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
weixin_47816946
simple-faster-rcnn-pytorch
提交
2fc727e4
S
simple-faster-rcnn-pytorch
项目概览
weixin_47816946
/
simple-faster-rcnn-pytorch
与 Fork 源项目一致
从无法访问的项目Fork
通知
8
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
S
simple-faster-rcnn-pytorch
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
2fc727e4
编写于
12月 29, 2017
作者:
C
chenyuntc
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update docs
上级
80dd5972
变更
2
隐藏空白更改
内联
并排
Showing
2 changed file
with
12 addition
and
11 deletion
+12
-11
model/utils/creator_tool.py
model/utils/creator_tool.py
+2
-2
utils/config.py
utils/config.py
+10
-9
未找到文件。
model/utils/creator_tool.py
浏览文件 @
2fc727e4
...
...
@@ -53,7 +53,7 @@ class ProposalTargetCreator(object):
sampled as foregrounds.
Offsets and scales of bounding boxes are calculated using
:func:`
chainercv.links.model.faster_rcnn
.bbox2loc`.
:func:`
model.utils.bbox_tools
.bbox2loc`.
Also, types of input arrays and output arrays are same.
Here are notations.
...
...
@@ -141,7 +141,7 @@ class AnchorTargetCreator(object):
Offsets and scales to match anchors to the ground truth are
calculated using the encoding scheme of
:func:`
~chainercv.links.model.faster_rcnn
.bbox2loc`.
:func:`
model.utils.bbox_tools
.bbox2loc`.
.. [#] Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun.
\
Faster R-CNN: Towards Real-Time Object Detection with
\
...
...
utils/config.py
浏览文件 @
2fc727e4
...
...
@@ -8,8 +8,8 @@ from pprint import pprint
class
Config
:
# data
voc_data_dir
=
'/home/cy/.chainer/dataset/pfnet/chainercv/voc/VOCdevkit/VOC2007/'
min_size
=
600
max_size
=
1000
min_size
=
600
# image resize
max_size
=
1000
# image resize
num_workers
=
8
test_num_workers
=
8
...
...
@@ -18,7 +18,8 @@ class Config:
roi_sigma
=
1.
# param for optimizer
weight_decay
=
0.0005
# 0.0005 in origin paper but 0.0001 in tf-faster-rcnn
# 0.0005 in origin paper but 0.0001 in tf-faster-rcnn
weight_decay
=
0.0005
lr_decay
=
0.1
# 1e-3 -> 1e-4
lr
=
1e-3
...
...
@@ -33,20 +34,20 @@ class Config:
pretrained_model
=
'vgg16'
# training
epoch
=
1
00
epoch
=
1
4
use_adam
=
False
use_chainer
=
False
use_drop
=
False
use_adam
=
False
# Use Adam optimizer
use_chainer
=
False
# try match everything as chainer
use_drop
=
False
# use dropout in RoIHead
# debug
debug_file
=
'/tmp/debugf'
test_num
=
10000
# model
load_path
=
None
# '/mnt/3/rpn.pth'
load_path
=
None
caffe_pretrain
=
False
caffe_pretrain
=
False
# use caffe pretrained model instead of torchvision
caffe_pretrain_path
=
'checkpoints/vgg16-caffe.pth'
def
_parse
(
self
,
kwargs
):
...
...
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