From b16ce46851f0462c8cbfcb3ca715af76a7951a0d Mon Sep 17 00:00:00 2001 From: Jason Date: Fri, 12 Aug 2022 21:36:31 +0800 Subject: [PATCH 1/3] Update README.md --- README.md | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index a6d848775a..410559060d 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ ## 支持模型 -| 任务场景 | 模型 | X64 CPU | Nvidia-GPU | Nvidia-GPU TensorRT | +| 任务场景 | 模型 | X86 CPU | NVIDIA GPU | TensorRT | | -------- | ------------------------------------------------------------ | ------- | ---------- | ------------------- | | 图像分类 | [PaddleClas/ResNet50](./examples/vision/classification/paddleclas) | √ | √ | √ | | | [PaddleClas/PPLCNet](./examples/vision/classification/paddleclas) | √ | √ | √ | @@ -41,7 +41,7 @@ | | [PaddleDetection/FasterRCNN](./examples/vision/detection/paddledetection) | √ | √ | - | | | [WongKinYiu/YOLOv7](./examples/vision/detection/yolov7) | √ | √ | √ | -#### 快速开始 +## 快速开始 #### 安装FastDeploy Python From 9cbc2ba3718dc5d996cdd51c6afd8c2d25d958aa Mon Sep 17 00:00:00 2001 From: Jason Date: Fri, 12 Aug 2022 21:42:23 +0800 Subject: [PATCH 2/3] Update README.md --- README.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/README.md b/README.md index 410559060d..4cbb3a3b55 100644 --- a/README.md +++ b/README.md @@ -23,7 +23,7 @@ ## 支持模型 -| 任务场景 | 模型 | X86 CPU | NVIDIA GPU | TensorRT | +| 任务场景 | 模型 | CPU | NVIDIA GPU | TensorRT | | -------- | ------------------------------------------------------------ | ------- | ---------- | ------------------- | | 图像分类 | [PaddleClas/ResNet50](./examples/vision/classification/paddleclas) | √ | √ | √ | | | [PaddleClas/PPLCNet](./examples/vision/classification/paddleclas) | √ | √ | √ | From f473aa88e690451c55f2a93e67f1f0fc662f929b Mon Sep 17 00:00:00 2001 From: Jason Date: Fri, 12 Aug 2022 21:59:04 +0800 Subject: [PATCH 3/3] Update README.md --- README.md | 76 +++++++++++++++++++++++++++++++++++++++++++++++++++++-- 1 file changed, 74 insertions(+), 2 deletions(-) diff --git a/README.md b/README.md index 4cbb3a3b55..5619db1600 100644 --- a/README.md +++ b/README.md @@ -21,7 +21,7 @@ ## 发版历史 - [v0.2.0] 2022.08.18 全面开源服务端部署代码，支持40+视觉模型在CPU/GPU，以及通过GPU TensorRT加速部署 -## 支持模型 +## 服务端模型 | 任务场景 | 模型 | CPU | NVIDIA GPU | TensorRT | | -------- | ------------------------------------------------------------ | ------- | ---------- | ------------------- | @@ -86,7 +86,7 @@ DetectionResult: [xmin, ymin, xmax, ymax, score, label_id] ... ``` -## 更多部署示例 +## 更多服务端部署示例 FastDeploy提供了大量部署示例供开发者参考，支持模型在CPU、GPU以及TensorRT的部署 @@ -99,6 +99,78 @@ FastDeploy提供了大量部署示例供开发者参考，支持模型在CPU、G - [人脸检测模型部署](examples/vision/facedet) - [更多视觉模型部署示例...](examples/vision) +### 📱轻量化SDK快速实现端侧AI推理部署 + + +| 任务场景 | 模型 | 大小(MB) | 边缘端 | 移动端 | 移动端 | +| ------------------ | ---------------------------- | --------------------- | --------------------- | ---------------------- | --------------------- | +| ---- | --- | --- | Linux | Android | iOS | +| ----- | ---- | --- | ARM CPU | ARM CPU | ARM CPU | +| Classfication | PP-LCNet | 11.9 | ✅ | ✅ | ✅ | +| | PP-LCNetv2 | 26.6 | ✅ | ✅ | ✅ | +| | EfficientNet | 31.4 | ✅ | ✅ | ✅ | +| | GhostNet | 20.8 | ✅ | ✅ | ✅ | +| | MobileNetV1 | 17 | ✅ | ✅ | ✅ | +| | MobileNetV2 | 14.2 | ✅ | ✅ | ✅ | +| | MobileNetV3 | 22 | ✅ | ✅ | ✅ | +| | ShuffleNetV2 | 9.2 | ✅ | ✅ | ✅ | +| | SqueezeNetV1.1 | 5 | ✅ | ✅ | ✅ | +| | Inceptionv3 | 95.5 | ✅ | ✅ | ✅ | +| | PP-HGNet | 59 | ✅ | ✅ | ✅ | +| | SwinTransformer_224_win7 | 352.7 | ✅ | ✅ | ✅ | +| Detection | PP-PicoDet_s_320_coco | 4.1 | ✅ | ✅ | ✅ | +| | PP-PicoDet_s_320_lcnet | 4.9 | ✅ | ✅ | ✅ | +| | CenterNet | 4.8 | ✅ | ✅ | ✅ | +| | YOLOv3_MobileNetV3 | 94.6 | ✅ | ✅ | ✅ | +| | PP-YOLO_tiny_650e_coco | 4.4 | ✅ | ✅ | ✅ | +| | SSD_MobileNetV1_300_120e_voc | 23.3 | ✅ | ✅ | ✅ | +| | PP-YOLO_ResNet50vd | 188.5 | ✅ | ✅ | ✅ | +| | PP-YOLOv2_ResNet50vd | 218.7 | ✅ | ✅ | ✅ | +| | PP-YOLO_crn_l_300e_coco | 209.1 | ✅ | ✅ | ✅ | +| | YOLOv5s | 29.3 | ✅ | ✅ | ✅ | +| Face Detection | BlazeFace | 1.5 | ✅ | ✅ | ✅ | +| Face Localisation | RetinaFace | 1.7 | ✅ | ❌ | ❌ | +| Keypoint Detection | PP-TinyPose | 5.5 | ✅ | ✅ | ✅ | +| Segmentation | PP-LiteSeg(STDC1) | 32.2 | ✅ | ✅ | ✅ | +| | PP-HumanSeg-Lite | 0.556 | ✅ | ✅ | ✅ | +| | HRNet-w18 | 38.7 | ✅ | ✅ | ✅ | +| | PP-HumanSeg-Server | 107.2 | ✅ | ✅ | ✅ | +| | Unet | 53.7 | ❌ | ✅ | ❌ | +| OCR | PP-OCRv1 | 2.3+4.4 | ✅ | ✅ | ✅ | +| | PP-OCRv2 | 2.3+4.4 | ✅ | ✅ | ✅ | +| | PP-OCRv3 | 2.4+10.6 | ✅ | ✅ | ✅ | +| | PP-OCRv3-tiny | 2.4+10.7 | ✅ | ✅ | ✅ | + + +#### 边缘侧部署 + +- ARM Linux 系统 + - [C++ Inference部署（含视频流）](./docs/ARM-Linux-CPP-SDK-Inference.md) + - [C++ 服务化部署](./docs/ARM-Linux-CPP-SDK-Serving.md) + - [Python Inference部署](./docs/ARM-Linux-Python-SDK-Inference.md) + - [Python 服务化部署](./docs/ARM-Linux-Python-SDK-Serving.md) + +#### 移动端部署 + +- [iOS 系统部署](./docs/iOS-SDK.md) +- [Android 系统部署](./docs/Android-SDK.md) + +#### 自定义模型部署 + +- [快速实现个性化模型替换](./docs/Replace-Model-With-Anther-One.md) + +## 社区交流 + +- **加入社区👬：** 微信扫描二维码后，填写问卷加入交流群，与开发者共同讨论推理部署痛点问题 + +
+ +
+ +## Acknowledge + +本项目中SDK生成和下载使用了[EasyEdge](https://ai.baidu.com/easyedge/app/openSource)中的免费开放能力，再次表示感谢。 + ## License