Skip to content
体验新版
项目
组织
正在加载...
登录
切换导航
打开侧边栏
TonyTonyFun
Paddle
提交
fb87df66
P
Paddle
项目概览
TonyTonyFun
/
Paddle
与 Fork 源项目一致
Fork自
PaddlePaddle / Paddle
通知
1
Star
0
Fork
0
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
0
列表
看板
标记
里程碑
合并请求
0
Wiki
0
Wiki
分析
仓库
DevOps
项目成员
Pages
P
Paddle
项目概览
项目概览
详情
发布
仓库
仓库
文件
提交
分支
标签
贡献者
分支图
比较
Issue
0
Issue
0
列表
看板
标记
里程碑
合并请求
0
合并请求
0
Pages
分析
分析
仓库分析
DevOps
Wiki
0
Wiki
成员
成员
收起侧边栏
关闭侧边栏
动态
分支图
创建新Issue
提交
Issue看板
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
fb87df66
编写于
4月 21, 2022
作者:
R
RichardWooSJTU
提交者:
GitHub
4月 21, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix nms op docs (#41792)
* fix nms op doc missing default value
上级
9db6c762
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
8 addition
and
7 deletion
+8
-7
python/paddle/vision/ops.py
python/paddle/vision/ops.py
+8
-7
未找到文件。
python/paddle/vision/ops.py
浏览文件 @
fb87df66
...
@@ -1399,26 +1399,27 @@ def nms(boxes,
...
@@ -1399,26 +1399,27 @@ def nms(boxes,
IoU = \frac{intersection\_area(box1, box2)}{union\_area(box1, box2)}
IoU = \frac{intersection\_area(box1, box2)}{union\_area(box1, box2)}
If scores are provided, input boxes will be sorted by their scores firstly.
If scores are provided, input boxes will be sorted by their scores firstly.
If category_idxs and categories are provided, NMS will be performed with a batched style,
If category_idxs and categories are provided, NMS will be performed with a batched style,
which means NMS will be applied to each category respectively and results of each category
which means NMS will be applied to each category respectively and results of each category
will be concated and sorted by scores.
will be concated and sorted by scores.
If K is provided, only the first k elements will be returned. Otherwise, all box indices sorted by scores will be returned.
If K is provided, only the first k elements will be returned. Otherwise, all box indices sorted by scores will be returned.
Args:
Args:
boxes(Tensor): The input boxes data to be computed, it's a 2D-Tensor with
boxes(Tensor): The input boxes data to be computed, it's a 2D-Tensor with
the shape of [num_boxes, 4] and boxes should be sorted by their
the shape of [num_boxes, 4]. The data type is float32 or float64.
confidence scores. The data type is float32 or float64.
Given as [[x1, y1, x2, y2], …], (x1, y1) is the top left coordinates,
Given as [[x1, y1, x2, y2], …], (x1, y1) is the top left coordinates,
and (x2, y2) is the bottom right coordinates.
and (x2, y2) is the bottom right coordinates.
Their relation should be ``0 <= x1 < x2 && 0 <= y1 < y2``.
Their relation should be ``0 <= x1 < x2 && 0 <= y1 < y2``.
iou_threshold(float32): IoU threshold for determine overlapping boxes. Default value: 0.3.
iou_threshold(float32
, optional
): IoU threshold for determine overlapping boxes. Default value: 0.3.
scores(Tensor, optional): Scores corresponding to boxes, it's a 1D-Tensor with
scores(Tensor, optional): Scores corresponding to boxes, it's a 1D-Tensor with
shape of [num_boxes]. The data type is float32 or float64.
shape of [num_boxes]. The data type is float32 or float64.
Default: None.
category_idxs(Tensor, optional): Category indices corresponding to boxes.
category_idxs(Tensor, optional): Category indices corresponding to boxes.
it's a 1D-Tensor with shape of [num_boxes]. The data type is int64.
it's a 1D-Tensor with shape of [num_boxes]. The data type is int64.
Default: None.
categories(List, optional): A list of unique id of all categories. The data type is int64.
categories(List, optional): A list of unique id of all categories. The data type is int64.
Default: None.
top_k(int64, optional): The top K boxes who has higher score and kept by NMS preds to
top_k(int64, optional): The top K boxes who has higher score and kept by NMS preds to
consider. top_k should be smaller equal than num_boxes.
consider. top_k should be smaller equal than num_boxes.
Default: None.
Returns:
Returns:
Tensor: 1D-Tensor with the shape of [num_boxes]. Indices of boxes kept by NMS.
Tensor: 1D-Tensor with the shape of [num_boxes]. Indices of boxes kept by NMS.
...
...
编辑
预览
Markdown
is supported
0%
请重试
或
添加新附件
.
添加附件
取消
You are about to add
0
people
to the discussion. Proceed with caution.
先完成此消息的编辑!
取消
想要评论请
注册
或
登录