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
2c47839b
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
未验证
提交
2c47839b
编写于
8月 03, 2021
作者:
S
shangliang Xu
提交者:
GitHub
8月 03, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
[doc fix] fix detr docs, test=document_fix (#3872)
上级
6e8607b4
变更
2
显示空白变更内容
内联
并排
Showing
2 changed file
with
12 addition
and
0 deletion
+12
-0
configs/deformable_detr/README.md
configs/deformable_detr/README.md
+6
-0
configs/detr/README.md
configs/detr/README.md
+6
-0
未找到文件。
configs/deformable_detr/README.md
浏览文件 @
2c47839b
...
@@ -17,6 +17,12 @@ Deformable DETR is an object detection model based on DETR. We reproduced the mo
...
@@ -17,6 +17,12 @@ Deformable DETR is an object detection model based on DETR. We reproduced the mo
-
Deformable DETR is trained on COCO train2017 dataset and evaluated on val2017 results of
`mAP(IoU=0.5:0.95)`
.
-
Deformable DETR is trained on COCO train2017 dataset and evaluated on val2017 results of
`mAP(IoU=0.5:0.95)`
.
-
Deformable DETR uses 8GPU to train 50 epochs.
-
Deformable DETR uses 8GPU to train 50 epochs.
GPU multi-card training
```
bash
export
CUDA_VISIBLE_DEVICES
=
0,1,2,3,4,5,6,7
python
-m
paddle.distributed.launch
--gpus
0,1,2,3,4,5,6,7 tools/train.py
-c
configs/deformable_detr/deformable_detr_r50_1x_coco.yml
--fleet
-o
find_unused_parameters
=
True
```
## Citations
## Citations
```
```
@inproceedings{
@inproceedings{
...
...
configs/detr/README.md
浏览文件 @
2c47839b
...
@@ -17,6 +17,12 @@ DETR is an object detection model based on transformer. We reproduced the model
...
@@ -17,6 +17,12 @@ DETR is an object detection model based on transformer. We reproduced the model
-
DETR is trained on COCO train2017 dataset and evaluated on val2017 results of
`mAP(IoU=0.5:0.95)`
.
-
DETR is trained on COCO train2017 dataset and evaluated on val2017 results of
`mAP(IoU=0.5:0.95)`
.
-
DETR uses 8GPU to train 500 epochs.
-
DETR uses 8GPU to train 500 epochs.
GPU multi-card training
```
bash
export
CUDA_VISIBLE_DEVICES
=
0,1,2,3,4,5,6,7
python
-m
paddle.distributed.launch
--gpus
0,1,2,3,4,5,6,7 tools/train.py
-c
configs/detr/detr_r50_1x_coco.yml
--fleet
-o
find_unused_parameters
=
True
```
## Citations
## Citations
```
```
@inproceedings{detr,
@inproceedings{detr,
...
...
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