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
de2589ea
P
PaddleDetection
项目概览
PaddlePaddle
/
PaddleDetection
大约 1 年 前同步成功
通知
692
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
体验新版 GitCode,发现更多精彩内容 >>
未验证
提交
de2589ea
编写于
2月 24, 2020
作者:
G
Guanghua Yu
提交者:
GitHub
2月 24, 2020
浏览文件
操作
浏览文件
下载
电子邮件补丁
差异文件
Fix softlink (#256)
上级
3a9c4213
变更
15
显示空白变更内容
内联
并排
Showing
15 changed file
with
42 addition
and
22 deletion
+42
-22
README.md
README.md
+2
-2
README_en.md
README_en.md
+6
-5
docs/advanced_tutorials/slim/DISTILLATION.md
docs/advanced_tutorials/slim/DISTILLATION.md
+0
-1
docs/advanced_tutorials/slim/MODEL_ZOO.md
docs/advanced_tutorials/slim/MODEL_ZOO.md
+1
-1
docs/advanced_tutorials/slim/NAS.md
docs/advanced_tutorials/slim/NAS.md
+0
-1
docs/advanced_tutorials/slim/QUANTIZATION.md
docs/advanced_tutorials/slim/QUANTIZATION.md
+0
-1
docs/advanced_tutorials/slim/distillation/DISTILLATION.md
docs/advanced_tutorials/slim/distillation/DISTILLATION.md
+1
-0
docs/advanced_tutorials/slim/distillation/index.rst
docs/advanced_tutorials/slim/distillation/index.rst
+7
-0
docs/advanced_tutorials/slim/index.rst
docs/advanced_tutorials/slim/index.rst
+4
-4
docs/advanced_tutorials/slim/nas/NAS.md
docs/advanced_tutorials/slim/nas/NAS.md
+1
-0
docs/advanced_tutorials/slim/nas/index.rst
docs/advanced_tutorials/slim/nas/index.rst
+7
-0
docs/advanced_tutorials/slim/prune/index.rst
docs/advanced_tutorials/slim/prune/index.rst
+1
-1
docs/advanced_tutorials/slim/quantization/QUANTIZATION.md
docs/advanced_tutorials/slim/quantization/QUANTIZATION.md
+1
-0
docs/advanced_tutorials/slim/quantization/index.rst
docs/advanced_tutorials/slim/quantization/index.rst
+7
-0
slim/README.md
slim/README.md
+4
-6
未找到文件。
README.md
浏览文件 @
de2589ea
...
...
@@ -80,11 +80,11 @@ PaddleDetection的目的是为工业界和学术界提供丰富、易用的目
-
[
IPython Notebook demo
](
demo/mask_rcnn_demo.ipynb
)
-
[
迁移学习教程
](
docs/advanced_tutorials/TRANSFER_LEARNING_cn.md
)
-
[
模型压缩
](
slim
)
-
[
压缩benchmark
](
slim
)
-
[
量化
](
slim/quantization
)
-
[
剪枝
](
slim/prune
)
-
[
蒸馏
](
slim/distillation
)
-
[
神经网络搜索
](
slim/nas
)
-
[
压缩benchmark
](
slim
)
-
[
推理部署
](
inference
)
-
[
模型导出教程
](
docs/advanced_tutorials/inference/EXPORT_MODEL.md
)
-
[
预测引擎Python API使用示例
](
docs/advanced_tutorials/inference/INFERENCE.md
)
...
...
@@ -105,7 +105,7 @@ PaddleDetection的目的是为工业界和学术界提供丰富、易用的目
本项目的发布受
[
Apache 2.0 license
](
LICENSE
)
许可认证。
## 版本更新
v0.2.0版本已经在
`0
1
/2020`
发布,增加多个模型,升级数据处理模块,拆分YOLOv3的loss,修复已知诸多bug等,
v0.2.0版本已经在
`0
2
/2020`
发布,增加多个模型,升级数据处理模块,拆分YOLOv3的loss,修复已知诸多bug等,
详细内容请参考
[
版本更新文档
](
docs/CHANGELOG.md
)
。
## 如何贡献代码
...
...
README_en.md
浏览文件 @
de2589ea
...
...
@@ -91,10 +91,11 @@ Advanced Features:
-
[
IPython Notebook demo
](
demo/mask_rcnn_demo.ipynb
)
-
[
Transfer learning document
](
docs/advanced_tutorials/TRANSFER_LEARNING.md
)
-
[
Model compression
](
slim
)
-
[
Quantization-aware training example
](
slim/quantization
)
-
[
Model pruning example
](
slim/prune
)
-
[
Model distillation example
](
slim/distillation
)
-
[
Neural Architecture Search example
](
slim/nas
)
-
[
Model compression benchmark
](
slim
)
-
[
Quantization
](
slim/quantization
)
-
[
Model pruning
](
slim/prune
)
-
[
Model distillation
](
slim/distillation
)
-
[
Neural Architecture Search
](
slim/nas
)
-
[
Deployment
](
inference
)
-
[
Export model for inference
](
docs/advanced_tutorials/inference/EXPORT_MODEL.md
)
-
[
Model inference
](
docs/advanced_tutorials/inference/INFERENCE.md
)
...
...
@@ -115,7 +116,7 @@ Advanced Features:
PaddleDetection is released under the
[
Apache 2.0 license
](
LICENSE
)
.
