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
PaddlePaddle
PaddleDetection
提交
320c6eea
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
1 年多 前同步成功
通知
696
Star
11112
Fork
2696
代码
文件
提交
分支
Tags
贡献者
分支图
Diff
Issue
184
列表
看板
标记
里程碑
合并请求
40
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
184
Issue
184
列表
看板
标记
里程碑
合并请求
40
合并请求
40
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
320c6eea
编写于
7月 20, 2021
作者:
S
shangliang Xu
提交者:
GitHub
7月 20, 2021
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
[transformer] add readme and deformable configs (#3720)
上级
e8aeb802
变更
7
隐藏空白更改
内联
并排
Showing
7 changed file
with
185 addition
and
1 deletion
+185
-1
configs/deformable_detr/README.md
configs/deformable_detr/README.md
+30
-0
configs/deformable_detr/_base_/deformable_detr_r50.yml
configs/deformable_detr/_base_/deformable_detr_r50.yml
+48
-0
configs/deformable_detr/_base_/deformable_detr_reader.yml
configs/deformable_detr/_base_/deformable_detr_reader.yml
+49
-0
configs/deformable_detr/_base_/deformable_optimizer_1x.yml
configs/deformable_detr/_base_/deformable_optimizer_1x.yml
+16
-0
configs/deformable_detr/deformable_detr_r50_1x_coco.yml
configs/deformable_detr/deformable_detr_r50_1x_coco.yml
+8
-0
configs/detr/README.md
configs/detr/README.md
+33
-0
configs/detr/_base_/detr_r50.yml
configs/detr/_base_/detr_r50.yml
+1
-1
未找到文件。
configs/deformable_detr/README.md
0 → 100644
浏览文件 @
320c6eea
# Deformable DETR
## Introduction
Deformable DETR is an object detection model based on DETR. We reproduced the model of the paper.
## Model Zoo
| Backbone | Model | Images/GPU | Inf time (fps) | Box AP | Config | Download |
|:------:|:--------:|:--------:|:--------------:|:------:|:------:|:--------:|
| R-50 | Deformable DETR | 2 | --- | 44.1 |
[
config
](
https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/deformable_detr/deformable_detr_r50_1x_coco.yml
)
|
[
model
](
https://paddledet.bj.bcebos.com/models/deformable_detr_r50_1x_coco.pdparams
)
|
**Notes:**
-
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.
## Citations
```
@inproceedings{
zhu2021deformable,
title={Deformable DETR: Deformable Transformers for End-to-End Object Detection},
author={Xizhou Zhu and Weijie Su and Lewei Lu and Bin Li and Xiaogang Wang and Jifeng Dai},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=gZ9hCDWe6ke}
}
```
configs/deformable_detr/_base_/deformable_detr_r50.yml
0 → 100644
浏览文件 @
320c6eea
architecture
:
DETR
pretrain_weights
:
https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_vb_normal_pretrained.pdparams
hidden_dim
:
256
use_focal_loss
:
True
DETR
:
backbone
:
ResNet
transformer
:
DeformableTransformer
detr_head
:
DeformableDETRHead
post_process
:
DETRBBoxPostProcess
ResNet
:
# index 0 stands for res2
depth
:
50
norm_type
:
bn
freeze_at
:
0
return_idx
:
[
1
,
2
,
3
]
lr_mult_list
:
[
0.0
,
0.1
,
0.1
,
0.1
]
num_stages
:
4
DeformableTransformer
:
num_queries
:
300
position_embed_type
:
sine
nhead
:
8
num_encoder_layers
:
6
num_decoder_layers
:
6
dim_feedforward
:
1024
dropout
:
0.1
activation
:
relu
num_feature_levels
:
4
num_encoder_points
:
4
num_decoder_points
:
4
DeformableDETRHead
:
num_mlp_layers
:
3
DETRLoss
:
loss_coeff
:
{
class
:
2
,
bbox
:
5
,
giou
:
2
,
mask
:
1
,
dice
:
1
}
aux_loss
:
True
HungarianMatcher
:
matcher_coeff
:
{
class
:
2
,
bbox
:
5
,
giou
:
2
}
configs/deformable_detr/_base_/deformable_detr_reader.yml
0 → 100644
浏览文件 @
320c6eea
worker_num
:
0
TrainReader
:
sample_transforms
:
-
Decode
:
{}
-
RandomFlip
:
{
prob
:
0.5
}
-
RandomSelect
:
{
transforms1
:
[
RandomShortSideResize
:
{
short_side_sizes
:
[
480
,
512
,
544
,
576
,
608
,
640
,
672
,
704
,
736
,
768
,
800
],
max_size
:
1333
}
],
transforms2
:
[
RandomShortSideResize
:
{
short_side_sizes
:
[
400
,
500
,
600
]
},
RandomSizeCrop
:
{
min_size
:
384
,
max_size
:
600
},
RandomShortSideResize
:
{
short_side_sizes
:
[
480
,
512
,
544
,
576
,
608
,
640
,
672
,
704
,
736
,
768
,
800
],
max_size
:
1333
}
]
}
-
NormalizeImage
:
{
is_scale
:
true
,
mean
:
[
0.485
,
0.456
,
0.406
],
std
:
[
0.229
,
0.224
,
0.225
]}
-
NormalizeBox
:
{}
-
BboxXYXY2XYWH
:
{}
-
Permute
:
{}
batch_transforms
:
-
PadMaskBatch
:
{
pad_to_stride
:
-1
,
return_pad_mask
:
true
}
batch_size
:
2
shuffle
:
true
drop_last
:
true
collate_batch
:
false
use_shared_memory
:
false
EvalReader
:
sample_transforms
:
-
Decode
:
{}
-
Resize
:
{
target_size
:
[
800
,
1333
],
keep_ratio
:
True
}
-
NormalizeImage
:
{
is_scale
:
true
,
mean
:
[
0.485
,
0.456
,
0.406
],
std
:
[
0.229
,
0.224
,
0.225
]}
-
Permute
:
{}
batch_transforms
:
-
PadMaskBatch
:
{
pad_to_stride
:
-1
,
return_pad_mask
:
true
}
batch_size
:
1
shuffle
:
false
drop_last
:
false
drop_empty
:
false
TestReader
:
sample_transforms
:
-
Decode
:
{}
-
Resize
:
{
target_size
:
[
800
,
1333
],
keep_ratio
:
True
}
-
NormalizeImage
:
{
is_scale
:
true
,
mean
:
[
0.485
,
0.456
,
0.406
],
std
:
[
0.229
,
0.224
,
0.225
]}
-
Permute
:
{}
batch_transforms
:
-
PadMaskBatch
:
{
pad_to_stride
:
-1
,
return_pad_mask
:
true
}
batch_size
:
1
shuffle
:
false
drop_last
:
false
configs/deformable_detr/_base_/deformable_optimizer_1x.yml
0 → 100644
浏览文件 @
320c6eea
epoch
:
50
LearningRate
:
base_lr
:
0.0002
schedulers
:
-
!PiecewiseDecay
gamma
:
0.1
milestones
:
[
40
]
use_warmup
:
false
OptimizerBuilder
:
clip_grad_by_norm
:
0.1
regularizer
:
false
optimizer
:
type
:
AdamW
weight_decay
:
0.0001
configs/deformable_detr/deformable_detr_r50_1x_coco.yml
0 → 100644
浏览文件 @
320c6eea
_BASE_
:
[
'
../datasets/coco_detection.yml'
,
'
../runtime.yml'
,
'
_base_/deformable_optimizer_1x.yml'
,
'
_base_/deformable_detr_r50.yml'
,
'
_base_/deformable_detr_reader.yml'
,
]
weights
:
output/deformable_detr_r50_1x_coco/model_final
configs/detr/README.md
0 → 100644
浏览文件 @
320c6eea
# DETR
## Introduction
DETR is an object detection model based on transformer. We reproduced the model of the paper.
## Model Zoo
| Backbone | Model | Images/GPU | Inf time (fps) | Box AP | Config | Download |
|:------:|:--------:|:--------:|:--------------:|:------:|:------:|:--------:|
| R-50 | DETR | 4 | --- | 42.3 |
[
config
](
https://github.com/PaddlePaddle/PaddleDetection/blob/develop/configs/detr/detr_r50_1x_coco.yml
)
|
[
model
](
https://paddledet.bj.bcebos.com/models/detr_r50_1x_coco.pdparams
)
|
**Notes:**
-
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.
## Citations
```
@inproceedings{detr,
author = {Nicolas Carion and
Francisco Massa and
Gabriel Synnaeve and
Nicolas Usunier and
Alexander Kirillov and
Sergey Zagoruyko},
title = {End-to-End Object Detection with Transformers},
booktitle = {ECCV},
year = {2020}
}
```
configs/detr/_base_/detr_r50.yml
浏览文件 @
320c6eea
architecture
:
DETR
pretrain_weights
:
https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_
cos
_pretrained.pdparams
pretrain_weights
:
https://paddledet.bj.bcebos.com/models/pretrained/ResNet50_
vb_normal
_pretrained.pdparams
hidden_dim
:
256
...
...
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