c5a87fb1bc
* Fix include and lib paths for onnxruntime. * Fixes for SSD export test * Add onnx2openvino and OpenVINODetector. Test models: ssd, retinanet, fcos, fsaf. * Add support for two-stage models: faster_rcnn, cascade_rcnn * Add doc * Add strip_doc_string for openvino. * Fix openvino preprocess. * Add OpenVINO to test_wrapper.py. * Fix * Add openvino_execute. * Removed preprocessing. * Fix onnxruntime cmake. * Rewrote postprocessing and forward, added docstrings and fixes. * Added device type change to OpenVINOWrapper. * Update forward_of_single_roi_extractor_dynamic_openvino and fix doc. * Update docs. * Add OpenVINODetector and onn2openvino tests. * Add input_info to onnx2openvino. * Add TestOpenVINOExporter and test_single_roi_extractor. * Moved get_input_shape_from_cfg to openvino_utils.py and added test. * Added test_cascade_roi_head. * Add backend.check_env() to tests. * Add OpenVINO to get_rewrite_outputs and to some tests in test_mmdet_models. * Moved test_single_roi_extractor to test_mmdet_models. * Removed TestOpenVINOExporter.
Introduction
English | 简体中文
MMDeploy is an open-source deep learning model deployment toolset. It is a part of the OpenMMLab project.
Major features
-
OpenMMLab model support Models in OpenMMLab can be deployed with this project. Such as MMClassification, MMDetection, etc.
-
Multiple inference engine support Models can be export and inference with different backend. Such as ONNX Runtime, TensorRT, etc.
-
Model rewrite Modules and functions used in models can be rewritten to meet the demond of different backend. It is easy to add new model support.
License
This project is released under the Apache 2.0 license.
Codebase and Backend support
Supported codebase:
- MMClassification
- MMDetection
- MMSegmentation
- MMEditing
- MMOCR
Supported backend:
- ONNX Runtime
- TensorRT
- PPL
- ncnn
Installation
Please refer to build.md for installation.
Getting Started
Please read how_to_convert_model.md for the basic usage of MMDeploy. There are also tutorials for how to create config, how to support new model and how to test model.
Please refer to FAQ for frequently asked questions.
Contributing
We appreciate all contributions to improve MMDeploy. Please refer to CONTRIBUTING.md for the contributing guideline.
Projects in OpenMMLab
- MMCV: OpenMMLab foundational library for computer vision.
- MIM: MIM Installs OpenMMLab Packages.
- MMClassification: OpenMMLab image classification toolbox and benchmark.
- MMDetection: OpenMMLab detection toolbox and benchmark.
- MMDetection3D: OpenMMLab's next-generation platform for general 3D object detection.
- MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark.
- MMAction2: OpenMMLab's next-generation action understanding toolbox and benchmark.
- MMTracking: OpenMMLab video perception toolbox and benchmark.
- MMPose: OpenMMLab pose estimation toolbox and benchmark.
- MMEditing: OpenMMLab image and video editing toolbox.
- MMOCR: A Comprehensive Toolbox for Text Detection, Recognition and Understanding.
- MMGeneration: OpenMMLab image and video generative models toolbox.