mirrors
/
mmdeploy
mirror of https://github.com/open-mmlab/mmdeploy.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

Update readme intro image and docs (#2175) 

* update logo

* update

* update

* update

* fix ci

* Revert "update logo"

This reverts commit 6935ff0bce.

* update intro

* fix
pull/2186/head
RunningLeon 2023-06-14 16:16:25 +08:00 committed by GitHub
parent f6a116894b
commit a8775d2cf1
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
17 changed files with 206 additions and 76 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

10
.github/workflows/build.yml vendored
View File

@ -203,14 +203,14 @@ jobs:
build_cuda113:
runs-on: ubuntu-20.04
container:
image: pytorch/pytorch:1.10.0-cuda11.3-cudnn8-devel
image: pytorch/pytorch:1.12.0-cuda11.3-cudnn8-devel
strategy:
matrix:
torch: [1.10.0+cu113]
torch: [1.12.0+cu113]
include:
- torch: 1.10.0+cu113
torch_version: torch1.10
torchvision: 0.11.0+cu113
- torch: 1.12.0+cu113
torch_version: torch1.12
torchvision: 0.13.0+cu113
steps:
- uses: actions/checkout@v2
- name: Install system dependencies

2
.github/workflows/docker.yml vendored
View File

@ -44,7 +44,7 @@ jobs:
run: |
echo $MMDEPLOY_VERSION
echo $TAG
docker build docker/Release/ -t ${TAG} --build-arg MMDEPLOY_VERSION=${MMDEPLOY_VERSION}
docker build docker/Release/ -t ${TAG} --no-cache --build-arg MMDEPLOY_VERSION=${MMDEPLOY_VERSION}
- name: Push Docker image
continue-on-error: true
run: |

18
configs/mmpose/pose-detection_simcc_openvino_static-256x192.py 100644
View File

@ -0,0 +1,18 @@
_base_ = ['./pose-detection_static.py', '../_base_/backends/openvino.py']
backend_config = dict(
model_inputs=[dict(opt_shapes=dict(input=[1, 3, 256, 192]))])
onnx_config = dict(
input_shape=[192, 256],
output_names=['simcc_x', 'simcc_y'],
dynamic_axes={
'input': {
0: 'batch',
},
'simcc_x': {
0: 'batch'
},
'simcc_y': {
0: 'batch'
}
})

4
docs/en/03-benchmark/supported_models.md
View File

@ -17,11 +17,11 @@ The table below lists the models that are guaranteed to be exportable to other b
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | Y | Y | N | N |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | N | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | MMDetection | N | N | N | N | N | Y | N | N |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | MMDetection | N | N | Y | N | ? | Y | N | N |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | MMDetection | N | Y | N | N | N | Y | N | N |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | MMDetection | N | Y | N | N | N | Y | N | N |
| [ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |

6
docs/en/04-supported-codebases/mmdet.md
View File

@ -206,10 +206,10 @@ Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Inter
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | Object Detection | Y | Y | N | ? | Y |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | Object Detection | N | Y | N | ? | Y |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | Object Detection | Y | Y | N | ? | Y |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | Object Detection | Y | Y | N | ? | ? |
| [RTMDet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet) | Object Detection | Y | Y | N | ? | ? |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | Object Detection | Y | Y | N | ? | Y |
| [RTMDet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet) | Object Detection | Y | Y | N | ? | Y |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | Instance Segmentation | Y | Y | N | N | Y |
| [Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/mask_rcnn) | Instance Segmentation | Y | Y | N | N | Y |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin) | Instance Segmentation | Y | Y | N | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin) | Instance Segmentation | Y | Y | N | N | Y |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | Instance Segmentation | Y | N | N | N | Y |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | Instance Segmentation | Y | N | N | N | Y |

2
docs/en/04-supported-codebases/mmpose.md
View File

@ -158,5 +158,5 @@ TODO
| [MSPN](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#mspn-arxiv-2019) | PoseDetection | Y | Y | Y | N | Y |
| [LiteHRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | PoseDetection | Y | Y | Y | N | Y |
| [Hourglass](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#hourglass-eccv-2016) | PoseDetection | Y | Y | Y | N | Y |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | N |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | Y |
| [RTMPose](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose) | PoseDetection | Y | Y | Y | N | Y |

