Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[Docs] Update Docs in RTMPose #2057

Merged
merged 6 commits into from
Mar 14, 2023
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 8 additions & 6 deletions projects/rtmpose/README.md
Original file line number Diff line number Diff line change
Expand Up @@ -52,10 +52,12 @@ Coming soon

- 🚀 **High efficiency and high accuracy**

- t | 68.5 AP on COCO with CPU: 300+ FPS / GPU: 940+ FPS
- s | 72.2 AP on COCO with CPU: 200+ FPS / GPU: 710+ FPS
- m | 75.8 AP on COCO with CPU: 90+ FPS / GPU: 430+ FPS
- l | 76.5 AP on COCO with CPU: 50+ FPS / GPU: 280+ FPS
| Model | AP(COCO) | CPU-FPS | GPU-FPS |
| :---: | :------: | :-----: | :-----: |
| t | 68.5 | 300+ | 940+ |
| s | 72.2 | 200+ | 710+ |
| m | 75.8 | 90+ | 430+ |
| l | 76.5 | 50+ | 280+ |

- 🛠️ **Easy to deploy**

Expand Down Expand Up @@ -217,7 +219,7 @@ We provide two appoaches to try RTMPose:

### Pre-compiled MMDeploy SDK (Recommended)

MMDeploy provides pre-compiled SDK to conduct inference with RTMPose projects.
MMDeploy provides a precompiled SDK for Pipeline reasoning on RTMPose projects, where the model used for reasoning is the SDK version. For the tutorial of exporting the SDK version model, see [SDK Reasoning](#%EF%B8%8F-step3-inference-with-sdk), and for detailed parameter settings of inference, see [Pipeline Reasoning](#-step4-pipeline-inference).

Env Requirements:

Expand Down Expand Up @@ -423,7 +425,7 @@ python tools/deploy.py \

The converted model file is `{work-dir}/end2end.engine` by defaults.

If the script runs successfully, you will see the following files:
🎊 If the script runs successfully, you will see the following files:

![convert_models](https://user-images.githubusercontent.com/13503330/217726963-7815dd01-561a-4605-b0c6-07b6fe1956c3.png)

Expand Down
14 changes: 8 additions & 6 deletions projects/rtmpose/README_CN.md
Original file line number Diff line number Diff line change
Expand Up @@ -48,10 +48,12 @@ Coming soon

- 🚀 **高精度,低延迟**

- t | COCO 68.5 AP | CPU: 300+ FPS / GPU: 940+ FPS
- s | COCO 72.2 AP | CPU: 200+ FPS / GPU: 710+ FPS
- m | COCO 75.8 AP | CPU: 90+ FPS / GPU: 430+ FPS
- l | COCO 76.5 AP | CPU: 50+ FPS / GPU: 280+ FPS
| Model | AP(COCO) | CPU-FPS | GPU-FPS |
| :---: | :------: | :-----: | :-----: |
| t | 68.5 | 300+ | 940+ |
| s | 72.2 | 200+ | 710+ |
| m | 75.8 | 90+ | 430+ |
| l | 76.5 | 50+ | 280+ |

- 🛠️ **易部署**

Expand Down Expand Up @@ -212,7 +214,7 @@ RTMPose 是一个长期优化迭代的项目,致力于业务场景下的高性

### MMDeploy SDK 预编译包 (推荐)

MMDeploy 提供了预编译的 SDK,用于对 RTMPose 项目进行推理
MMDeploy 提供了预编译的 SDK,用于对 RTMPose 项目进行 Pipeline 推理,其中推理所用的模型为 SDK 版本。导出 SDK 版模型的教程见 [SDK 推理](#%EF%B8%8F-sdk-推理),推理的详细参数设置见 [Pipeline 推理](#-pipeline-推理)

说明:

Expand Down Expand Up @@ -423,7 +425,7 @@ python tools/deploy.py \

默认导出模型文件为 `{work-dir}/end2end.engine`

如果模型顺利导出,你将会看到样例图片上的检测结果:
🎊 如果模型顺利导出,你将会看到样例图片上的检测结果:

![convert_models](https://user-images.githubusercontent.com/13503330/217726963-7815dd01-561a-4605-b0c6-07b6fe1956c3.png)

Expand Down