python
# Create optimizer
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册