8
docs/en/04-supported-codebases/mmpretrain.md
View File

@ -181,8 +181,8 @@ Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Inter
| [ShuffleNetV1](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) | Y | Y | Y | Y | Y | Y |
| [VisionTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) | Y | Y | Y | Y | ? | Y |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | Y | Y | Y | N | ? | N |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | Y | Y | N | N | ? | N |
| [EfficientNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/efficientnet) | Y | Y | N | N | ? | N |
| [Conformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/conformer) | Y | Y | N | N | ? | N |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | Y | Y | Y | N | ? | Y |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | Y | Y | Y | Y | ? | Y |
| [EfficientNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/efficientnet) | Y | Y | Y | N | ? | Y |
| [Conformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/conformer) | Y | Y | Y | N | ? | Y |
| [EfficientFormer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/efficientformer) | Y | Y | Y | N | ? | Y |

46
docs/en/05-supported-backends/onnxruntime.md
View File

@ -1,4 +1,4 @@
# ONNX Runtime Support
# onnxruntime 支持情况
## Introduction of ONNX Runtime
@ -6,19 +6,29 @@
## Installation
*Please note that only **onnxruntime>=1.8.1** of CPU version on Linux platform is supported by now.*
*Please note that only **onnxruntime>=1.8.1** of on Linux platform is supported by now.*
- Install ONNX Runtime python package
### Install ONNX Runtime python package
- CPU Version
```bash
pip install onnxruntime==1.8.1
pip install onnxruntime==1.8.1 # if you want to use cpu version
```
- GPU Version
```bash
pip install onnxruntime-gpu==1.8.1 # if you want to use gpu version
```
## Build custom ops
### Prerequisite
### Download ONNXRuntime Library
- Download `onnxruntime-linux` from ONNX Runtime [releases](https://github.com/microsoft/onnxruntime/releases/tag/v1.8.1), extract it, expose `ONNXRUNTIME_DIR` and finally add the lib path to `LD_LIBRARY_PATH` as below:
Download `onnxruntime-linux-*.tgz` library from ONNX Runtime [releases](https://github.com/microsoft/onnxruntime/releases/tag/v1.8.1), extract it, expose `ONNXRUNTIME_DIR` and finally add the lib path to `LD_LIBRARY_PATH` as below:
- CPU Version
```bash
wget https://github.com/microsoft/onnxruntime/releases/download/v1.8.1/onnxruntime-linux-x64-1.8.1.tgz
@ -29,12 +39,34 @@ export ONNXRUNTIME_DIR=$(pwd)
export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH
```
- GPU Version
```bash
wget https://github.com/microsoft/onnxruntime/releases/download/v1.8.1/onnxruntime-linux-x64-gpu-1.8.1.tgz
tar -zxvf onnxruntime-linux-x64-gpu-1.8.1.tgz
cd onnxruntime-linux-x64-gpu-1.8.1
export ONNXRUNTIME_DIR=$(pwd)
export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH
```
### Build on Linux
- CPU Version
```bash
cd ${MMDEPLOY_DIR} # To MMDeploy root directory
mkdir -p build && cd build
cmake -DMMDEPLOY_TARGET_BACKENDS=ort -DONNXRUNTIME_DIR=${ONNXRUNTIME_DIR} ..
cmake -DMMDEPLOY_TARGET_DEVICES='cpu' -DMMDEPLOY_TARGET_BACKENDS=ort -DONNXRUNTIME_DIR=${ONNXRUNTIME_DIR} ..
make -j$(nproc) && make install
```
- GPU Version
```bash
cd ${MMDEPLOY_DIR} # To MMDeploy root directory
mkdir -p build && cd build
cmake -DMMDEPLOY_TARGET_DEVICES='cuda' -DMMDEPLOY_TARGET_BACKENDS=ort -DONNXRUNTIME_DIR=${ONNXRUNTIME_DIR} ..
make -j$(nproc) && make install
```

