Skip to content

Commit

Permalink
Fox docs (PaddlePaddle#562)
Browse files Browse the repository at this point in the history
* fix consistency for pix2pix

* fix doc of fom

* add docs for fom lite

Co-authored-by: LDOUBLEV <liuvv0203@outlook.com>
  • Loading branch information
lzzyzlbb and LDOUBLEV authored Jan 21, 2022
1 parent 516ed93 commit 940dc26
Show file tree
Hide file tree
Showing 3 changed files with 4 additions and 4 deletions.
4 changes: 2 additions & 2 deletions deploy/lite/README.md
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
# Paddle-Lite端侧部署

本教程将介绍基于[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) 在移动端部署PaddleDetection模型的详细步骤
本教程将介绍基于[Paddle Lite](https://github.com/PaddlePaddle/Paddle-Lite) 在移动端部署FOM模型的详细步骤

Paddle Lite是飞桨轻量化推理引擎,为手机、IOT端提供高效推理能力,并广泛整合跨平台硬件,为端侧部署及应用落地问题提供轻量化的部署方案。

Expand All @@ -11,7 +11,7 @@ Paddle Lite是飞桨轻量化推理引擎,为手机、IOT端提供高效推理
- 安卓手机(armv7或armv8)

### 1.1 准备交叉编译环境
交叉编译环境用于编译 Paddle Lite 和 PaddleDetection 的C++ demo。
交叉编译环境用于编译 Paddle Lite 和 FOM 的C++ demo。
支持多种开发环境,不同开发环境的编译流程请参考对应文档,请确保安装完成Java jdk、Android NDK(R17以上)。

1. [Docker](https://paddle-lite.readthedocs.io/zh/latest/source_compile/compile_env.html#docker)
Expand Down
2 changes: 1 addition & 1 deletion docs/en_US/tutorials/motion_driving.md
Original file line number Diff line number Diff line change
Expand Up @@ -190,7 +190,7 @@ The prediction models will be exported to the directory of `output_inference/fom

- [Deployment of FOM model with Paddle Lite](https://github.com/PaddlePaddle/PaddleGAN/tree/develop/deploy/lite)

- [FOM-Lite-Demo](https://paddlegan.bj.bcebos.com/applications/first_order_model/paddle_lite/apk/face_detection_demo 2.zip)。For more details, please refer to [Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite) .
- [FOM-Lite-Demo](https://paddlegan.bj.bcebos.com/applications/first_order_model/paddle_lite/apk/fom_demo.zip)。For more details, please refer to [Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite) .

Current problems: (a).Paddle Lite performs slightly worse than Paddle Inference,under optimization (b).Run Generator in a single thread, if the number of frames is too large, it will run at the small core rather than the large core.

Expand Down
2 changes: 1 addition & 1 deletion docs/zh_CN/tutorials/motion_driving.md
Original file line number Diff line number Diff line change
Expand Up @@ -180,7 +180,7 @@ python tools/export_model.py \

#### 4.2 PaddleLite部署
- [使用Paddle Lite部署FOM模型](https://github.com/PaddlePaddle/PaddleGAN/tree/develop/deploy/lite)
- [FOM-Lite-Demo](https://paddlegan.bj.bcebos.com/applications/first_order_model/paddle_lite/apk/face_detection_demo%202.zip)。更多内容,请参考[Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite)
- [FOM-Lite-Demo](https://paddlegan.bj.bcebos.com/applications/first_order_model/paddle_lite/apk/fom_demo.zip)。更多内容,请参考[Paddle-Lite](https://github.com/PaddlePaddle/Paddle-Lite)
目前问题:
(a).Paddle Lite运行效果略差于Paddle Inference,正在优化中
(b).单线程跑Generator,帧数多了会跑到小核不跑大核
Expand Down

0 comments on commit 940dc26

Please sign in to comment.