[Enhancement]: add md link check github action (#1320)
* add md link check action * add config * fix doc link * fix dead links * change dev-1.x to 1.x * fix mmocr urlpull/1401/head^2
RunningLeon
GitHub
parent
09c6bd75aa
commit
25aa0d4c0a
.github
demo/tutorials
docker
CPU
GPU
docs
en
01-how-to-build
02-how-to-run
03-benchmark
05-supported-backends
zh_cn
01-how-to-build
02-how-to-run
03-benchmark
05-supported-backends
mmdeploy/apis/onnx/passes
|
|
@ -9,7 +9,7 @@ body:
|
|||
label: Checklist
|
||||
options:
|
||||
- label: I have searched related issues but cannot get the expected help.
|
||||
- label: 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md) but cannot get the expected help.
|
||||
- label: 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/faq.md) but cannot get the expected help.
|
||||
- label: 3. The bug has not been fixed in the latest version.
|
||||
- type: textarea
|
||||
attributes:
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@ blank_issues_enabled: false
|
|||
|
||||
contact_links:
|
||||
- name: 💥 FAQ
|
||||
url: https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/faq.md
|
||||
url: https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/faq.md
|
||||
about: Check if your issue already has solutions
|
||||
- name: 💬 Forum
|
||||
url: https://github.com/open-mmlab/mmdeploy/discussions
|
||||
|
|
|
|||
|
|
@ -0,0 +1,33 @@
|
|||
{
|
||||
"ignorePatterns": [
|
||||
|
||||
{
|
||||
"pattern": "^https://developer.nvidia.com/"
|
||||
},
|
||||
{
|
||||
"pattern": "^https://docs.openvino.ai/"
|
||||
},
|
||||
{
|
||||
"pattern": "^https://developer.android.com/"
|
||||
},
|
||||
{
|
||||
"pattern": "^https://developer.qualcomm.com/"
|
||||
},
|
||||
{
|
||||
"pattern": "^http://localhost"
|
||||
}
|
||||
],
|
||||
"httpHeaders": [
|
||||
{
|
||||
"urls": ["https://github.com/", "https://guides.github.com/", "https://help.github.com/", "https://docs.github.com/"],
|
||||
"headers": {
|
||||
"Accept-Encoding": "zstd, br, gzip, deflate"
|
||||
}
|
||||
}
|
||||
],
|
||||
"timeout": "20s",
|
||||
"retryOn429": true,
|
||||
"retryCount": 5,
|
||||
"fallbackRetryDelay": "30s",
|
||||
"aliveStatusCodes": [200, 206, 429]
|
||||
}
|
||||
|
|
@ -27,6 +27,15 @@ jobs:
|
|||
run: |
|
||||
python .github/scripts/check_index_rst.py docs/en/index.rst
|
||||
python .github/scripts/check_index_rst.py docs/zh_cn/index.rst
|
||||
- name: Check markdown link
|
||||
uses: gaurav-nelson/github-action-markdown-link-check@v1
|
||||
with:
|
||||
use-quiet-mode: 'yes'
|
||||
use-verbose-mode: 'yes'
|
||||
# check-modified-files-only: 'yes'
|
||||
config-file: '.github/md-link-config.json'
|
||||
folder-path: 'docs/en, docs/zh_cn'
|
||||
file-path: './README.md, ./LICENSE, ./README_zh-CN.md'
|
||||
- name: Check doc link
|
||||
run: |
|
||||
python .github/scripts/doc_link_checker.py --target docs/zh_cn
|
||||
|
|
|
|||
|
|
@ -19,10 +19,10 @@
|
|||
<div> </div>
|
||||
</div>
|
||||
|
||||
[](https://mmdeploy.readthedocs.io/en/latest/)
|
||||
[](https://mmdeploy.readthedocs.io/en/1.x/)
|
||||
[](https://github.com/open-mmlab/mmdeploy/actions)
|
||||
[](https://codecov.io/gh/open-mmlab/mmdeploy)
|
||||
[](https://github.com/open-mmlab/mmdeploy/blob/master/LICENSE)
|
||||
[](https://codecov.io/gh/open-mmlab/mmdeploy)
|
||||
[](https://github.com/open-mmlab/mmdeploy/tree/1.x/LICENSE)
|
||||
[](https://github.com/open-mmlab/mmdeploy/issues)
|
||||
[](https://github.com/open-mmlab/mmdeploy/issues)
|
||||
|
||||
|
|
@ -75,7 +75,7 @@ The benchmark can be found from [here](docs/en/03-benchmark/benchmark.md)
|
|||
|
||||
All kinds of modules in the SDK can be extended, such as `Transform` for image processing, `Net` for Neural Network inference, `Module` for postprocessing and so on
|
||||
|
||||
## [Documentation](https://mmdeploy.readthedocs.io/en/latest/)
|
||||
## [Documentation](https://mmdeploy.readthedocs.io/en/1.x/)
|
||||
|
||||
Please read [getting_started](docs/en/get_started.md) for the basic usage of MMDeploy. We also provide tutoials about:
|
||||
|
||||
|
|
|
|||
|
|
@ -19,10 +19,10 @@
|
|||
<div> </div>
|
||||
</div>
|
||||
|
||||
[](https://mmdeploy.readthedocs.io/zh_CN/latest/)
|
||||
[](https://mmdeploy.readthedocs.io/zh_CN/1.x/)
|
||||
[](https://github.com/open-mmlab/mmdeploy/actions)
|
||||
[](https://codecov.io/gh/open-mmlab/mmdeploy)
|
||||
[](https://github.com/open-mmlab/mmdeploy/blob/master/LICENSE)
|
||||
[](https://codecov.io/gh/open-mmlab/mmdeploy)
|
||||
[](https://github.com/open-mmlab/mmdeploy/tree/1.x/LICENSE)
|
||||
[](https://github.com/open-mmlab/mmdeploy/issues)
|
||||
[](https://github.com/open-mmlab/mmdeploy/issues)
|
||||
|
||||
|
|
@ -75,7 +75,7 @@ MMDeploy 是 [OpenMMLab](https://openmmlab.com/) 模型部署工具箱，**为
|
|||
- Net 推理
|
||||
- Module 后处理
|
||||
|
||||
## [中文文档](https://mmdeploy.readthedocs.io/zh_CN/latest/)
|
||||
## [中文文档](https://mmdeploy.readthedocs.io/zh_CN/1.x/)
|
||||
|
||||
- [快速上手](docs/zh_cn/get_started.md)
|
||||
- [编译](docs/zh_cn/01-how-to-build/build_from_source.md)
|
||||
|
|
@ -119,7 +119,7 @@ MMDeploy 是 [OpenMMLab](https://openmmlab.com/) 模型部署工具箱，**为
|
|||
|
||||
## 基准与模型库
|
||||
|
||||
基准和支持的模型列表可以在[基准](https://mmdeploy.readthedocs.io/zh_CN/latest/benchmark.html)和[模型列表](https://mmdeploy.readthedocs.io/en/latest/supported_models.html)中获得。
|
||||
基准和支持的模型列表可以在[基准](https://mmdeploy.readthedocs.io/zh_CN/1.x/03-benchmark/benchmark.html)和[模型列表](https://mmdeploy.readthedocs.io/en/1.x/03-benchmark/supported_models.html)中获得。
|
||||
|
||||
## 贡献指南
|
||||
|
||||
|
|
|
|||
|
|
@ -6,7 +6,7 @@
|
|||
"id": "mAWHDEbr6Q2i"
|
||||
},
|
||||
"source": [
|
||||
"[](https://colab.research.google.com/github/open-mmlab/mmdeploy/blob/master/demo/tutorials_1.ipynb)\n",
|
||||
"[](https://colab.research.google.com/github/open-mmlab/mmdeploy/tree/1.x/demo/tutorials_1.ipynb)\n",
|
||||
"# 前言\n",
|
||||
"OpenMMLab 的算法如何部署？是很多社区用户的困惑。而模型部署工具箱 [MMDeploy](https://zhuanlan.zhihu.com/p/450342651) 的开源，强势打通了从算法模型到应用程序这 \"最后一公里\"！\n",
|
||||
"今天我们将开启模型部署入门系列教程，在模型部署开源库 MMDeploy 的辅助下，介绍以下内容：\n",
|
||||
|
|
|
|||
|
|