34
docs/en/05-supported-backends/openvino.md
View File

@ -6,21 +6,45 @@ This tutorial is based on Linux systems like Ubuntu-18.04.
It is recommended to create a virtual environment for the project.
1. Install [OpenVINO](https://docs.openvino.ai/2021.4/get_started.html). It is recommended to use the installer or install using pip.
Installation example using [pip](https://pypi.org/project/openvino-dev/):
### Install python package
Install [OpenVINO](https://docs.openvino.ai/2022.3/get_started.html). It is recommended to use the installer or install using pip.
Installation example using [pip](https://pypi.org/project/openvino-dev/):
```bash
pip install openvino-dev
pip install openvino-dev[onnx]==2022.3.0
```
2. \*`Optional` If you want to use OpenVINO in SDK, you need install OpenVINO with [install_guides](https://docs.openvino.ai/2021.4/openvino_docs_install_guides_installing_openvino_linux.html#install-openvino).
### Download OpenVINO runtime for SDK (Optional)
3. Install MMDeploy following the [instructions](../01-how-to-build/build_from_source.md).
If you want to use OpenVINO in SDK, you need install OpenVINO with [install_guides](https://docs.openvino.ai/2022.3/openvino_docs_install_guides_installing_openvino_from_archive_linux.html#installing-openvino-runtime).
Take `openvino==2022.3.0` as example:
```bash
wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3/linux/l_openvino_toolkit_ubuntu20_2022.3.0.9052.9752fafe8eb_x86_64.tgz
tar xzf ./l_openvino_toolkit*.tgz
cd l_openvino*
export InferenceEngine_DIR=$pwd/runtime/cmake
bash ./install_dependencies/install_openvino_dependencies.sh
```
### Build mmdeploy SDK with OpenVINO (Optional)
Install MMDeploy following the [instructions](../01-how-to-build/build_from_source.md).
```bash
cd ${MMDEPLOY_DIR} # To MMDeploy root directory
mkdir -p build && cd build
cmake -DMMDEPLOY_TARGET_DEVICES='cpu' -DMMDEPLOY_TARGET_BACKENDS=openvino -DInferenceEngine_DIR=${InferenceEngine_DIR} ..
make -j$(nproc) && make install
```
To work with models from [MMDetection](https://mmdetection.readthedocs.io/en/3.x/get_started.html), you may need to install it additionally.
## Usage
You could follow the instructions of tutorial [How to convert model](../02-how-to-run/convert_model.md)
Example:
```bash

10
docs/zh_cn/03-benchmark/supported_models.md
View File

@ -17,11 +17,11 @@
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | Y | Y | N | N |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | N | N | N |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin)[\*](#note) | MMDetection | N | Y | Y | N | N | Y | N | N |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | MMDetection | N | N | N | N | N | Y | N | N |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | MMDetection | N | N | Y | N | ? | Y | N | N |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | N | N | N |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | MMDetection | N | Y | Y | N | ? | Y | N | N |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | MMDetection | N | Y | N | N | N | Y | N | N |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | MMDetection | N | Y | N | N | N | Y | N | N |
| [ResNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/resnet) | MMPretrain | Y | Y | Y | Y | Y | Y | Y | Y |
@ -85,9 +85,9 @@
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | MMPose | N | Y | Y | Y | N | N | N | N |
| [PointPillars](https://github.com/open-mmlab/mmdetection3d/tree/main/configs/pointpillars) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [CenterPoint (pillar)](https://github.com/open-mmlab/mmdetection3d/tree/main/configs/centerpoint) | MMDetection3d | ? | Y | Y | N | N | Y | N | N |
| [RotatedRetinaNet](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_retinanet/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Oriented RCNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/oriented_rcnn/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/gliding_vertex/README.md) | RotatedDetection | N | N | Y | N | N | N | N | N |
| [RotatedRetinaNet](https://github.com/open-mmlab/mmrotate/blob/main/configs/rotated_retinanet/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Oriented RCNN](https://github.com/open-mmlab/mmrotate/blob/main/configs/oriented_rcnn/README.md) | RotatedDetection | N | Y | Y | N | N | N | N | N |
