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
27号BigBang
Mask_RCNN
提交
1aeb72d5
M
Mask_RCNN
项目概览
27号BigBang
/
Mask_RCNN
与 Fork 源项目一致
从无法访问的项目Fork
通知
3
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
M
Mask_RCNN
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
前往新版Gitcode,体验更适合开发者的 AI 搜索 >>
提交
1aeb72d5
编写于
9月 13, 2018
作者:
keineahnung2345
提交者:
Waleed
9月 20, 2018
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix the comment on output shape in RPN
上级
10a364f9
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
7 addition
and
7 deletion
+7
-7
mrcnn/model.py
mrcnn/model.py
+7
-7
未找到文件。
mrcnn/model.py
浏览文件 @
1aeb72d5
...
...
@@ -839,9 +839,9 @@ def rpn_graph(feature_map, anchors_per_location, anchor_stride):
every pixel in the feature map), or 2 (every other pixel).
Returns:
rpn_
logits: [batch, H, W
, 2] Anchor classifier logits (before softmax)
rpn_probs: [batch, H
, W
, 2] Anchor classifier probabilities.
rpn_bbox: [batch, H
, W
, (dy, dx, log(dh), log(dw))] Deltas to be
rpn_
class_logits: [batch, H * W * anchors_per_location
, 2] Anchor classifier logits (before softmax)
rpn_probs: [batch, H
* W * anchors_per_location
, 2] Anchor classifier probabilities.
rpn_bbox: [batch, H
* W * anchors_per_location
, (dy, dx, log(dh), log(dw))] Deltas to be
applied to anchors.
"""
# TODO: check if stride of 2 causes alignment issues if the feature map
...
...
@@ -863,7 +863,7 @@ def rpn_graph(feature_map, anchors_per_location, anchor_stride):
rpn_probs
=
KL
.
Activation
(
"softmax"
,
name
=
"rpn_class_xxx"
)(
rpn_class_logits
)
# Bounding box refinement. [batch, H, W, anchors per location
,
depth]
# Bounding box refinement. [batch, H, W, anchors per location
*
depth]
# where depth is [x, y, log(w), log(h)]
x
=
KL
.
Conv2D
(
anchors_per_location
*
4
,
(
1
,
1
),
padding
=
"valid"
,
activation
=
'linear'
,
name
=
'rpn_bbox_pred'
)(
shared
)
...
...
@@ -885,9 +885,9 @@ def build_rpn_model(anchor_stride, anchors_per_location, depth):
depth: Depth of the backbone feature map.
Returns a Keras Model object. The model outputs, when called, are:
rpn_
logits: [batch, H, W
, 2] Anchor classifier logits (before softmax)
rpn_probs: [batch,
W, W
, 2] Anchor classifier probabilities.
rpn_bbox: [batch, H
, W
, (dy, dx, log(dh), log(dw))] Deltas to be
rpn_
class_logits: [batch, H * W * anchors_per_location
, 2] Anchor classifier logits (before softmax)
rpn_probs: [batch,
H * W * anchors_per_location
, 2] Anchor classifier probabilities.
rpn_bbox: [batch, H
* W * anchors_per_location
, (dy, dx, log(dh), log(dw))] Deltas to be
applied to anchors.
"""
input_feature_map
=
KL
.
Input
(
shape
=
[
None
,
None
,
depth
],
...
...
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