@ -85,9 +85,9 @@ ENV PATH="/root/workspace/ncnn/build/tools/quantize/:${PATH}"
|
|||
### install mmdeploy
|
||||
WORKDIR /root/workspace
|
||||
ARG VERSION
|
||||
RUN git clone -b dev-1.x https://github.com/open-mmlab/mmdeploy.git &&\
|
||||
RUN git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git &&\
|
||||
cd mmdeploy &&\
|
||||
if [ -z ${VERSION} ] ; then echo "No MMDeploy version passed in, building on dev-1.x" ; else git checkout tags/v${VERSION} -b tag_v${VERSION} ; fi &&\
|
||||
if [ -z ${VERSION} ] ; then echo "No MMDeploy version passed in, building on 1.x" ; else git checkout tags/v${VERSION} -b tag_v${VERSION} ; fi &&\
|
||||
git submodule update --init --recursive &&\
|
||||
rm -rf build &&\
|
||||
mkdir build &&\
|
||||
|
|
|
|||
|
|
@ -65,9 +65,9 @@ RUN cp -r /usr/local/lib/python${PYTHON_VERSION}/dist-packages/tensorrt* /opt/co
|
|||
ENV ONNXRUNTIME_DIR=/root/workspace/onnxruntime-linux-x64-${ONNXRUNTIME_VERSION}
|
||||
ENV TENSORRT_DIR=/workspace/tensorrt
|
||||
ARG VERSION
|
||||
RUN git clone -b dev-1.x https://github.com/open-mmlab/mmdeploy &&\
|
||||
RUN git clone -b 1.x https://github.com/open-mmlab/mmdeploy &&\
|
||||
cd mmdeploy &&\
|
||||
if [ -z ${VERSION} ] ; then echo "No MMDeploy version passed in, building on dev-1.x" ; else git checkout tags/v${VERSION} -b tag_v${VERSION} ; fi &&\
|
||||
if [ -z ${VERSION} ] ; then echo "No MMDeploy version passed in, building on 1.x" ; else git checkout tags/v${VERSION} -b tag_v${VERSION} ; fi &&\
|
||||
git submodule update --init --recursive &&\
|
||||
mkdir -p build &&\
|
||||
cd build &&\
|
||||
|
|
|
|||
|
|
@ -97,7 +97,7 @@ make -j$(nproc) install
|
|||
<tr>
|
||||
<td>OpenJDK </td>
|
||||
<td>It is necessary for building Java API.</br>
|
||||
See <a href='https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/csrc/mmdeploy/apis/java/README.md'> Java API build </a> for building tutorials.
|
||||
See <a href='https://github.com/open-mmlab/mmdeploy/tree/1.x/csrc/mmdeploy/apis/java/README.md'> Java API build </a> for building tutorials.
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
|
|||
|
|
@ -26,7 +26,7 @@ Note:
|
|||
- If it fails when `git clone` via `SSH`, you can try the `HTTPS` protocol like this:
|
||||
|
||||
```shell
|
||||
git clone -b dev-1.x https://github.com/open-mmlab/mmdeploy.git --recursive
|
||||
git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git --recursive
|
||||
```
|
||||
|
||||
## Build
|
||||
|
|
|
|||
|
|
@ -223,7 +223,7 @@ It takes about 15 minutes to install ppl.cv on a Jetson Nano. So, please be pati
|
|||
## Install MMDeploy
|
||||
|
||||
```shell
|
||||
git clone -b dev-1.x --recursive https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone -b 1.x --recursive https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
export MMDEPLOY_DIR=$(pwd)
|
||||
```
|
||||
|
|
@ -289,9 +289,9 @@ pip install -r requirements/build.txt
|
|||
pip install -v -e . # or "python setup.py develop"
|
||||
```
|
||||
|
||||
1. Follow [this document](../02-how-to-run/convert_model.md) on how to convert model files.
|
||||
2. Follow [this document](../02-how-to-run/convert_model.md) on how to convert model files.
|
||||
|
||||
For this example, we have used [retinanet_r18_fpn_1x_coco.py](https://github.com/open-mmlab/mmdetection/blob/3.x/configs/retinanet/retinanet_r18_fpn_1x_coco.py) as the model config, and [this file](https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r18_fpn_1x_coco/retinanet_r18_fpn_1x_coco_20220407_171055-614fd399.pth) as the corresponding checkpoint file. Also for deploy config, we have used [detection_tensorrt_dynamic-320x320-1344x1344.py](https://github.com/open-mmlab/mmdeploy/blob/master/configs/mmdet/detection/detection_tensorrt_dynamic-320x320-1344x1344.py)
|
||||
For this example, we have used [retinanet_r18_fpn_1x_coco.py](https://github.com/open-mmlab/mmdetection/blob/3.x/configs/retinanet/retinanet_r18_fpn_1x_coco.py) as the model config, and [this file](https://download.openmmlab.com/mmdetection/v2.0/retinanet/retinanet_r18_fpn_1x_coco/retinanet_r18_fpn_1x_coco_20220407_171055-614fd399.pth) as the corresponding checkpoint file. Also for deploy config, we have used [detection_tensorrt_dynamic-320x320-1344x1344.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmdet/detection/detection_tensorrt_dynamic-320x320-1344x1344.py)
|
||||
|
||||
```shell
|
||||
python ./tools/deploy.py \
|
||||
|
|
|
|||
|
|
@ -158,7 +158,7 @@ label: 65, score: 0.95
|
|||
|
||||
- MMDet models.
|
||||
|
||||
YOLOV3 & YOLOX: you may paste the following partition configuration into [detection_rknn_static-320x320.py](https://github.com/open-mmlab/mmdeploy/blob/master/configs/mmdet/detection/detection_rknn_static-320x320.py):
|
||||
YOLOV3 & YOLOX: you may paste the following partition configuration into [detection_rknn_static-320x320.py](https://github.com/open-mmlab/mmdeploy/blob/1.x/configs/mmdet/detection/detection_rknn_static-320x320.py):
|
||||
|
||||
```python
|
||||
# yolov3, yolox
|
||||
|
|
@ -173,7 +173,7 @@ label: 65, score: 0.95
|
|||
])
|
||||
```
|
||||
|
||||
RetinaNet & SSD & FSAF with rknn-toolkit2, you may paste the following partition configuration into [detection_rknn_static-320x320.py](https://github.com/open-mmlab/mmdeploy/blob/master/configs/mmdet/detection/detection_rknn_static-320x320.py). Users with rknn-toolkit can directly use default config.
|
||||
RetinaNet & SSD & FSAF with rknn-toolkit2, you may paste the following partition configuration into [detection_rknn_static-320x320.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmdet/detection/detection_rknn_static-320x320.py). Users with rknn-toolkit can directly use default config.
|
||||
|
||||
```python
|
||||
# retinanet, ssd
|
||||
|
|
|
|||
|
|
@ -47,7 +47,7 @@ In order to use the prebuilt package, you need to install some third-party depen
|
|||
2. Clone the mmdeploy repository
|
||||
|
||||
```bash
|
||||
git clone -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
```
|
||||
|
||||
:point_right: The main purpose here is to use the configs, so there is no need to compile `mmdeploy`.