| [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/main/configs/gliding_vertex/README.md) | RotatedDetection | N | N | Y | N | N | N | N | N |
## Note

48
docs/zh_cn/04-supported-codebases/mmdet.md
View File

@ -192,27 +192,27 @@ cv2.imwrite('output_detection.png', img)
## 模型支持列表
| Model | Task | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO |
| :-------------------------------------------------------------------------------------------: | :------------------: | :---------: | :------: | :--: | :---: | :------: |
| [ATSS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/atss) | ObjectDetection | Y | Y | N | N | Y |
| [FCOS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fcos) | ObjectDetection | Y | Y | Y | N | Y |
| [FoveaBox](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/foveabox) | ObjectDetection | Y | N | N | N | Y |
| [FSAF](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fsaf) | ObjectDetection | Y | Y | Y | Y | Y |
| [RetinaNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/retinanet) | ObjectDetection | Y | Y | Y | Y | Y |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/ssd) | ObjectDetection | Y | Y | Y | N | Y |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | ObjectDetection | N | N | N | N | Y |
| [YOLOv3](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolo) | ObjectDetection | Y | Y | Y | N | Y |
| [YOLOX](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolox) | ObjectDetection | Y | Y | Y | N | Y |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | ObjectDetection | Y | Y | N | Y | Y |
| [Faster R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | ObjectDetection | Y | Y | Y | Y | Y |
| [Faster R-CNN + DCN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | ObjectDetection | Y | Y | Y | Y | Y |
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | ObjectDetection | Y | Y | N | ? | Y |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | ObjectDetection | N | Y | N | ? | Y |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | ObjectDetection | Y | Y | N | ? | Y |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | Object Detection | Y | Y | N | ? | ? |
| [RTMDet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet) | Object Detection | Y | Y | N | ? | ? |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | InstanceSegmentation | Y | Y | N | N | Y |
| [Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/mask_rcnn) | InstanceSegmentation | Y | Y | N | N | Y |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin) | InstanceSegmentation | Y | Y | N | N | N |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | InstanceSegmentation | Y | N | N | N | Y |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | InstanceSegmentation | Y | N | N | N | Y |
| Model | Task | OnnxRuntime | TensorRT | ncnn | PPLNN | OpenVINO |
| :-------------------------------------------------------------------------------------------: | :-------------------: | :---------: | :------: | :--: | :---: | :------: |
| [ATSS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/atss) | Object Detection | Y | Y | N | N | Y |
| [FCOS](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fcos) | Object Detection | Y | Y | Y | N | Y |
| [FoveaBox](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/foveabox) | Object Detection | Y | N | N | N | Y |
| [FSAF](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/fsaf) | Object Detection | Y | Y | Y | Y | Y |
| [RetinaNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/retinanet) | Object Detection | Y | Y | Y | Y | Y |
| [SSD](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/ssd) | Object Detection | Y | Y | Y | N | Y |
| [VFNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/vfnet) | Object Detection | N | N | N | N | Y |
| [YOLOv3](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolo) | Object Detection | Y | Y | Y | N | Y |
| [YOLOX](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/yolox) | Object Detection | Y | Y | Y | N | Y |
| [Cascade R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | Object Detection | Y | Y | N | Y | Y |
| [Faster R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | Object Detection | Y | Y | Y | Y | Y |
| [Faster R-CNN + DCN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/faster_rcnn) | Object Detection | Y | Y | Y | Y | Y |
