-
Notifications
You must be signed in to change notification settings - Fork 1.3k
Translate to Chinese: Chap 1 #544
Translate to Chinese: Chap 1 #544
Conversation
…-level-api-branch
…gh-level-api-branch
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Otherwise LGTM
``` | ||
|
||
### 创建Trainer | ||
### 配置训练程序 | ||
训练程序的目的是定义一个训练模型的网络结构.对于线性回归来讲,它就是一个从输入到输出的简单的全连接层。更加复杂的结果,比如卷积神经网络,递归神经网络等会在随后的章节中介绍。训练程序必须返回`平均损失`作为第一个返回值,因为它会被后面反向传播算法所用到。 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
网络结构.对于线性
Incorrect period.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
missed this. I will fix it in the next PR on Chap 4
01.fit_a_line/README.cn.md
Outdated
trainer = fluid.Trainer( | ||
train_func=train_program, | ||
place=place, | ||
optimizer=fluid.optimizer.SGD(learning_rate=0.001)) |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Will need to use the optimizer_func later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Good catch
01.fit_a_line/README.cn.md
Outdated
``` | ||
|
||
![png](./image/train_and_test.png) | ||
|
||
### 应用模型 | ||
## 推测 |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Maybe we should use '预测', although I honestly don't know if that's the go to translation.
No description provided.