|
||||
|
|
|
|||
|
|
@ -61,8 +61,8 @@ The table below lists the models that are guaranteed to be exportable to other b
|
|||
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segmenter) [\*static](#note) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
|
||||
| [SRCNN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srcnn) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/esrgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [Real-ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/real_esrgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [EDSR](https://github.com/open-mmlab/mmediting/tree/1.x/configs/edsr) | MMEditing | Y | Y | Y | Y | N | Y | N | N |
|
||||
| [RDN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/rdn) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ If your target platform is **Ubuntu 18.04 or later version**, we encourage you t
|
|||
[scripts](../01-how-to-build/build_from_script.md). For example, the following commands install mmdeploy as well as inference engine - `ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -50,9 +50,9 @@ If neither **I** nor **II** meets your requirements, [building mmdeploy from sou
|
|||
|
||||
## Convert model
|
||||
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) to convert mmaction2 models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmaction2 models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
When using `tools/deploy.py`, it is crucial to specify the correct deployment config. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmaction) of all supported backends for mmaction2, under which the config file path follows the pattern:
|
||||
When using `tools/deploy.py`, it is crucial to specify the correct deployment config. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmaction) of all supported backends for mmaction2, under which the config file path follows the pattern:
|
||||
|
||||
```
|
||||
{task}/{task}_{backend}-{precision}_{static | dynamic}_{shape}.py
|
||||
|
|
@ -178,7 +178,7 @@ for label_id, score in result:
|
|||
print(label_id, score)
|
||||
```
|
||||
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo).
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
|
||||
|
||||
> MMAction2 only API of c, c++ and python for now.
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ There are several methods to install mmdeploy, among which you can choose an app
|
|||
|
||||
**Method I:** Install precompiled package
|
||||
|
||||
> **TODO**. MMDeploy hasn't released based on dev-1.x branch.
|
||||
> **TODO**. MMDeploy hasn't released based on 1.x branch.
|
||||
|
||||
**Method II:** Build using scripts
|
||||
|
||||
|
|
@ -35,7 +35,7 @@ If your target platform is **Ubuntu 18.04 or later version**, we encourage you t
|
|||
[scripts](../01-how-to-build/build_from_script.md). For example, the following commands install mmdeploy as well as inference engine - `ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -48,7 +48,7 @@ If neither **I** nor **II** meets your requirements, [building mmdeploy from sou
|
|||
|
||||
## Convert model
|
||||
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) to convert mmcls models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmcls models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
The command below shows an example about converting `resnet18` model to onnx model that can be inferred by ONNX Runtime.
|
||||
|
||||
|
|
@ -70,7 +70,7 @@ python tools/deploy.py \
|
|||
--dump-info
|
||||
```
|
||||
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmcls) of all supported backends for mmclassification. The config filename pattern is:
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmcls) of all supported backends for mmclassification. The config filename pattern is:
|
||||
|
||||
```
|
||||
classification_{backend}-{precision}_{static | dynamic}_{shape}.py
|
||||
|
|
@ -81,7 +81,7 @@ classification_{backend}-{precision}_{static | dynamic}_{shape}.py
|
|||
- **{static | dynamic}:** static shape or dynamic shape
|
||||
- **{shape}:** input shape or shape range of a model
|
||||
|
||||
Therefore, in the above example, you can also convert `resnet18` to other backend models by changing the deployment config file `classification_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmcls), e.g., converting to tensorrt-fp16 model by `classification_tensorrt-fp16_dynamic-224x224-224x224.py`.
|
||||
Therefore, in the above example, you can also convert `resnet18` to other backend models by changing the deployment config file `classification_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmcls), e.g., converting to tensorrt-fp16 model by `classification_tensorrt-fp16_dynamic-224x224-224x224.py`.
|
||||
|
||||
```{tip}
|
||||
When converting mmcls models to tensorrt models, --device should be set to "cuda"
|
||||
|
|
@ -168,7 +168,7 @@ for label_id, score in result:
|
|||
print(label_id, score)
|
||||
```
|
||||
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo).
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
|
||||
|
||||
## Supported models
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ There are several methods to install mmdeploy, among which you can choose an app
|
|||
|
||||
**Method I:** Install precompiled package
|
||||
|
||||
> **TODO**. MMDeploy hasn't released based on dev-1.x branch.
|
||||
> **TODO**. MMDeploy hasn't released based on 1.x branch.
|
||||
|
||||
**Method II:** Build using scripts
|
||||
|
||||
|
|
@ -35,7 +35,7 @@ If your target platform is **Ubuntu 18.04 or later version**, we encourage you t
|
|||
[scripts](../01-how-to-build/build_from_script.md). For example, the following commands install mmdeploy as well as inference engine - `ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -48,7 +48,7 @@ If neither **I** nor **II** meets your requirements, [building mmdeploy from sou
|
|||
|
||||
## Convert model
|
||||
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) to convert mmdet models to the specified backend models. Its detailed usage can be learned from [here](../02-how-to-run/convert_model.md).
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmdet models to the specified backend models. Its detailed usage can be learned from [here](../02-how-to-run/convert_model.md).
|
||||
|
||||
The command below shows an example about converting `Faster R-CNN` model to onnx model that can be inferred by ONNX Runtime.
|
||||
|
||||
|
|
@ -68,7 +68,7 @@ python tools/deploy.py \
|
|||
--dump-info
|
||||
```
|
||||
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmdet) of all supported backends for mmdetection, under which the config file path follows the pattern:
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmdet) of all supported backends for mmdetection, under which the config file path follows the pattern:
|
||||
|
||||
```
|
||||
{task}/{task}_{backend}-{precision}_{static | dynamic}_{shape}.py
|
||||
|
|
@ -90,7 +90,7 @@ It is crucial to specify the correct deployment config during model conversion.
|
|||
|
||||
- **{shape}:** input shape or shape range of a model
|
||||
|
||||
Therefore, in the above example, you can also convert `faster r-cnn` to other backend models by changing the deployment config file `detection_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmdet/detection), e.g., converting to tensorrt-fp16 model by `detection_tensorrt-fp16_dynamic-320x320-1344x1344.py`.
|
||||
Therefore, in the above example, you can also convert `faster r-cnn` to other backend models by changing the deployment config file `detection_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmdet/detection), e.g., converting to tensorrt-fp16 model by `detection_tensorrt-fp16_dynamic-320x320-1344x1344.py`.
|
||||
|
||||
```{tip}
|
||||
When converting mmdet models to tensorrt models, --device should be set to "cuda"
|
||||
|
|
@ -185,7 +185,7 @@ for index, bbox, label_id in zip(indices, bboxes, labels):
|
|||
cv2.imwrite('output_detection.png', img)
|
||||
```
|
||||
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo).
