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
s920243400
PaddleDetection
提交
f0177a1e
P
PaddleDetection
项目概览
s920243400
/
PaddleDetection
与 Fork 源项目一致
Fork自
PaddlePaddle / PaddleDetection
通知
2
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
PaddleDetection
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
提交
f0177a1e
编写于
3月 05, 2019
作者:
J
jerrywgz
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
refine doc, test=develop
上级
21e0d35c
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
12 addition
and
10 deletion
+12
-10
paddle/fluid/API.spec
paddle/fluid/API.spec
+1
-1
python/paddle/fluid/layers/detection.py
python/paddle/fluid/layers/detection.py
+11
-9
未找到文件。
paddle/fluid/API.spec
浏览文件 @
f0177a1e
...
@@ -328,7 +328,7 @@ paddle.fluid.layers.polygon_box_transform (ArgSpec(args=['input', 'name'], varar
...
@@ -328,7 +328,7 @@ paddle.fluid.layers.polygon_box_transform (ArgSpec(args=['input', 'name'], varar
paddle.fluid.layers.yolov3_loss (ArgSpec(args=['x', 'gtbox', 'gtlabel', 'anchors', 'anchor_mask', 'class_num', 'ignore_thresh', 'downsample_ratio', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '991e934c3e09abf0edec7c9c978b4691'))
paddle.fluid.layers.yolov3_loss (ArgSpec(args=['x', 'gtbox', 'gtlabel', 'anchors', 'anchor_mask', 'class_num', 'ignore_thresh', 'downsample_ratio', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '991e934c3e09abf0edec7c9c978b4691'))
paddle.fluid.layers.box_clip (ArgSpec(args=['input', 'im_info', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '397e9e02b451d99c56e20f268fa03f2e'))
paddle.fluid.layers.box_clip (ArgSpec(args=['input', 'im_info', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '397e9e02b451d99c56e20f268fa03f2e'))
paddle.fluid.layers.multiclass_nms (ArgSpec(args=['bboxes', 'scores', 'score_threshold', 'nms_top_k', 'keep_top_k', 'nms_threshold', 'normalized', 'nms_eta', 'background_label', 'name'], varargs=None, keywords=None, defaults=(0.3, True, 1.0, 0, None)), ('document', 'ca7d1107b6c5d2d6d8221039a220fde0'))
paddle.fluid.layers.multiclass_nms (ArgSpec(args=['bboxes', 'scores', 'score_threshold', 'nms_top_k', 'keep_top_k', 'nms_threshold', 'normalized', 'nms_eta', 'background_label', 'name'], varargs=None, keywords=None, defaults=(0.3, True, 1.0, 0, None)), ('document', 'ca7d1107b6c5d2d6d8221039a220fde0'))
paddle.fluid.layers.distribute_fpn_proposals (ArgSpec(args=['fpn_rois', 'min_level', 'max_level', 'refer_level', 'refer_scale', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'f
a7008889611447edd1bac71dd42b558
'))
paddle.fluid.layers.distribute_fpn_proposals (ArgSpec(args=['fpn_rois', 'min_level', 'max_level', 'refer_level', 'refer_scale', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'f
dffe52577f7e74c090b030867fefc11
'))
paddle.fluid.layers.accuracy (ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None)), ('document', '9808534c12c5e739a10f73ebb0b4eafd'))
paddle.fluid.layers.accuracy (ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None)), ('document', '9808534c12c5e739a10f73ebb0b4eafd'))
paddle.fluid.layers.auc (ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1)), ('document', 'e0e95334fce92d16c2d9db6e7caffc47'))
paddle.fluid.layers.auc (ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1)), ('document', 'e0e95334fce92d16c2d9db6e7caffc47'))
paddle.fluid.layers.exponential_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', '98a5050bee8522fcea81aa795adaba51'))
paddle.fluid.layers.exponential_decay (ArgSpec(args=['learning_rate', 'decay_steps', 'decay_rate', 'staircase'], varargs=None, keywords=None, defaults=(False,)), ('document', '98a5050bee8522fcea81aa795adaba51'))
...
...
python/paddle/fluid/layers/detection.py
浏览文件 @
f0177a1e
...
@@ -2231,21 +2231,23 @@ def distribute_fpn_proposals(fpn_rois,
...
@@ -2231,21 +2231,23 @@ def distribute_fpn_proposals(fpn_rois,
refer_scale
,
refer_scale
,
name
=
None
):
name
=
None
):
"""
"""
Distribute all proposals into different fpn level, with respect to scale
In Feature Pyramid Networks (FPN) models, it is needed to distribute all
of the proposals, the referring scale and the referring level. Besides, to
proposals into different FPN level, with respect to scale of the proposals,
restore the order of proposals, we return an array which indicates the
the referring scale and the referring level. Besides, to restore the order
original index of rois in current proposals. To compute fpn level for each
of proposals, we return an array which indicates the original index of rois
roi, the formula is given as follows:
in current proposals. To compute FPN level for each roi, the formula is
given as follows:
.. math::
.. math::
roi\_scale = \sqrt{BBoxArea(fpn\_roi)}
level = floor(\log(
\\
frac{roi\_scale}{refer\_scale}) + refer\_level)
roi\_scale &= \sqrt{BBoxArea(fpn\_roi)}
where BBoxArea is the area of each roi
level = floor(&\log(
\\
frac{roi\_scale}{refer\_scale}) + refer\_level)
where BBoxArea is a function to compute the area of each roi.
Args:
Args:
fpn_rois(variable): The input fpn_rois, the
last
dimension is 4.
fpn_rois(variable): The input fpn_rois, the
second
dimension is 4.
min_level(int): The lowest level of FPN layer where the proposals come
min_level(int): The lowest level of FPN layer where the proposals come
from.
from.
max_level(int): The highest level of FPN layer where the proposals
max_level(int): The highest level of FPN layer where the proposals
...
...
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