mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
aa6931bee9
* add onnx_ort_runtime demo * rm in requirements * support batch eval * fixed MattingResults bug * move assignment for DetectionResult * integrated x2paddle * add model convert readme * update readme * re-lint * add processor api * Add MattingResult Free * change valid_cpu_backends order * add ppocr benchmark * mv bs from 64 to 32 * fixed quantize.md * fixed quantize bugs * Add Monitor for benchmark * update mem monitor * Set trt_max_batch_size default 1 * fixed ocr benchmark bug * support yolov5 in serving * Fixed yolov5 serving * Fixed postprocess * update yolov5 to 7.0 * add poros runtime demos * update readme * Support poros abi=1 * rm useless note * deal with comments * support pp_trt for ppseg * fixed symlink problem * Add is_mini_pad and stride for yolov5 * Add yolo series for paddle format * fixed bugs * fixed bug * support yolov5seg * fixed bug * refactor yolov5seg * fixed bug * mv Mask int32 to uint8 * add yolov5seg example * rm log info * fixed code style * add yolov5seg example in python * fixed dtype bug * update note * deal with comments * get sorted index * add yolov5seg test case * Add GPL-3.0 License * add round func * deal with comments * deal with commens Co-authored-by: Jason <jiangjiajun@baidu.com>
English | 简体中文
Visual Model Deployment
This directory provides the deployment of various visual models, including the following task types
| Task Type | Description | Predicted Structure |
|---|---|---|
| Detection | Target detection. Input the image, detect the object’s position in the image, and return the detected box coordinates, category, and confidence coefficient | DetectionResult |
| Segmentation | Semantic segmentation. Input the image and output the classification and confidence coefficient of each pixel | SegmentationResult |
| Classification | Image classification. Input the image and output the classification result and confidence coefficient of the image | ClassifyResult |
| FaceDetection | Face detection. Input the image, detect the position of faces in the image, and return detected box coordinates and key points of faces | FaceDetectionResult |
| FaceAlignment | Face alignment(key points detection).Input the image and return face key points | FaceAlignmentResult |
| KeypointDetection | Key point detection. Input the image and return the coordinates and confidence coefficient of the key points of the person's behavior in the image | KeyPointDetectionResult |
| FaceRecognition | Face recognition. Input the image and return an embedding of facial features that can be used for similarity calculation | FaceRecognitionResult |
| Matting | Matting. Input the image and return the Alpha value of each pixel in the foreground of the image | MattingResult |
| OCR | Text box detection, classification, and text box content recognition. Input the image and return the text box’s coordinates, orientation category, and content | OCRResult |
| MOT | Multi-objective tracking. Input the image and detect the position of objects in the image, and return detected box coordinates, object id, and class confidence | MOTResult |
| HeadPose | Head posture estimation. Return head Euler angle | HeadPoseResult |
FastDeploy API Design
Generally, visual models have a uniform task paradigm. When designing API (including C++/Python), FastDeploy conducts four steps to deploy visual models
- Model loading
- Image pre-processing
- Model Inference
- Post-processing of inference results
Targeted at the vision suite of PaddlePaddle and external popular models, FastDeploy provides an end-to-end deployment service. Users merely prepare the model and follow these steps to complete the deployment
- Model Loading
- Calling the
predictinterface
When deploying visual models, FastDeploy supports one-click switching of the backend inference engine. Please refer to How to switch model inference engine.