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
|
||||
|
||||
## Supported models
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ There are several methods to install mmdeploy, among which you can choose an app
|
|||
|
||||
**Method I:** Install precompiled package
|
||||
|
||||
> **TODO**. MMDeploy hasn't released based on dev-1.x branch.
|
||||
> **TODO**. MMDeploy hasn't released based on 1.x branch.
|
||||
|
||||
**Method II:** Build using scripts
|
||||
|
||||
|
|
@ -35,7 +35,7 @@ If your target platform is **Ubuntu 18.04 or later version**, we encourage you t
|
|||
[scripts](../01-how-to-build/build_from_script.md). For example, the following commands install mmdeploy as well as inference engine - `ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -48,9 +48,9 @@ If neither **I** nor **II** meets your requirements, [building mmdeploy from sou
|
|||
|
||||
## Convert model
|
||||
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) to convert mmedit models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmedit models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
When using `tools/deploy.py`, it is crucial to specify the correct deployment config. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmedit) of all supported backends for mmedit, under which the config file path follows the pattern:
|
||||
When using `tools/deploy.py`, it is crucial to specify the correct deployment config. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmedit) of all supported backends for mmedit, under which the config file path follows the pattern:
|
||||
|
||||
```
|
||||
{task}/{task}_{backend}-{precision}_{static | dynamic}_{shape}.py
|
||||
|
|
@ -90,7 +90,7 @@ python tools/deploy.py \
|
|||
--dump-info
|
||||
```
|
||||
|
||||
You can also convert the above model to other backend models by changing the deployment config file `*_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmedit), e.g., converting to tensorrt model by `super-resolution/super-resolution_tensorrt-_dynamic-32x32-512x512.py`.
|
||||
You can also convert the above model to other backend models by changing the deployment config file `*_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmedit), e.g., converting to tensorrt model by `super-resolution/super-resolution_tensorrt-_dynamic-32x32-512x512.py`.
|
||||
|
||||
```{tip}
|
||||
When converting mmedit models to tensorrt models, --device should be set to "cuda"
|
||||
|
|
@ -179,7 +179,7 @@ result = result[..., ::-1]
|
|||
cv2.imwrite('output_restorer.bmp', result)
|
||||
```
|
||||
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo).
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
|
||||
|
||||
## Supported models
|
||||
|
||||
|
|
@ -188,8 +188,8 @@ Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Inter
|
|||
| [SRCNN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srcnn) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/esrgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [ESRGAN-PSNR](https://github.com/open-mmlab/mmediting/tree/1.x/configs/esrgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [Real-ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/real_esrgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [EDSR](https://github.com/open-mmlab/mmediting/tree/1.x/configs/edsr) | super-resolution | Y | Y | Y | N | Y |
|
||||
| [RDN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/rdn) | super-resolution | Y | Y | Y | Y | Y |
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ There are several methods to install mmdeploy, among which you can choose an app
|
|||
|
||||
**Method I:** Install precompiled package
|
||||
|
||||
> **TODO**. MMDeploy hasn't released based on dev-1.x branch.
|
||||
> **TODO**. MMDeploy hasn't released based on 1.x branch.
|
||||
|
||||
**Method II:** Build using scripts
|
||||
|
||||
|
|
@ -36,7 +36,7 @@ If your target platform is **Ubuntu 18.04 or later version**, we encourage you t
|
|||
[scripts](../01-how-to-build/build_from_script.md). For example, the following commands install mmdeploy as well as inference engine - `ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -49,9 +49,9 @@ If neither **I** nor **II** meets your requirements, [building mmdeploy from sou
|
|||
|
||||
## Convert model
|
||||
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) to convert mmocr models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmocr models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
When using `tools/deploy.py`, it is crucial to specify the correct deployment config. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmocr) of all supported backends for mmocr, under which the config file path follows the pattern:
|
||||
When using `tools/deploy.py`, it is crucial to specify the correct deployment config. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmocr) of all supported backends for mmocr, under which the config file path follows the pattern:
|
||||
|
||||
```
|
||||
{task}/{task}_{backend}-{precision}_{static | dynamic}_{shape}.py
|
||||
|
|
@ -109,7 +109,7 @@ python tools/deploy.py \
|
|||
--dump-info
|
||||
```
|
||||
|
||||
You can also convert the above models to other backend models by changing the deployment config file `*_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmocr), e.g., converting `dbnet` to tensorrt-fp32 model by `text-detection/text-detection_tensorrt-_dynamic-320x320-2240x2240.py`.
|
||||
You can also convert the above models to other backend models by changing the deployment config file `*_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmocr), e.g., converting `dbnet` to tensorrt-fp32 model by `text-detection/text-detection_tensorrt-_dynamic-320x320-2240x2240.py`.
|
||||
|
||||
```{tip}
|
||||
When converting mmocr models to tensorrt models, --device should be set to "cuda"
|
||||
|
|
@ -226,7 +226,7 @@ texts = recognizer(img)
|
|||
print(texts)
|
||||
```
|
||||
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo).
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
|
||||
|
||||
## Supported models
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ There are several methods to install mmdeploy, among which you can choose an app
|
|||
|
||||
**Method I:** Install precompiled package
|
||||
|
||||
> **TODO**. MMDeploy hasn't released based on dev-1.x branch.
|
||||
> **TODO**. MMDeploy hasn't released based on 1.x branch.
|
||||
|
||||
**Method II:** Build using scripts
|
||||
|
||||
|
|
@ -35,7 +35,7 @@ If your target platform is **Ubuntu 18.04 or later version**, we encourage you t
|
|||
[scripts](../01-how-to-build/build_from_script.md). For example, the following commands install mmdeploy as well as inference engine - `ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -48,7 +48,7 @@ If neither **I** nor **II** meets your requirements, [building mmdeploy from sou
|
|||
|
||||
## Convert model
|
||||
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) to convert mmpose models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmpose models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
The command below shows an example about converting `hrnet` model to onnx model that can be inferred by ONNX Runtime.
|
||||
|
||||
|
|
@ -67,7 +67,7 @@ python tools/deploy.py \
|
|||
--show
|
||||
```
|
||||
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmpose) of all supported backends for mmpose. The config filename pattern is:
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmpose) of all supported backends for mmpose. The config filename pattern is:
|
||||
|
||||
```
|
||||
pose-detection_{backend}-{precision}_{static | dynamic}_{shape}.py
|
||||
|
|
@ -78,7 +78,7 @@ pose-detection_{backend}-{precision}_{static | dynamic}_{shape}.py
|
|||
- **{static | dynamic}:** static shape or dynamic shape
|
||||
- **{shape}:** input shape or shape range of a model
|
||||
|
||||
Therefore, in the above example, you can also convert `hrnet` to other backend models by changing the deployment config file `pose-detection_onnxruntime_static.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmpose), e.g., converting to tensorrt model by `pose-detection_tensorrt_static-256x192.py`.
|
||||
Therefore, in the above example, you can also convert `hrnet` to other backend models by changing the deployment config file `pose-detection_onnxruntime_static.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmpose), e.g., converting to tensorrt model by `pose-detection_tensorrt_static-256x192.py`.
|
||||
|
||||
```{tip}
|
||||
When converting mmpose models to tensorrt models, --device should be set to "cuda"
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ There are several methods to install mmdeploy, among which you can choose an app
|
|||
|
||||
**Method I:** Install precompiled package
|
||||
|
||||
> **TODO**. MMDeploy hasn't released based on dev-1.x branch.
|
||||
> **TODO**. MMDeploy hasn't released based on 1.x branch.
|
||||
|
||||
**Method II:** Build using scripts
|
||||
|
||||
|
|
@ -36,7 +36,7 @@ If your target platform is **Ubuntu 18.04 or later version**, we encourage you t
|
|||
[scripts](../01-how-to-build/build_from_script.md). For example, the following commands install mmdeploy as well as inference engine - `ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -54,7 +54,7 @@ If neither **I** nor **II** meets your requirements, [building mmdeploy from sou
|
|||
|
||||
## Convert model
|
||||
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) to convert mmseg models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) to convert mmseg models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
The command below shows an example about converting `unet` model to onnx model that can be inferred by ONNX Runtime.
|
||||
|
||||
|
|
@ -76,7 +76,7 @@ python tools/deploy.py \
|
|||
--dump-info
|
||||
```
|
||||
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmseg) of all supported backends for mmsegmentation. The config filename pattern is:
|
||||
It is crucial to specify the correct deployment config during model conversion. We've already provided builtin deployment config [files](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmseg) of all supported backends for mmsegmentation. The config filename pattern is:
|
||||
|
||||
```
|
||||
segmentation_{backend}-{precision}_{static | dynamic}_{shape}.py
|
||||
|
|
@ -87,7 +87,7 @@ segmentation_{backend}-{precision}_{static | dynamic}_{shape}.py
|
|||
- **{static | dynamic}:** static shape or dynamic shape
|
||||
- **{shape}:** input shape or shape range of a model
|
||||
|
||||
Therefore, in the above example, you can also convert `unet` to other backend models by changing the deployment config file `segmentation_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmseg), e.g., converting to tensorrt-fp16 model by `segmentation_tensorrt-fp16_dynamic-512x1024-2048x2048.py`.
