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
573d7314
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
573d7314
编写于
4月 07, 2022
作者:
G
Guanghua Yu
提交者:
GitHub
4月 07, 2022
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
add picodet quant model (#5617)
上级
ac528aaf
变更
3
隐藏空白更改
内联
并排
Showing
3 changed file
with
46 addition
and
38 deletion
+46
-38
configs/picodet/README.md
configs/picodet/README.md
+12
-19
configs/picodet/README_en.md
configs/picodet/README_en.md
+12
-19
configs/slim/quant/picodet_s_416_lcnet_quant.yml
configs/slim/quant/picodet_s_416_lcnet_quant.yml
+22
-0
未找到文件。
configs/picodet/README.md
浏览文件 @
573d7314
...
@@ -220,9 +220,10 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
...
@@ -220,9 +220,10 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
### 部署
### 部署
-
PaddleInference demo
[
Python
](
../../deploy/python
)
&
[
C++
](
../../deploy/cpp
)
-
OpenVINO demo
[
Python
](
../../deploy/third_engine/demo/openvino/python
)
-
[
PaddleLite C++ demo
](
../../deploy/lite
)
-
[
PaddleLite C++ demo
](
../../deploy/lite
)
-
[
Android demo(Paddle Lite)
](
https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo
)
-
[
Android demo(Paddle Lite)
](
https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo
)
-
PaddleInference demo
[
Python
](
../../deploy/python
)
&
[
C++
](
../../deploy/cpp
)
Android demo可视化:
Android demo可视化:
...
@@ -237,43 +238,35 @@ Android demo可视化:
...
@@ -237,43 +238,35 @@ Android demo可视化:
<summary>
依赖包:
</summary>
<summary>
依赖包:
</summary>
-
PaddlePaddle >= 2.2.2
-
PaddlePaddle >= 2.2.2
-
PaddleSlim >= 2.2.
1
-
PaddleSlim >= 2.2.
2
**安装:**
**安装:**
```
shell
```
shell
pip
install
paddleslim
==
2.2.
1
pip
install
paddleslim
==
2.2.
2
```
```
</details>
</details>
<details>
<details
open
>
<summary>
量化训练
(点击展开)
</summary>
<summary>
量化训练
</summary>
开始量化训练:
开始量化训练:
```
shell
```
shell
python tools/train.py
-c
configs/picodet/picodet_s_
320
_coco_lcnet.yml
\
python tools/train.py
-c
configs/picodet/picodet_s_
416
_coco_lcnet.yml
\
--slim_config
configs/slim/quant/picodet_s_quant.yml
--eval
--slim_config
configs/slim/quant/picodet_s_
416_lcnet_
quant.yml
--eval
```
```
-
更多细节请参考
[
slim文档
](
https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim
)
-
更多细节请参考
[
slim文档
](
https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim
)
</details>
</details>
<details>
-
量化训练Model ZOO:
<summary>
离线量化 (点击展开)
</summary>
校准及导出量化模型:
```
shell
| 量化模型 | 输入尺寸 | mAP
<sup>
val
<br>
0.5:0.95 | Configs | Weight | Inference Model | Paddle Lite(INT8) |
python tools/post_quant.py
-c
configs/picodet/picodet_s_320_coco_lcnet.yml
\
| :-------- | :--------: | :--------------------: | :-------: | :----------------: | :----------------: | :----------------: |
--slim_config
configs/slim/post_quant/picodet_s_ptq.yml
| PicoDet-S | 416
*
416 | 31.5 |
[
config
](
./picodet_s_416_coco_lcnet.yml
)
|
[
slim config
](
../slim/quant/picodet_s_416_lcnet_quant.yml
)
|
[
model
](
https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet_quant.pdparams
)
|
[
w/ 后处理
](
https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant.tar
)
|
[
w/o 后处理
](
https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant_non_postprocess.tar
)
|
[
w/ 后处理
](
https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant.nb
)
|
[
w/o 后处理
](
https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant_non_postprocess.nb
)
|
```
-
注意: 离线量化模型精度问题正在解决中.
</details>
## 非结构化剪枝
## 非结构化剪枝
...
...
configs/picodet/README_en.md
浏览文件 @
573d7314
...
@@ -216,9 +216,10 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
...
