Add lrn layer #9157
Add lrn layer #9157
Conversation
|
|
|
|
As a supplement, doc format standard is in |
python/paddle/fluid/layers/nn.py
Outdated
| k(float): An offset (usually positive to avoid dividing by 0) | ||
| alpha(float): The scaling parameter | ||
| beta(float): The exponent | ||
| name(str): A name for this operation |
There was a problem hiding this comment.
功能介绍部分请简单介绍下LRN，给出参考文献及链接（如果有）。
参数介绍部分，遗漏了input，没有写明默认值，缺少必要的标点。
还存在其他问题。请参考 API注释撰写标准 撰写注释。同时注意语言上的问题。
|
Please add a test for your wrapper. |
doc/fluid/dev/src/fc.py
Outdated
| **Local Response Normalization Operator** | ||
|
|
||
| This operator comes from the paper: | ||
| <<ImageNet Classification with Deep Convolutional Neural Networks>>. |
There was a problem hiding this comment.
参考文献 请移动至 参数介绍前，另去掉书名号，加上文献链接。
此处请添加 功能介绍。
There was a problem hiding this comment.
1.参考文献 请移动至 公式符号介绍后，参数介绍前。
2. 补充功能介绍
doc/fluid/dev/src/fc.py
Outdated
| k(float, default 2.0): An offset (usually positive to avoid dividing by 0). | ||
| alpha(float, default 1e-4): The scaling parameter. | ||
| beta(float, default 0.75): The exponent. | ||
| name(str, default None): A name for this operation. |
There was a problem hiding this comment.
L105 不要使用 简写 如 dims
L105~L110 参数名和括号间请加一个空格。
doc/fluid/dev/src/lrn.py
Outdated
|
|
||
| data = fluid.layers.data(name="data", shape=[3, 112, 112], dtype="float32") | ||
| lrn = fluid.layers.lrn(input=data) | ||
| """ |
There was a problem hiding this comment.
Please delete this file.
python/paddle/fluid/layers/nn.py
Outdated
| """ | ||
| **Local Response Normalization Operator** | ||
|
|
||
| Refer to `ImageNet Classification with Deep Convolutional Neural Networks |
There was a problem hiding this comment.
- 请补充api的功能介绍。
- 参考文献 放置 参数介绍前 公式符号介绍后。
| Args: | ||
| input (Variable): The input tensor of this layer, and the dimension of input tensor must be 4. | ||
| n (int, default 5): The number of channels to sum over. | ||
| k (float, default 1.0): An offset (usually positive to avoid dividing by 0). |
|
@luotao1 注释的格式差不多了，你看下内容、表达上怎么样？ |
|
@ranqiu92 内容上由 @qingqing01 把关即可。 |
|
@luotao1 Sure, I will review it ASAP. |
There was a problem hiding this comment.
@luotao1 Most of the documentation is good. There is a small suggestion. Please fix that before merging. Thank you for the great PR!
python/paddle/fluid/layers/nn.py
Outdated
|
|
||
| def lrn(input, n=5, k=1.0, alpha=1e-4, beta=0.75, name=None): | ||
| """ | ||
| Local Response Normalization Layer. This layer performs a kind of |
Now the LRN is not exported to Python, I add a LRN layer in nn.py, please have a look.