|
||||
Therefore, in the above example, you can also convert `unet` to other backend models by changing the deployment config file `segmentation_onnxruntime_dynamic.py` to [others](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmseg), e.g., converting to tensorrt-fp16 model by `segmentation_tensorrt-fp16_dynamic-512x1024-2048x2048.py`.
|
||||
|
||||
```{tip}
|
||||
When converting mmseg models to tensorrt models, --device should be set to "cuda"
|
||||
|
|
@ -184,7 +184,7 @@ img = img.astype(np.uint8)
|
|||
cv2.imwrite('output_segmentation.png', img)
|
||||
```
|
||||
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo).
|
||||
Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Interface), such as C, C++, C#, Java and so on. You can learn their usage from [demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo).
|
||||
|
||||
## Supported models
|
||||
|
||||
|
|
|
|||
|
|
@ -63,4 +63,4 @@ Take custom operator `roi_align` for example.
|
|||
## References
|
||||
|
||||
- [How to export Pytorch model with custom op to ONNX and run it in ONNX Runtime](https://github.com/onnx/tutorials/blob/master/PyTorchCustomOperator/README.md)
|
||||
- [How to add a custom operator/kernel in ONNX Runtime](https://github.com/microsoft/onnxruntime/blob/master/docs/AddingCustomOp.md)
|
||||
- [How to add a custom operator/kernel in ONNX Runtime](https://onnxruntime.ai/docs/reference/operators/add-custom-op.html)
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ pip install openvino-dev
|
|||
|
||||
3. Install MMDeploy following the [instructions](../01-how-to-build/build_from_source.md).
|
||||
|
||||
To work with models from [MMDetection](https://github.com/open-mmlab/mmdetection/blob/master/docs/get_started.md), you may need to install it additionally.
|
||||
To work with models from [MMDetection](https://mmdetection.readthedocs.io/en/3.x/get_started.html), you may need to install it additionally.
|
||||
|
||||
## Usage
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
Currently, MMDeploy only tests rk3588 and rv1126 with linux platform.
|
||||
|
||||
The following features cannot be automatically enabled by mmdeploy and you need to manually modify the configuration in MMDeploy like [here](https://github.com/open-mmlab/mmdeploy/blob/master/configs/_base_/backends/rknn.py).
|
||||
The following features cannot be automatically enabled by mmdeploy and you need to manually modify the configuration in MMDeploy like [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/_base_/backends/rknn.py).
|
||||
|
||||
- target_platform other than default
|
||||
- quantization settings
|
||||
|
|
|
|||
|
|
@ -105,7 +105,7 @@ html_theme_path = [pytorch_sphinx_theme.get_html_theme_path()]
|
|||
# documentation.
|
||||
#
|
||||
html_theme_options = {
|
||||
'logo_url': 'https://mmdeploy.readthedocs.io/en/latest/',
|
||||
'logo_url': 'https://mmdeploy.readthedocs.io/en/1.x/',
|
||||
'menu': [{
|
||||
'name': 'GitHub',
|
||||
'url': 'https://github.com/open-mmlab/mmdeploy'
|
||||
|
|
|
|||
|
|
@ -269,7 +269,7 @@ for index, bbox, label_id in zip(indices, bboxes, labels):
|
|||
cv2.imwrite('output_detection.png', img)
|
||||
```
|
||||
|
||||
You can find more examples from [here](https://github.com/open-mmlab/mmdeploy/tree/master/demo/python).
|
||||
You can find more examples from [here](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/python).
|
||||
|
||||
#### C++ API
|
||||
|
||||
|
|
@ -321,9 +321,9 @@ find_package(MMDeploy REQUIRED)
|
|||
target_link_libraries(${name} PRIVATE mmdeploy ${OpenCV_LIBS})
|
||||
```
|
||||
|
||||
For more SDK C++ API usages, please read these [samples](https://github.com/open-mmlab/mmdeploy/tree/master/demo/csrc/cpp).
|
||||
For more SDK C++ API usages, please read these [samples](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/csrc/cpp).
|
||||
|
||||
For the rest C, C# and Java API usages, please read [C demos](https://github.com/open-mmlab/mmdeploy/tree/master/demo/csrc/c), [C# demos](https://github.com/open-mmlab/mmdeploy/tree/master/demo/csharp) and [Java demos](https://github.com/open-mmlab/mmdeploy/tree/master/demo/java) respectively.
|
||||
For the rest C, C# and Java API usages, please read [C demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/csrc/c), [C# demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/csharp) and [Java demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/java) respectively.
|
||||
We'll talk about them more in our next release.
|
||||
|
||||
#### Accelerate preprocessing（Experimental）
|
||||
|
|
|
|||
|
|
@ -1,3 +1,3 @@
|
|||
## <a href='https://mmdeploy.readthedocs.io/en/latest/'>English</a>
|
||||
## <a href='https://mmdeploy.readthedocs.io/en/1.x/'>English</a>
|
||||
|
||||
## <a href='https://mmdeploy.readthedocs.io/zh_CN/latest/'>简体中文</a>
|
||||
## <a href='https://mmdeploy.readthedocs.io/zh_CN/1.x/'>简体中文</a>
|
||||
|
|
|
|||
|
|
@ -98,7 +98,7 @@ make -j$(nproc) install
|
|||
<tr>
|
||||
<td>OpenJDK </td>
|
||||
<td>编译Java API之前需要先准备OpenJDK开发环境</br>
|
||||
请参考 <a href='https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/csrc/mmdeploy/apis/java/README.md'> Java API 编译 </a> 进行构建.
|
||||
请参考 <a href='https://github.com/open-mmlab/mmdeploy/tree/1.x/csrc/mmdeploy/apis/java/README.md'> Java API 编译 </a> 进行构建.