## Updates
v0.2.0 was released at
`0
1
/2020`
, add some models,Upgrade data processing module, Split YOLOv3's loss, fix many known bugs, etc.
v0.2.0 was released at
`0
2
/2020`
, add some models,Upgrade data processing module, Split YOLOv3's loss, fix many known bugs, etc.
Please refer to
[
版本更新文档
](
docs/CHANGELOG.md
)
for details.
## Contributing
...
...
docs/advanced_tutorials/slim/DISTILLATION.md
已删除
120000 → 0
浏览文件 @
3a9c4213
../../../slim/distillation/README.md
\ No newline at end of file
docs/advanced_tutorials/slim/MODEL_ZOO.md
浏览文件 @
de2589ea
slim/README.md
\ No newline at end of file
../../../slim/README.md
\ No newline at end of file
docs/advanced_tutorials/slim/NAS.md
已删除
120000 → 0
浏览文件 @
3a9c4213
../../../slim/nas/README.md
\ No newline at end of file
docs/advanced_tutorials/slim/QUANTIZATION.md
已删除
120000 → 0
浏览文件 @
3a9c4213
../../../slim/quantization/README.md
\ No newline at end of file
docs/advanced_tutorials/slim/distillation/DISTILLATION.md
0 → 120000
浏览文件 @
de2589ea
../../../../slim/distillation/README.md
\ No newline at end of file
docs/advanced_tutorials/slim/distillation/index.rst
0 → 100644
浏览文件 @
de2589ea
模型蒸馏
===========================================
.. toctree::
:maxdepth: 2
DISTILLATION.md
docs/advanced_tutorials/slim/index.rst
浏览文件 @
de2589ea
...
...
@@ -4,8 +4,8 @@
.. toctree::
:maxdepth: 2
DISTILLATION.md
QUANTIZATION.md
NAS.md
prune/index
MODEL_ZOO.md
distillation/index
quantization/index
nas/index
prune/index
docs/advanced_tutorials/slim/nas/NAS.md
0 → 120000
浏览文件 @
de2589ea
../../../../slim/nas/README.md
\ No newline at end of file
docs/advanced_tutorials/slim/nas/index.rst
0 → 100644
浏览文件 @
de2589ea
神经网络搜索
===========================================
.. toctree::
:maxdepth: 2
NAS.md
docs/advanced_tutorials/slim/prune/index.rst
浏览文件 @
de2589ea
模型剪枝
教程
模型剪枝
===========================================
.. toctree::
...
...
docs/advanced_tutorials/slim/quantization/QUANTIZATION.md
0 → 120000
浏览文件 @
de2589ea
../../../../slim/quantization/README.md
\ No newline at end of file
docs/advanced_tutorials/slim/quantization/index.rst
0 → 100644
浏览文件 @
de2589ea
模型量化
===========================================
.. toctree::
:maxdepth: 2
QUANTIZATION.md
slim/README.md
浏览文件 @
de2589ea
#
简介
#
压缩benchmark
在PaddleDetection, 提供了基于PaddleSlim进行模型压缩的完整教程和实验结果。详细教程请参考:
...
...
@@ -9,8 +9,6 @@
下面给出压缩的benchmark实验结果。
# 压缩模型库
## 测试环境
-
Python 2.7.1
...
...
@@ -23,7 +21,7 @@
### 训练策略
-
剪裁模型训练时使用
[
PaddleDetection模型库
](
../docs/MODEL_ZOO_cn.md
)
发布的模型权重作为预训练权重。
-
剪裁模型训练时使用
[
PaddleDetection模型库
](
https://paddledetection.readthedocs.io/zh/latest/MODEL_ZOO_cn.html
)
发布的模型权重作为预训练权重。
-
剪裁训练使用模型默认配置,即除
`pretrained_weights`
外配置不变。
-
剪裁模型全部为基于敏感度的卷积通道剪裁。
-
YOLOv3模型主要剪裁
`yolo_head`
部分,即剪裁参数如下。
...
...
@@ -69,7 +67,7 @@
### 蒸馏通道剪裁模型
可通过高精度模型蒸馏通道剪裁后模型的方式,训练方法及相关示例见
[
蒸馏通道剪裁模型
](
.
/extensions/distill_pruned_model/distill_pruned_model_demo.ipynb
)
。
可通过高精度模型蒸馏通道剪裁后模型的方式,训练方法及相关示例见
[
蒸馏通道剪裁模型
](
https://github.com/PaddlePaddle/PaddleDetection/blob/master/slim
/extensions/distill_pruned_model/distill_pruned_model_demo.ipynb
)
。
COCO数据集上蒸馏通道剪裁模型库如下。
...
...
@@ -93,7 +91,7 @@ Pascal VOC数据集上蒸馏通道剪裁模型库如下。
### 训练策略
-
蒸馏模型训练时teacher模型使用
[
PaddleDetection模型库
](
../docs/MODEL_ZOO_cn.md
)
发布的模型权重作为预训练权重。
-
蒸馏模型训练时teacher模型使用
[
PaddleDetection模型库
](
https://paddledetection.readthedocs.io/zh/latest/MODEL_ZOO_cn.html
)
发布的模型权重作为预训练权重。
-
蒸馏模型训练时student模型使用backbone的预训练权重
### YOLOv3 on COCO
...
...
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