-
Notifications
You must be signed in to change notification settings - Fork 672
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
【Hackathon 6th No.16】为 Paddle 新增 LPPool1D / LPPool2D API #6639
base: develop
Are you sure you want to change the base?
Conversation
Asthestarsfalll
commented
May 8, 2024
- 【Hackathon 6th No.16】为 Paddle 新增 LPPool1D / LPPool2D API -part Paddle#63544
感谢你贡献飞桨文档,文档预览构建中,Docs-New 跑完后即可预览,预览链接:http://preview-pr-6639.paddle-docs-preview.paddlepaddle.org.cn/documentation/docs/zh/api/index_cn.html |
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.
在 paddle.nn.Overview 加一下描述
- **norm_type** (int|float):幂平均池化的指数,不可以为 0。 | ||
- **kernel_size** (int|list|tuple):池化核大小。如果它是一个元组或列表,它必须包含两个整数值,(pool_size_Height, pool_size_Width)。若为一个整数,则它的平方值将作为池化核大小,比如若 pool_size=2,则池化核大小为 2x2。 | ||
- **stride** (int|list|tuple,可选):池化层的步长。如果它是一个元组或列表,它将包含两个整数,(pool_stride_Height, pool_stride_Width)。若为一个整数,则表示 H 和 W 维度上 stride 均为该值。默认值为 None,这时会使用 kernel_size 作为 stride。 | ||
- **padding** (str|int|list|tuple,可选) 池化填充。如果它是一个字符串,可以是"VALID"或者"SAME",表示填充算法,计算细节可参考上述 pool_padding = "SAME"或 pool_padding = "VALID" 时的计算公式。如果它是一个元组或列表,它可以有 3 种格式:(1)包含 2 个整数值:[pad_height, pad_width];(2)包含 4 个整数值:[pad_height_top, pad_height_bottom, pad_width_left, pad_width_right];(3)包含 4 个二元组:当 data_format 为"NCHW"时为 [[0,0], [0,0], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right]],当 data_format 为"NHWC"时为[[0,0], [pad_height_top, pad_height_bottom], [pad_width_left, pad_width_right], [0,0]]。若为一个整数,则表示 H 和 W 维度上均为该值。默认值:0。 |
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.
计算细节可参考上述 pool_padding = "SAME"或 pool_padding = "VALID" 时的计算公式。
上述的 pool_padding 是啥
input(N_i, C_j, stride[0] \times h + m, stride[1] \times w + n)^{norm\_type})^{1 / norm\_type} | ||
|
||
|
||
参数 |
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.
这边的参数的一些描述也和英文对齐吧,比如 pool_size_Height
..