|
||||
</td>
|
||||
</tr>
|
||||
</tbody>
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ git clone -b master git@github.com:open-mmlab/mmdeploy.git --recursive
|
|||
- 如果以 `SSH` 方式 `git clone` 代码失败，您可以尝试使用 `HTTPS` 协议下载代码：
|
||||
|
||||
```bash
|
||||
git clone -b dev-1.x https://github.com/open-mmlab/mmdeploy.git MMDeploy
|
||||
git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git MMDeploy
|
||||
cd MMDeploy
|
||||
git submodule update --init --recursive
|
||||
```
|
||||
|
|
|
|||
|
|
@ -199,7 +199,7 @@ conda activate mmdeploy
|
|||
## 安装 MMDeploy
|
||||
|
||||
```shell
|
||||
git clone -b dev-1.x --recursive https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone -b 1.x --recursive https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
export MMDEPLOY_DIR=$(pwd)
|
||||
```
|
||||
|
|
|
|||
|
|
@ -102,7 +102,7 @@ python tools/deploy.py \
|
|||
|
||||
- YOLOV3 & YOLOX
|
||||
|
||||
将下面的模型拆分配置写入到 [detection_rknn_static.py](https://github.com/open-mmlab/mmdeploy/blob/master/configs/mmdet/detection/detection_rknn_static.py)
|
||||
将下面的模型拆分配置写入到 [detection_rknn_static.py](https://github.com/open-mmlab/mmdeploy/blob/1.x/configs/mmdet/detection/detection_rknn_static-320x320.py)
|
||||
|
||||
```python
|
||||
# yolov3, yolox
|
||||
|
|
@ -132,7 +132,7 @@ python tools/deploy.py \
|
|||
|
||||
- RetinaNet & SSD & FSAF with rknn-toolkit2
|
||||
|
||||
将下面的模型拆分配置写入到 [detection_rknn_static.py](https://github.com/open-mmlab/mmdeploy/blob/master/configs/mmdet/detection/detection_rknn_static.py)。使用 rknn-toolkit 的用户则不用。
|
||||
将下面的模型拆分配置写入到 [detection_rknn_static.py](https://github.com/open-mmlab/mmdeploy/blob/1.x/configs/mmdet/detection/detection_rknn_static-320x320.py)。使用 rknn-toolkit 的用户则不用。
|
||||
|
||||
```python
|
||||
# retinanet, ssd
|
||||
|
|
|
|||
|
|
@ -55,7 +55,7 @@ ______________________________________________________________________
|
|||
2. 克隆mmdeploy仓库
|
||||
|
||||
```bash
|
||||
git clone -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
```
|
||||
|
||||
:point_right: 这里主要为了使用configs文件，所以没有加`--recursive`来下载submodule，也不需要编译`mmdeploy`
|
||||
|
|
|
|||
|
|
@ -61,8 +61,8 @@
|
|||
| [Segmenter](https://github.com/open-mmlab/mmsegmentation/tree/1.x/configs/segmenter) [\*static](#note) | MMSegmentation | Y | Y | Y | Y | N | Y | N | N |
|
||||
| [SRCNN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srcnn) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/esrgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [Real-ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/real_esrgan) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
| [EDSR](https://github.com/open-mmlab/mmediting/tree/1.x/configs/edsr) | MMEditing | Y | Y | Y | Y | N | Y | N | N |
|
||||
| [RDN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/rdn) | MMEditing | Y | Y | Y | Y | Y | Y | N | N |
|
||||
|
|
|
|||
|
|
@ -37,7 +37,7 @@ mmdeploy 有以下几种安装方式:
|
|||
比如，以下命令可以安装 mmdeploy 以及配套的推理引擎——`ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -50,10 +50,10 @@ export LD_LIBRARY_PATH=$(pwd)/../mmdeploy-dep/onnxruntime-linux-x64-1.8.1/lib/:$
|
|||
|
||||
## 模型转换
|
||||
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) 把 mmaction2 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) 把 mmaction2 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmaction)。
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmaction)。
|
||||
文件的命名模式是：
|
||||
|
||||
```
|
||||
|
|
@ -181,7 +181,7 @@ for label_id, score in result:
|
|||
```
|
||||
|
||||
除了python API，mmdeploy SDK 还提供了诸如 C、C++、C#、Java等多语言接口。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo)学习其他语言接口的使用方法。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo)学习其他语言接口的使用方法。
|
||||
|
||||
> mmaction2 的 C#，Java接口待开发
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ mmdeploy 有以下几种安装方式:
|
|||
|
||||
**方式一：** 安装预编译包
|
||||
|
||||
> 待 mmdeploy 正式发布 dev-1.x，再补充
|
||||
> 待 mmdeploy 正式发布 1.x，再补充
|
||||
|
||||
**方式二：** 一键式脚本安装
|
||||
|
||||
|
|
@ -35,7 +35,7 @@ mmdeploy 有以下几种安装方式:
|
|||
比如，以下命令可以安装 mmdeploy 以及配套的推理引擎——`ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -48,8 +48,8 @@ export LD_LIBRARY_PATH=$(pwd)/../mmdeploy-dep/onnxruntime-linux-x64-1.8.1/lib/:$
|
|||
|
||||
## 模型转换
|
||||
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) 把 mmcls 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/docs/zh_cn/02-how-to-run/convert_model.md#使用方法).
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) 把 mmcls 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/zh_cn/02-how-to-run/convert_model.md#使用方法).
|
||||
|
||||
以下，我们将演示如何把 `resnet18` 转换为 onnx 模型。
|
||||
|
||||
|
|
@ -71,7 +71,7 @@ python tools/deploy.py \
|
|||
--dump-info
|
||||
```
|
||||
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmcls)。
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmcls)。
|
||||
文件的命名模式是：
|
||||
|
||||
```
|
||||
|
|
@ -173,7 +173,7 @@ for label_id, score in result:
|
|||
```
|
||||
|
||||
除了python API，mmdeploy SDK 还提供了诸如 C、C++、C#、Java等多语言接口。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo)学习其他语言接口的使用方法。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo)学习其他语言接口的使用方法。
|
||||
|
||||
## 模型支持列表
|
||||
|
||||
|
|
|
|||
|
|
@ -49,7 +49,7 @@ export LD_LIBRARY_PATH=$(pwd)/../mmdeploy-dep/onnxruntime-linux-x64-1.8.1/lib/:$
|
|||
## 模型转换
|
||||
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/1.x/tools/deploy.py) 把 mmdet 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
以下，我们将演示如何把 `Faster R-CNN` 转换为 onnx 模型。
|
||||
|
||||
|
|
@ -188,7 +188,7 @@ cv2.imwrite('output_detection.png', img)
|
|||
```
|
||||
|
||||
除了python API，mmdeploy SDK 还提供了诸如 C、C++、C#、Java等多语言接口。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo)学习其他语言接口的使用方法。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo)学习其他语言接口的使用方法。
|
||||
|
||||
## 模型支持列表
|
||||
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ mmdeploy 有以下几种安装方式:
|
|||
|
||||
**方式一：** 安装预编译包
|
||||
|
||||
> 待 mmdeploy 正式发布 dev-1.x，再补充
|
||||
> 待 mmdeploy 正式发布 1.x，再补充
|
||||
|
||||
**方式二：** 一键式脚本安装
|
||||
|
||||
|
|
@ -36,7 +36,7 @@ mmdeploy 有以下几种安装方式:
|
|||
比如，以下命令可以安装 mmdeploy 以及配套的推理引擎——`ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -49,10 +49,10 @@ export LD_LIBRARY_PATH=$(pwd)/../mmdeploy-dep/onnxruntime-linux-x64-1.8.1/lib/:$
|
|||
|
||||
## 模型转换
|
||||
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) 把 mmedit 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/docs/zh_cn/02-how-to-run/convert_model.md#使用方法).
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) 把 mmedit 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/zh_cn/02-how-to-run/convert_model.md#使用方法).
