apps/FastDeploy
1
0
Fork 0
mirror of https://github.com/PaddlePaddle/FastDeploy.git synced 2025-10-25 09:31:38 +08:00
Code Issues Actions 4 Packages Projects Releases Wiki Activity
Files
fdea6f1454dd529ab488095d2a96a8a88b06b84c
FastDeploy/examples/vision
History
WJJ1995 ea0bac4061 [Benchmark] Add GPU OpenVIVO Option in benchmark (#786) 
* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

* update python api_docs

* update index.rst

* add runtime cpp examples

* deal with comments

* Update infer_paddle_tensorrt.py

* Add runtime quick start

* deal with comments

* fixed reused_input_tensors&&reused_output_tensors

* fixed docs

* fixed headpose typo

* fixed typo

* refactor yolov5

* update model infer

* refactor pybind for yolov5

* rm origin yolov5

* fixed bugs

* rm cuda preprocess

* fixed bugs

* fixed bugs

* fixed bug

* fixed bug

* fix pybind

* rm useless code

* add convert_and_permute

* fixed bugs

* fixed im_info for bs_predict

* fixed bug

* add bs_predict for yolov5

* Add runtime test and batch eval

* deal with comments

* fixed bug

* update testcase

* fixed batch eval bug

* fixed preprocess bug

* refactor yolov7

* add yolov7 testcase

* rm resize_after_load and add is_scale_up

* fixed bug

* set multi_label true

* optimize rvm preprocess

* optimizer rvm postprocess

* fixed bug

* deal with comments

* fixed bugs

* add gpu ov for benchmark

Co-authored-by: Jason <928090362@qq.com>
Co-authored-by: Jason <jiangjiajun@baidu.com>
2022-12-05 10:51:13 +08:00
..
classification
[Doc][Serving]serving doc update version to 1.0.0 (#755)
2022-11-30 14:41:42 +08:00
detection
[Benchmark] Add GPU OpenVIVO Option in benchmark (#786)
2022-12-05 10:51:13 +08:00
facealign
Rename PaddleBackend to PaddleInferBackend (#728)
2022-11-28 21:29:09 +08:00
facedet
[Android] add enableCamera method app examples (#751)
2022-11-30 10:41:01 +08:00
faceid
[Doc] Fix the version statement for all example docs (#654)
2022-11-22 15:00:00 +08:00
headpose
Rename PaddleBackend to PaddleInferBackend (#728)
2022-11-28 21:29:09 +08:00
keypointdetection
[Doc] Fix the version statement for all example docs (#654)
2022-11-22 15:00:00 +08:00
matting
Rename PaddleBackend to PaddleInferBackend (#728)
2022-11-28 21:29:09 +08:00
ocr
[Bug Fix] Modify TRT dynamic input shape for PP-OCRv2 python demo. (#775)
2022-12-02 11:19:00 +08:00
segmentation/paddleseg
[Other] Update deprecated segmentation apis && segmentation label map resize interinterpolation (#790)
2022-12-05 09:57:54 +08:00
sr
[Model] Modify SR (#674)
2022-11-25 18:31:22 +08:00
tracking/pptracking
[Doc] Fix the version statement for all example docs (#654)
2022-11-22 15:00:00 +08:00
README.md
[Doc] Fix dead links (#517)
2022-11-07 20:49:41 +08:00

README.md

视觉模型部署

本目录下提供了各类视觉模型的部署，主要涵盖以下任务类型

任务类型 说明 预测结果结构体
Detection 目标检测，输入图像，检测图像中物体位置，并返回检测框坐标及类别和置信度 DetectionResult
Segmentation 语义分割，输入图像，给出图像中每个像素的分类及置信度 SegmentationResult
Classification 图像分类，输入图像，给出图像的分类结果和置信度 ClassifyResult
FaceDetection 人脸检测，输入图像，检测图像中人脸位置，并返回检测框坐标及人脸关键点 FaceDetectionResult
FaceAlignment 人脸对齐(人脸关键点检测)，输入图像，返回人脸关键点 FaceAlignmentResult
KeypointDetection 关键点检测，输入图像，返回图像中人物行为的各个关键点坐标和置信度 KeyPointDetectionResult
FaceRecognition 人脸识别，输入图像，返回可用于相似度计算的人脸特征的embedding FaceRecognitionResult
Matting 抠图，输入图像，返回图片的前景每个像素点的Alpha值 MattingResult
OCR 文本框检测，分类，文本框内容识别，输入图像，返回文本框坐标，文本框的方向类别以及框内的文本内容 OCRResult
MOT 多目标跟踪，输入图像，检测图像中物体位置，并返回检测框坐标，对象id及类别置信度 MOTResult
HeadPose 头部姿态估计，返回头部欧拉角 HeadPoseResult

FastDeploy API设计

视觉模型具有较有统一任务范式，在设计API时（包括C++/Python），FastDeploy将视觉模型的部署拆分为四个步骤

  • 模型加载
  • 图像预处理
  • 模型推理
  • 推理结果后处理

FastDeploy针对飞桨的视觉套件，以及外部热门模型，提供端到端的部署服务，用户只需准备模型，按以下步骤即可完成整个模型的部署

  • 加载模型
  • 调用predict接口

FastDeploy在各视觉模型部署时，也支持一键切换后端推理引擎，详情参阅如何切换模型推理引擎。