@@ -216,9 +216,10 @@ paddle2onnx --model_dir output_inference/picodet_s_320_coco_lcnet/ \
### Deploy
### Deploy
-
PaddleInference demo
[
Python
](
../../deploy/python
)
&
[
C++
](
../../deploy/cpp
)
-
OpenVINO demo
[
Python
](
../../deploy/third_engine/demo/openvino/python
)
-
[
PaddleLite C++ demo
](
../../deploy/lite
)
-
[
PaddleLite C++ demo
](
../../deploy/lite
)
-
[
Android demo(Paddle Lite)
](
https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo
)
-
[
Android demo(Paddle Lite)
](
https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/develop/object_detection/android/app/cxx/picodet_detection_demo
)
-
PaddleInference demo
[
Python
](
../../deploy/python
)
&
[
C++
](
../../deploy/cpp
)
Android demo visualization:
Android demo visualization:
...
@@ -233,43 +234,35 @@ Android demo visualization:
...
@@ -233,43 +234,35 @@ Android demo visualization:
<summary>
Requirements:
</summary>
<summary>
Requirements:
</summary>
-
PaddlePaddle >= 2.2.2
-
PaddlePaddle >= 2.2.2
-
PaddleSlim >= 2.2.
1
-
PaddleSlim >= 2.2.
2
**Install:**
**Install:**
```
shell
```
shell
pip
install
paddleslim
==
2.2.
1
pip
install
paddleslim
==
2.2.
2
```
```
</details>
</details>
<details>
<details
open
>
<summary>
Quant aware
(click to expand)
</summary>
<summary>
Quant aware
</summary>
Configure the quant config and start training:
Configure the quant config and start training:
```
shell
```
shell
python tools/train.py
-c
configs/picodet/picodet_s_
320
_coco_lcnet.yml
\
python tools/train.py
-c
configs/picodet/picodet_s_
416
_coco_lcnet.yml
\
--slim_config
configs/slim/quant/picodet_s_quant.yml
--eval
--slim_config
configs/slim/quant/picodet_s_
416_lcnet_
quant.yml
--eval
```
```
-
More detail can refer to
[
slim document
](
https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim
)
-
More detail can refer to
[
slim document
](
https://github.com/PaddlePaddle/PaddleDetection/tree/develop/configs/slim
)
</details>
</details>
<details>
-
Quant Aware Model ZOO:
<summary>
Post quant (click to expand)
</summary>
Configure the post quant config and start calibrate model:
```
shell
| Quant Model | Input size | mAP
<sup>
val
<br>
0.5:0.95 | Configs | Weight | Inference Model | Paddle Lite(INT8) |
python tools/post_quant.py
-c
configs/picodet/picodet_s_320_coco_lcnet.yml
\
| :-------- | :--------: | :--------------------: | :-------: | :----------------: | :----------------: | :----------------: |
--slim_config
configs/slim/post_quant/picodet_s_ptq.yml
| PicoDet-S | 416
*
416 | 31.5 |
[
config
](
./picodet_s_416_coco_lcnet.yml
)
|
[
slim config
](
../slim/quant/picodet_s_416_lcnet_quant.yml
)
|
[
model
](
https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet_quant.pdparams
)
|
[
w/ postprocess
](
https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant.tar
)
|
[
w/o postprocess
](
https://paddledet.bj.bcebos.com/deploy/Inference/picodet_s_416_coco_lcnet_quant_non_postprocess.tar
)
|
[
w/ postprocess
](
https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant.nb
)
|
[
w/o postprocess
](
https://paddledet.bj.bcebos.com/deploy/paddlelite/picodet_s_416_coco_lcnet_quant_non_postprocess.nb
)
|
```
-
Notes: Now the accuracy of post quant is abnormal and this problem is being solved.
</details>
## Unstructured Pruning
## Unstructured Pruning
...
...
configs/slim/quant/picodet_s_416_lcnet_quant.yml
0 → 100644
浏览文件 @
573d7314
pretrain_weights
:
https://paddledet.bj.bcebos.com/models/picodet_s_416_coco_lcnet.pdparams
slim
:
QAT
QAT
:
quant_config
:
{
'
activation_preprocess_type'
:
'
PACT'
,
'
weight_quantize_type'
:
'
channel_wise_abs_max'
,
'
activation_quantize_type'
:
'
moving_average_abs_max'
,
'
weight_bits'
:
8
,
'
activation_bits'
:
8
,
'
dtype'
:
'
int8'
,
'
window_size'
:
10000
,
'
moving_rate'
:
0.9
,
'
quantizable_layer_type'
:
[
'
Conv2D'
,
'
Linear'
]}
print_model
:
False
TrainReader
:
batch_size
:
48
LearningRate
:
base_lr
:
0.024
schedulers
:
-
!CosineDecay
max_epochs
:
300
-
!LinearWarmup
start_factor
:
0.1
steps
:
300
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