|
||||
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmedit)。
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmedit)。
|
||||
文件的命名模式是：
|
||||
|
||||
```
|
||||
|
|
@ -185,7 +185,7 @@ cv2.imwrite('output_restorer.bmp', result)
|
|||
```
|
||||
|
||||
除了python API，mmdeploy SDK 还提供了诸如 C、C++、C#、Java等多语言接口。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo)学习其他语言接口的使用方法。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo)学习其他语言接口的使用方法。
|
||||
|
||||
## 模型支持列表
|
||||
|
||||
|
|
@ -194,8 +194,8 @@ cv2.imwrite('output_restorer.bmp', result)
|
|||
| [SRCNN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srcnn) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/esrgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [ESRGAN-PSNR](https://github.com/open-mmlab/mmediting/tree/1.x/configs/esrgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srresnet_srgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [SRResNet](https://github.com/open-mmlab/mmediting/tree/1.x/configs/srgan_resnet) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [Real-ESRGAN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/real_esrgan) | super-resolution | Y | Y | Y | Y | Y |
|
||||
| [EDSR](https://github.com/open-mmlab/mmediting/tree/1.x/configs/edsr) | super-resolution | Y | Y | Y | N | Y |
|
||||
| [RDN](https://github.com/open-mmlab/mmediting/tree/1.x/configs/rdn) | super-resolution | Y | Y | Y | Y | Y |
|
||||
|
|
|
|||
|
|
@ -30,7 +30,7 @@ mmdeploy 有以下几种安装方式:
|
|||
|
||||
**方式一：** 安装预编译包
|
||||
|
||||
> 待 mmdeploy 正式发布 dev-1.x，再补充
|
||||
> 待 mmdeploy 正式发布 1.x，再补充
|
||||
|
||||
**方式二：** 一键式脚本安装
|
||||
|
||||
|
|
@ -38,7 +38,7 @@ mmdeploy 有以下几种安装方式:
|
|||
比如，以下命令可以安装 mmdeploy 以及配套的推理引擎——`ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -51,10 +51,10 @@ export LD_LIBRARY_PATH=$(pwd)/../mmdeploy-dep/onnxruntime-linux-x64-1.8.1/lib/:$
|
|||
|
||||
## 模型转换
|
||||
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) 把 mmocr 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) 把 mmocr 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmocr)。
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmocr)。
|
||||
文件的命名模式是：
|
||||
|
||||
```
|
||||
|
|
@ -232,7 +232,7 @@ print(texts)
|
|||
```
|
||||
|
||||
除了python API，mmdeploy SDK 还提供了诸如 C、C++、C#、Java等多语言接口。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo)学习其他语言接口的使用方法。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo)学习其他语言接口的使用方法。
|
||||
|
||||
## 模型支持列表
|
||||
|
||||
|
|
|
|||
|
|
@ -27,7 +27,7 @@ mmdeploy 有以下几种安装方式:
|
|||
|
||||
**方式一：** 安装预编译包
|
||||
|
||||
> 待 mmdeploy 正式发布 dev-1.x，再补充
|
||||
> 待 mmdeploy 正式发布 1.x，再补充
|
||||
|
||||
**方式二：** 一键式脚本安装
|
||||
|
||||
|
|
@ -35,7 +35,7 @@ mmdeploy 有以下几种安装方式:
|
|||
比如，以下命令可以安装 mmdeploy 以及配套的推理引擎——`ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -48,8 +48,8 @@ export LD_LIBRARY_PATH=$(pwd)/../mmdeploy-dep/onnxruntime-linux-x64-1.8.1/lib/:$
|
|||
|
||||
## 模型转换
|
||||
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) 把 mmpose 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) 把 mmpose 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
以下，我们将演示如何把 `hrnet` 转换为 onnx 模型。
|
||||
|
||||
|
|
@ -68,7 +68,7 @@ python tools/deploy.py \
|
|||
--show
|
||||
```
|
||||
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmpose)。
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmpose)。
|
||||
文件的命名模式是：
|
||||
|
||||
```
|
||||
|
|
|
|||
|
|
@ -28,7 +28,7 @@ mmdeploy 有以下几种安装方式:
|
|||
|
||||
**方式一：** 安装预编译包
|
||||
|
||||
> 待 mmdeploy 正式发布 dev-1.x，再补充
|
||||
> 待 mmdeploy 正式发布 1.x，再补充
|
||||
|
||||
**方式二：** 一键式脚本安装
|
||||
|
||||
|
|
@ -36,7 +36,7 @@ mmdeploy 有以下几种安装方式:
|
|||
比如，以下命令可以安装 mmdeploy 以及配套的推理引擎——`ONNX Runtime`.
|
||||
|
||||
```shell
|
||||
git clone --recursive -b dev-1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
git clone --recursive -b 1.x https://github.com/open-mmlab/mmdeploy.git
|
||||
cd mmdeploy
|
||||
python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc)
|
||||
export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH
|
||||
|
|
@ -53,8 +53,8 @@ export LD_LIBRARY_PATH=$(pwd)/../mmdeploy-dep/onnxruntime-linux-x64-1.8.1/lib/:$
|
|||
|
||||
## 模型转换
|
||||
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/tools/deploy.py) 把 mmseg 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/1.x/tools/deploy.py) 把 mmseg 模型一键式转换为推理后端模型。
|
||||
该工具的详细使用说明请参考[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage).
|
||||
|
||||
以下，我们将演示如何把 `unet` 转换为 onnx 模型。
|
||||
|
||||
|
|
@ -76,7 +76,7 @@ python tools/deploy.py \
|
|||
--dump-info
|
||||
```
|
||||
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmseg)。
|
||||
转换的关键之一是使用正确的配置文件。项目中已内置了各后端部署[配置文件](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/mmseg)。
|
||||
文件的命名模式是：
|
||||
|
||||
```
|
||||
|
|
@ -188,7 +188,7 @@ cv2.imwrite('output_segmentation.png', img)
|
|||
```
|
||||
|
||||
除了python API，mmdeploy SDK 还提供了诸如 C、C++、C#、Java等多语言接口。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/demo)学习其他语言接口的使用方法。
|
||||
你可以参考[样例](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo)学习其他语言接口的使用方法。
|
||||
|
||||
## 模型支持列表
|
||||
|
||||
|
|
|
|||
|
|
@ -63,4 +63,4 @@ Take custom operator `roi_align` for example.
|
|||
## References
|
||||
|
||||
- [How to export Pytorch model with custom op to ONNX and run it in ONNX Runtime](https://github.com/onnx/tutorials/blob/master/PyTorchCustomOperator/README.md)
|
||||
- [How to add a custom operator/kernel in ONNX Runtime](https://github.com/microsoft/onnxruntime/blob/master/docs/AddingCustomOp.md)
|
||||
- [How to add a custom operator/kernel in ONNX Runtime](https://onnxruntime.ai/docs/reference/operators/add-custom-op.html)
|
||||
|
|
|
|||
|
|
@ -17,7 +17,7 @@ pip install openvino-dev
|
|||
|
||||
3. Install MMDeploy following the [instructions](../01-how-to-build/build_from_source.md).
|
||||
|
||||
To work with models from [MMDetection](https://github.com/open-mmlab/mmdetection/blob/master/docs/get_started.md), you may need to install it additionally.
|
||||
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.
|
||||
|
||||
## Usage
|
||||
|
||||
|
|
|
|||
|
|
@ -2,7 +2,7 @@
|
|||
|
||||
目前, MMDeploy 只在 rk3588 和 rv1126 的 linux 平台上测试过.
|
||||
|
||||
以下特性需要手动在 MMDeploy 自行配置，如[这里](https://github.com/open-mmlab/mmdeploy/blob/master/configs/_base_/backends/rknn.py).
|
||||
以下特性需要手动在 MMDeploy 自行配置，如[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/configs/_base_/backends/rknn.py).
|
||||
|
||||
- target_platform ！= default
|
||||
- quantization settings
|
||||
|
|
|
|||
|
|
@ -106,7 +106,7 @@ html_theme_path = [pytorch_sphinx_theme.get_html_theme_path()]
