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
牧羊zove
fcos
提交
75bb7859
F
fcos
项目概览
牧羊zove
/
fcos
与 Fork 源项目一致
从无法访问的项目Fork
通知
5
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
F
fcos
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
75bb7859
编写于
7月 02, 2019
作者:
Z
Zhi Tian
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
update README.md
上级
89e18e01
变更
1
隐藏空白更改
内联
并排
Showing
1 changed file
with
4 addition
and
4 deletion
+4
-4
README.md
README.md
+4
-4
未找到文件。
README.md
浏览文件 @
75bb7859
...
...
@@ -57,8 +57,6 @@ For your convenience, we provide the following trained models (more models are c
**ResNe(x)ts:**
*All ResNe(x)ts based models are trained with 16 images in a mini-batch and frozen batch normalizaiton (consistent with ).*
Model | Total training mem (GB) | Multi-scale training | Testing time / im | AP (minival) | AP (test-dev) | Link
--- |:---:|:---:|:---:|:---:|:--:|:---:
FCOS_R_50_FPN_1x | 29.3 | No | 71ms | 37.1 | 37.4 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/dDeDPBLEAt19Xrl/download
)
...
...
@@ -66,15 +64,17 @@ FCOS_R_101_FPN_2x | 44.1 | Yes | 74ms | 41.4 | 41.5 | [download](https://cloudst
FCOS_X_101_32x8d_FPN_2x | 72.9 | Yes | 122ms | 42.5 | 42.7 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/U5myBfGF7MviZ97/download
)
FCOS_X_101_64x4d_FPN_2x | 77.7 | Yes | 140ms | 43.0 | 43.2 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/wpwoCi4S8iajFi9/download
)
*
*MobileNets:*
*
*
All ResNe(x)t based models are trained with 16 images in a mini-batch and frozen batch normalizaiton (consistent with ).
*
*
We update batch normalizaiton for MobileNets based models. If you want to use SyncBN, please install pytorch-nightly.
*
*
*MobileNets:*
*
Model | Training batch size | Multi-scale training | Testing time / im | AP (minival) | Link
--- |:---:|:---:|:---:|:---:|:---:
FCOS_bn_bs16_MNV2_FPN_1x | 16 | No | 59ms | 31.0 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/B6BrLAiAEAYQkcy/download
)
FCOS_syncbn_bs32_MNV2_FPN_1x | 32 | No | 59ms | 33.1 |
[
download
](
https://cloudstor.aarnet.edu.au/plus/s/OpJtCJLj104i2Yc/download
)
*We update batch normalizaiton for MobileNet based models. If you want to use SyncBN, please install pytorch-nightly.*
[1]
*1x and 2x mean the model is trained for 90K and 180K iterations, respectively.*
\
[2]
*We report total training memory footprint on all GPUs instead of the memory footprint per GPU as in maskrcnn-benchmark*
.
\
[3]
*All results are obtained with a single model and without any test time data augmentation such as multi-scale, flipping and etc..*
\
...
...
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