| [GFL](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/gfl) | Object Detection | Y | Y | N | ? | Y |
| [RepPoints](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/reppoints) | Object Detection | N | Y | N | ? | Y |
| [DETR](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/detr) | Object Detection | Y | Y | N | ? | Y |
| [CenterNet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/centernet) | Object Detection | Y | Y | N | ? | Y |
| [RTMDet](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/rtmdet) | Object Detection | Y | Y | N | ? | Y |
| [Cascade Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/cascade_rcnn) | Instance Segmentation | Y | Y | N | N | Y |
| [Mask R-CNN](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/mask_rcnn) | Instance Segmentation | Y | Y | N | N | Y |
| [Swin Transformer](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/swin) | Instance Segmentation | Y | Y | N | N | Y |
| [SOLO](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solo) | Instance Segmentation | Y | N | N | N | Y |
| [SOLOv2](https://github.com/open-mmlab/mmdetection/tree/3.x/configs/solov2) | Instance Segmentation | Y | N | N | N | Y |

2
docs/zh_cn/04-supported-codebases/mmpose.md
View File

@ -162,5 +162,5 @@ task_processor.visualize(
| [MSPN](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#mspn-arxiv-2019) | PoseDetection | Y | Y | Y | N | Y |
| [LiteHRNet](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/backbones.html#litehrnet-cvpr-2021) | PoseDetection | Y | Y | Y | N | Y |
| [Hourglass](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#hourglass-eccv-2016) | PoseDetection | Y | Y | Y | N | Y |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | N |
| [SimCC](https://mmpose.readthedocs.io/en/latest/model_zoo_papers/algorithms.html#simcc-eccv-2022) | PoseDetection | Y | Y | Y | N | Y |
| [RTMPose](https://github.com/open-mmlab/mmpose/tree/main/projects/rtmpose) | PoseDetection | Y | Y | Y | N | Y |

8
docs/zh_cn/04-supported-codebases/mmpretrain.md
View File

@ -186,8 +186,8 @@ for label_id, score in result:
| [ShuffleNetV1](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v1) | Y | Y | Y | Y | Y | Y |
| [ShuffleNetV2](https://github.com/open-mmlab/mmpretrain/tree/main/configs/shufflenet_v2) | Y | Y | Y | Y | Y | Y |
| [VisionTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/vision_transformer) | Y | Y | Y | Y | ? | Y |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | Y | Y | Y | N | ? | N |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | Y | Y | N | N | ? | N |
| [EfficientNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/efficientnet) | Y | Y | N | N | ? | N |
| [Conformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/conformer) | Y | Y | N | N | ? | N |
| [SwinTransformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/swin_transformer) | Y | Y | Y | N | ? | Y |
| [MobileOne](https://github.com/open-mmlab/mmpretrain/tree/main/configs/mobileone) | Y | Y | Y | Y | ? | Y |
| [EfficientNet](https://github.com/open-mmlab/mmpretrain/tree/main/configs/efficientnet) | Y | Y | Y | N | ? | Y |
| [Conformer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/conformer) | Y | Y | Y | N | ? | Y |
| [EfficientFormer](https://github.com/open-mmlab/mmpretrain/tree/main/configs/efficientformer) | Y | Y | Y | N | ? | Y |

44
docs/zh_cn/05-supported-backends/onnxruntime.md
View File

@ -6,19 +6,29 @@
## Installation
*Please note that only **onnxruntime>=1.8.1** of CPU version on Linux platform is supported by now.*
*Please note that only **onnxruntime>=1.8.1** of on Linux platform is supported by now.*
- Install ONNX Runtime python package
### Install ONNX Runtime python package
- CPU Version
```bash
pip install onnxruntime==1.8.1
pip install onnxruntime==1.8.1 # if you want to use cpu version
```
- GPU Version
```bash
pip install onnxruntime-gpu==1.8.1 # if you want to use gpu version
```
## Build custom ops
### Prerequisite
### Download ONNXRuntime Library
- Download `onnxruntime-linux` from ONNX Runtime [releases](https://github.com/microsoft/onnxruntime/releases/tag/v1.8.1), extract it, expose `ONNXRUNTIME_DIR` and finally add the lib path to `LD_LIBRARY_PATH` as below:
Download `onnxruntime-linux-*.tgz` library from ONNX Runtime [releases](https://github.com/microsoft/onnxruntime/releases/tag/v1.8.1), extract it, expose `ONNXRUNTIME_DIR` and finally add the lib path to `LD_LIBRARY_PATH` as below:
- CPU Version
```bash
wget https://github.com/microsoft/onnxruntime/releases/download/v1.8.1/onnxruntime-linux-x64-1.8.1.tgz
@ -29,12 +39,34 @@ export ONNXRUNTIME_DIR=$(pwd)
export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH
```
- GPU Version
```bash
wget https://github.com/microsoft/onnxruntime/releases/download/v1.8.1/onnxruntime-linux-x64-gpu-1.8.1.tgz
tar -zxvf onnxruntime-linux-x64-gpu-1.8.1.tgz
cd onnxruntime-linux-x64-gpu-1.8.1
export ONNXRUNTIME_DIR=$(pwd)
export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH
```
### Build on Linux
- CPU Version
```bash
cd ${MMDEPLOY_DIR} # To MMDeploy root directory
mkdir -p build && cd build
cmake -DMMDEPLOY_TARGET_BACKENDS=ort -DONNXRUNTIME_DIR=${ONNXRUNTIME_DIR} ..
cmake -DMMDEPLOY_TARGET_DEVICES='cpu' -DMMDEPLOY_TARGET_BACKENDS=ort -DONNXRUNTIME_DIR=${ONNXRUNTIME_DIR} ..
make -j$(nproc) && make install
```
- GPU Version
```bash
cd ${MMDEPLOY_DIR} # To MMDeploy root directory
mkdir -p build && cd build
cmake -DMMDEPLOY_TARGET_DEVICES='cuda' -DMMDEPLOY_TARGET_BACKENDS=ort -DONNXRUNTIME_DIR=${ONNXRUNTIME_DIR} ..
make -j$(nproc) && make install
```

38
docs/zh_cn/05-supported-backends/openvino.md
View File

@ -1,4 +1,4 @@
# OpenVINO 支持情况
# OpenVINO Support
This tutorial is based on Linux systems like Ubuntu-18.04.
@ -6,21 +6,45 @@ This tutorial is based on Linux systems like Ubuntu-18.04.
It is recommended to create a virtual environment for the project.
1. Install [OpenVINO](https://docs.openvino.ai/2021.4/get_started.html). It is recommended to use the installer or install using pip.
Installation example using [pip](https://pypi.org/project/openvino-dev/):
### Install python package
Install [OpenVINO](https://docs.openvino.ai/2022.3/get_started.html). It is recommended to use the installer or install using pip.
Installation example using [pip](https://pypi.org/project/openvino-dev/):
```bash
pip install openvino-dev
pip install openvino-dev[onnx]==2022.3.0
```
2. \*`Optional` If you want to use OpenVINO in SDK, you need install OpenVINO with [install_guides](https://docs.openvino.ai/2021.4/openvino_docs_install_guides_installing_openvino_linux.html#install-openvino).
### Download OpenVINO runtime for SDK (Optional)
3. Install MMDeploy following the [instructions](../01-how-to-build/build_from_source.md).
If you want to use OpenVINO in SDK, you need install OpenVINO with [install_guides](https://docs.openvino.ai/2022.3/openvino_docs_install_guides_installing_openvino_from_archive_linux.html#installing-openvino-runtime).
Take `openvino==2022.3.0` as example:
To work with models from [MMDetection](https://github.com/open-mmlab/mmdetection/blob/3.x/docs/en/get_started.md), you may need to install it additionally.
```bash
wget https://storage.openvinotoolkit.org/repositories/openvino/packages/2022.3/linux/l_openvino_toolkit_ubuntu20_2022.3.0.9052.9752fafe8eb_x86_64.tgz
tar xzf ./l_openvino_toolkit*.tgz
cd l_openvino*
export InferenceEngine_DIR=$pwd/runtime/cmake
bash ./install_dependencies/install_openvino_dependencies.sh
```
### Build mmdeploy SDK with OpenVINO (Optional)
Install MMDeploy following the [instructions](../01-how-to-build/build_from_source.md).
```bash
cd ${MMDEPLOY_DIR} # To MMDeploy root directory
mkdir -p build && cd build
cmake -DMMDEPLOY_TARGET_DEVICES='cpu' -DMMDEPLOY_TARGET_BACKENDS=openvino -DInferenceEngine_DIR=${InferenceEngine_DIR} ..
make -j$(nproc) && make install
```
To work with models from [MMDetection](https://mmdetection.readthedocs.io/en/3.x/get_started.html), you may need to install it additionally.
## Usage
You could follow the instructions of tutorial [How to convert model](../02-how-to-run/convert_model.md)
Example:
```bash

BIN
resources/introduction.png
View File

Binary file not shown.
Side by Side Swipe Overlay

Before

Width:  |  Height:  |  Size: 206 KiB

After

Width:  |  Height:  |  Size: 701 KiB

2
tests/test_apis/test_onnx_passes.py
View File

@ -164,7 +164,7 @@ def test_flatten_cls_head():
batch = x.size(0)
gap = nn.functional.adaptive_avg_pool2d(x, (1, 1))
gap = gap.reshape(batch, -1)
return gap + 0 # gap should not be the output
return gap + 1 # gap should not be the output
model = TestModel()
x = torch.rand(1, 4, 8, 8)