|
|||
# documentation.
|
||||
#
|
||||
html_theme_options = {
|
||||
'logo_url': 'https://mmdeploy.readthedocs.io/zh_CN/latest/',
|
||||
'logo_url': 'https://mmdeploy.readthedocs.io/zh_CN/1.x/',
|
||||
'menu': [{
|
||||
'name': 'GitHub',
|
||||
'url': 'https://github.com/open-mmlab/mmdeploy'
|
||||
|
|
|
|||
|
|
@ -268,7 +268,7 @@ for index, bbox, label_id in zip(indices, bboxes, labels):
|
|||
cv2.imwrite('output_detection.png', img)
|
||||
```
|
||||
|
||||
更多示例，请查阅[这里](https://github.com/open-mmlab/mmdeploy/tree/master/demo/python)。
|
||||
更多示例，请查阅[这里](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/python)。
|
||||
|
||||
#### C++ API
|
||||
|
||||
|
|
@ -322,9 +322,9 @@ target_link_libraries(${name} PRIVATE mmdeploy ${OpenCV_LIBS})
|
|||
```
|
||||
|
||||
编译时，使用 -DMMDeploy_DIR，传入MMDeloyConfig.cmake所在的路径。它在预编译包中的sdk/lib/cmake/MMDeloy下。
|
||||
更多示例，请查阅[此处](https://github.com/open-mmlab/mmdeploy/tree/master/demo/csrc/cpp)。
|
||||
更多示例，请查阅[此处](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/csrc/cpp)。
|
||||
|
||||
对于 C API、C# API、Java API 的使用方法，请分别阅读代码[C demos](https://github.com/open-mmlab/mmdeploy/tree/master/demo/csrc/c)， [C# demos](https://github.com/open-mmlab/mmdeploy/tree/master/demo/csharp) 和 [Java demos](https://github.com/open-mmlab/mmdeploy/tree/master/demo/java)。
|
||||
对于 C API、C# API、Java API 的使用方法，请分别阅读代码[C demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/csrc/c)， [C# demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/csharp) 和 [Java demos](https://github.com/open-mmlab/mmdeploy/tree/1.x/demo/java)。
|
||||
我们将在后续版本中详细讲述它们的用法。
|
||||
|
||||
#### 加速预处理（实验性功能）
|
||||
|
|
|
|||
|
|
@ -1,3 +1,3 @@
|
|||
## <a href='https://mmdeploy.readthedocs.io/en/latest/'>English</a>
|
||||
## <a href='https://mmdeploy.readthedocs.io/en/1.x/'>English</a>
|
||||
|
||||
## <a href='https://mmdeploy.readthedocs.io/zh_CN/latest/'>简体中文</a>
|
||||
## <a href='https://mmdeploy.readthedocs.io/zh_CN/1.x/'>简体中文</a>
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
# 第二章：解决模型部署中的难题
|
||||
|
||||
在[第一章](https://mmdeploy.readthedocs.io/zh_CN/latest/tutorials/chapter_01_introduction_to_model_deployment.html)中，我们部署了一个简单的超分辨率模型，一切都十分顺利。但是，上一个模型还有一些缺陷——图片的放大倍数固定是 4，我们无法让图片放大任意的倍数。现在，我们来尝试部署一个支持动态放大倍数的模型，体验一下在模型部署中可能会碰到的困难。
|
||||
在[第一章](https://mmdeploy.readthedocs.io/zh_CN/1.x/tutorial/01_introduction_to_model_deployment.html)中，我们部署了一个简单的超分辨率模型，一切都十分顺利。但是，上一个模型还有一些缺陷——图片的放大倍数固定是 4，我们无法让图片放大任意的倍数。现在，我们来尝试部署一个支持动态放大倍数的模型，体验一下在模型部署中可能会碰到的困难。
|
||||
|
||||
## 模型部署中常见的难题
|
||||
|
||||
|
|
@ -10,7 +10,7 @@
|
|||
- 新算子的实现。深度学习技术日新月异，提出新算子的速度往往快于 ONNX 维护者支持的速度。为了部署最新的模型，部署工程师往往需要自己在 ONNX 和推理引擎中支持新算子。
|
||||
- 中间表示与推理引擎的兼容问题。由于各推理引擎的实现不同，对 ONNX 难以形成统一的支持。为了确保模型在不同的推理引擎中有同样的运行效果，部署工程师往往得为某个推理引擎定制模型代码，这为模型部署引入了许多工作量。
|
||||
|
||||
我们会在后续教程详细讲述解决这些问题的方法。如果对前文中 ONNX、推理引擎、中间表示、算子等名词感觉陌生，不用担心，可以阅读[第一章](https://mmdeploy.readthedocs.io/zh_CN/latest/tutorials/chapter_01_introduction_to_model_deployment.html)，了解有关概念。
|
||||
我们会在后续教程详细讲述解决这些问题的方法。如果对前文中 ONNX、推理引擎、中间表示、算子等名词感觉陌生，不用担心，可以阅读[第一章](https://mmdeploy.readthedocs.io/zh_CN/1.x/tutorial/01_introduction_to_model_deployment.html)，了解有关概念。
|
||||
|
||||
现在，让我们对原来的 SRCNN 模型做一些小的修改，体验一下模型动态化对模型部署造成的困难，并学习解决该问题的一种方法。
|
||||
|
||||
|
|
@ -38,7 +38,7 @@ def init_torch_model():
|
|||
|
||||
现在，假设我们要做一个超分辨率的应用。我们的用户希望图片的放大倍数能够自由设置。而我们交给用户的，只有一个 .onnx 文件和运行超分辨率模型的应用程序。我们在不修改 .onnx 文件的前提下改变放大倍数。
|
||||
|
||||
因此，我们必须修改原来的模型，令模型的放大倍数变成推理时的输入。在[第一章](https://mmdeploy.readthedocs.io/zh_CN/latest/tutorials/chapter_01_introduction_to_model_deployment.html)中的 Python 脚本的基础上，我们做一些修改，得到这样的脚本：
|
||||
因此，我们必须修改原来的模型，令模型的放大倍数变成推理时的输入。在[第一章](https://mmdeploy.readthedocs.io/zh_CN/1.x/tutorial/01_introduction_to_model_deployment.html)中的 Python 脚本的基础上，我们做一些修改，得到这样的脚本：
|
||||
|
||||
```python
|
||||
import torch
|
||||
|
|
@ -75,7 +75,7 @@ def init_torch_model():
|
|||
torch_model = SuperResolutionNet()
|
||||
|
||||
# Please read the code about downloading 'srcnn.pth' and 'face.png' in
|
||||
# https://mmdeploy.readthedocs.io/zh_CN/latest/tutorials/chapter_01_introduction_to_model_deployment.html#pytorch
|
||||
# https://mmdeploy.readthedocs.io/zh_CN/1.x/tutorial/01_introduction_to_model_deployment.html#pytorch
|
||||
state_dict = torch.load('srcnn.pth')['state_dict']
|
||||
|
||||
# Adapt the checkpoint
|
||||
|
|
|
|||
|
|
@ -44,7 +44,7 @@ python -c "import tensorrt;print(tensorrt.__version__)"
|
|||
|
||||
### Jetson
|
||||
|
||||
对于 Jetson 平台，我们有非常详细的安装环境配置教程，可参考 [MMDeploy 安装文档](https://github.com/open-mmlab/mmdeploy/blob/master/docs/zh_cn/01-how-to-build/jetsons.md)。需要注意的是，在 Jetson 上配置的 CUDA 版本 TensorRT 版本与 JetPack 强相关的，我们选择适配硬件的版本即可。配置好环境后，通过 `python -c "import tensorrt;print(tensorrt.__version__)"` 查看TensorRT版本是否正确。
|
||||
对于 Jetson 平台，我们有非常详细的安装环境配置教程，可参考 [MMDeploy 安装文档](https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/zh_cn/01-how-to-build/jetsons.md)。需要注意的是，在 Jetson 上配置的 CUDA 版本 TensorRT 版本与 JetPack 强相关的，我们选择适配硬件的版本即可。配置好环境后，通过 `python -c "import tensorrt;print(tensorrt.__version__)"` 查看TensorRT版本是否正确。
|
||||
|
||||
## 模型构建
|
||||
|
||||
|
|
|
|||
|
|
@ -18,6 +18,6 @@ def optimize_onnx(ctx, graph, params_dict, torch_out):
|
|||
logger.warning(
|
||||
'Can not optimize model, please build torchscipt extension.\n'
|
||||
'More details: '
|
||||
'https://github.com/open-mmlab/mmdeploy/blob/master/docs/en/experimental/onnx_optimizer.md' # noqa
|
||||
'https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/experimental/onnx_optimizer.md' # noqa
|
||||
)
|
||||
return graph, params_dict, torch_out
|
||||
|
|
|
|||
Loading…
Reference in New Issue