mirror of
https://github.com/open-mmlab/mmdeploy.git
synced 2025-01-14 08:09:43 +08:00
* make -install -> make install (#621) change `make -install` to `make install` https://github.com/open-mmlab/mmdeploy/issues/618 * [Fix] fix csharp api detector release result (#620) * fix csharp api detector release result * fix wrong count arg of xxx_release_result in c# api * [Enhancement] Support two-stage rotated detector TensorRT. (#530) * upload * add fake_multiclass_nms_rotated * delete unused code * align with pytorch * Update delta_midpointoffset_rbbox_coder.py * add trt rotated roi align * add index feature in nms * not good * fix index * add ut * add benchmark * move to csrc/mmdeploy * update unit test Co-authored-by: zytx121 <592267829@qq.com> * Reduce mmcls version dependency (#635) * fix shufflenetv2 with trt (#645) * fix shufflenetv2 and pspnet * fix ci * remove print * ' -> " (#654) If there is a variable in the string, single quotes will ignored it, while double quotes will bring the variable into the string after parsing * ' -> " (#655) same with https://github.com/open-mmlab/mmdeploy/pull/654 * Support deployment of Segmenter (#587) * support segmentor with ncnn * update regression yml * replace chunk with split to support ts * update regression yml * update docs * fix segmenter ncnn inference failure brought by #477 * add test * fix test for ncnn and trt * fix lint * export nn.linear to Gemm op in onnx for ncnn * fix ci * simplify `Expand` (#617) * Fix typo (#625) * Add make install in en docs * Add make install in zh docs * Fix typo * Merge and add windows build Co-authored-by: tripleMu <865626@163.com> * [Enhancement] Fix ncnn unittest (#626) * optmize-csp-darknet * replace floordiv to torch.div * update csp_darknet default implement * fix test * [Enhancement] TensorRT Anchor generator plugin (#646) * custom trt anchor generator * add ut * add docstring, update doc * Add partition doc and sample code (#599) * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * update torch2onnx tool to support onnx partition * add model partition of yolov3 * add cn doc * add to index.rst * resolve comment * resolve comments * fix lint * change caption level in docs * update docs (#624) * Add java apis and demos (#563) * add java classifier detector * add segmentor * fix lint * add ImageRestorer java apis and demo * remove useless count parameter for Segmentor and Restorer, add PoseDetector * add RotatedDetection java api and demo * add Ocr java demo and apis * remove mmrotate ncnn java api and demo * fix lint * sync java api folder after rebase to master * fix include * remove record * fix java apis dir path in cmake * add java demo readme * fix lint mdformat * add test javaapi ci * fix lint * fix flake8 * fix test javaapi ci * refactor readme.md * fix install opencv for ci * fix install opencv : add permission * add all codebases and mmcv install * add torch * install mmdeploy * fix image path * fix picture path * fix import ncnn * fix import ncnn * add submodule of pybind * fix pybind submodule * change download to git clone for submodule * fix ncnn dir * fix README error * simplify the github ci * fix ci * fix yapf * add JNI as required * fix Capitalize * fix Capitalize * fix copyright * ignore .class changed * add OpenJDK installation docs * install target of javaapi * simplify ci * add jar * fix ci * fix ci * fix test java command * debugging what failed * debugging what failed * debugging what failed * add java version info * install openjdk * add java env var * fix export * fix export * fix export * fix export * fix picture path * fix picture path * fix file name * fix file name * fix README * remove java_api strategy * fix python version * format task name * move args position * extract common utils code * show image class result * add detector result * segmentation result format * add ImageRestorer result * add PoseDetection java result format * fix ci * stage ocr * add visualize * move utils * fix lint * fix ocr bugs * fix ci demo * fix java classpath for ci * fix popd * fix ocr demo text garbled * fix ci * fix ci * fix ci * fix path of utils ci * update the circleci config file by adding workflows both for linux, windows and linux-gpu (#368) * update circleci by adding more workflows * fix test workflow failure on windows platform * fix docker exec command for SDK unittests * Fixed tensorrt plugin not found in Windows (#672) * update introduction.png (#674) * [Enhancement] Add fuse select assign pass (#589) * Add fuse select assign pass * move code to csrc * add config flag * remove bool cast * fix export sdk info of input shape (#667) * Update get_started.md (#675) Fix backend model assignment * Update get_started.md (#676) Fix backend model assignment * [Fix] fix clang build (#677) * fix clang build * fix ndk build * fix ndk build * switch to `std::filesystem` for clang-7 and later * Deploy the Swin Transformer on TensorRT. (#652) * resolve conflicts * update ut and docs * fix ut * refine docstring * add comments and refine UT * resolve comments * resolve comments * update doc * add roll export * check backend * update regression test * bump version to 0.6.0 (#680) * bump vertion to 0.6.0 * update version * pass img_metas while exporting to onnx (#681) * pass img_metas while exporting to onnx * remove try-catch in tools for beter debugging * use get * fix typo * [Fix] fix ssd ncnn ut (#692) * fix ssd ncnn ut * fix yapf * fix passing img_metas to pytorch2onnx for mmedit (#700) * fix passing img_metas for mmdet3d (#707) * [Fix] Fix android build (#698) * fix android build * fix cmake * fix url link * fix wrong exit code in pipeline_manager (#715) * fix exit * change to general exit errorcode=1 * fix passing wrong backend type (#719) * Rename onnx2ncnn to mmdeploy_onnx2ncnn (#694) * improvement(tools/onnx2ncnn.py): rename to mmdeploy_onnx2ncnn * format(tools/deploy.py): clean code * fix(init_plugins.py): improve if condition * fix(CI): update target * fix(test_onnx2ncnn.py): update desc * Update init_plugins.py * [Fix] Fix mmdet ort static shape bug (#687) * fix shape * add device * fix yapf * fix rewriter for transforms * reverse image shape * fix ut of distance2bbox * fix rewriter name * fix c4 for torchscript (#724) * [Enhancement] Standardize C API (#634) * unify C API naming * fix demo and move apis/c/* -> apis/c/mmdeploy/* * fix lint * fix C# project * fix Java API * [Enhancement] Support Slide Vertex TRT (#650) * reorgnize mmrotate * fix * add hbb2obb * add ut * fix rotated nms * update docs * update benchmark * update test * remove ort regression test, remove comment * Fix get-started rendering issues in readthedocs (#740) * fix mermaid markdown rendering issue in readthedocs * fix error in C++ example * fix error in c++ example in zh_cn get_started doc * [Fix] set default topk for dump info (#702) * set default topk for dump info * remove redundant docstrings * add ci densenet * fix classification warnings * fix mmcls version * fix logger.warnings * add version control (#754) * fix satrn for ORT (#753) * fix satrn for ORT * move rewrite into pytorch * Add inference latency test tool (#665) * add profile tool * remove print envs in profile tool * set cudnn_benchmark to True * add doc * update tests * fix typo * support test with images from a directory * update doc * resolve comments * [Enhancement] Add CSE ONNX pass (#647) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Test robot Just test robot * Update README.md Revert * [Fix] fix yolox point_generator (#758) * fix yolox point_generator * add a UT * resolve comments * fix comment lines * limit markdown version (#773) * [Enhancement] Better index put ONNX export. (#704) * Add rewriter for tensor setitem * add version check * Upgrade Dockerfile to use TensorRT==8.2.4.2 (#706) * Upgrade TensorRT to 8.2.4.2 * upgrade pytorch&mmcv in CPU Dockerfile * Delete redundant port example in Docker * change 160x160-608x608 to 64x64-608x608 for yolov3 * [Fix] reduce log verbosity & improve error reporting (#755) * reduce log verbosity & improve error reporting * improve error reporting * [Enhancement] Support latest ppl.nn & ppl.cv (#564) * support latest ppl.nn * fix pplnn for model convertor * fix lint * update memory policy * import algo from buffer * update ppl.cv * use `ppl.cv==0.7.0` * document supported ppl.nn version * skip pplnn dependency when building shared libs * [Fix][P0] Fix for torch1.12 (#751) * fix for torch1.12 * add comment * fix check env (#785) * [Fix] fix cascade mask rcnn (#787) * fix cascade mask rcnn * fix lint * add regression * [Feature] Support RoITransRoIHead (#713) * [Feature] Support RoITransRoIHead * Add docs * Add mmrotate models regression test * Add a draft for test code * change the argument name * fix test code * fix minor change for not class agnostic case * fix sample for test code * fix sample for test code * Add mmrotate in requirements * Revert "Add mmrotate in requirements" This reverts commit 043490075e6dbe4a8fb98e94b2b583b91fc5038d. * [Fix] fix triu (#792) * fix triu * triu -> triu_default * [Enhancement] Install Optimizer by setuptools (#690) * Add fuse select assign pass * move code to csrc * add config flag * Add fuse select assign pass * Add CSE for ONNX * remove useless code * Install optimizer by setup tools * fix comment * [Feature] support MMRotate model with le135 (#788) * support MMRotate model with le135 * cse before fuse select assign * remove unused import * [Fix] Support macOS build (#762) * fix macOS build * fix missing * add option to build & install examples (#822) * [Fix] Fix setup on non-linux-x64 (#811) * fix setup * replace long to int64_t * [Feature] support build single sdk library (#806) * build single lib for c api * update csharp doc & project * update test build * fix test build * fix * update document for building android sdk (#817) Co-authored-by: dwSun <dwsunny@icloud.com> * [Enhancement] support kwargs in SDK python bindings (#794) * support-kwargs * make '__call__' as single image inference and add 'batch' API to deal with batch images inference * fix linting error and typo * fix lint * improvement(sdk): add sdk code coverage (#808) * feat(doc): add CI * CI(sdk): add sdk coverage * style(test): code format * fix(CI): update coverage.info path * improvement(CI): use internal image * improvement(CI): push coverage info once * [Feature] Add C++ API for SDK (#831) * add C++ API * unify result type & add examples * minor fix * install cxx API headers * fix Mat, add more examples * fix monolithic build & fix lint * install examples correctly * fix lint * feat(tools/deploy.py): support snpe (#789) * fix(tools/deploy.py): support snpe * improvement(backend/snpe): review advices * docs(backend/snpe): update build * docs(backend/snpe): server support specify port * docs(backend/snpe): update path * fix(backend/snpe): time counter missing argument * docs(backend/snpe): add missing argument * docs(backend/snpe): update download and using * improvement(snpe_net.cpp): load model with modeldata * Support setup on environment with no PyTorch (#843) * support test with multi batch (#829) * support test with multi batch * resolve comment * import algorithm from buffer (#793) * [Enhancement] build sdk python api in standard-alone manner (#810) * build sdk python api in standard-alone manner * enable MMDEPLOY_BUILD_SDK_MONOLITHIC and MMDEPLOY_BUILD_EXAMPLES in prebuild config * link mmdeploy to python target when monolithic option is on * checkin README to describe precompiled package build procedure * use packaging.version.parse(python_version) instead of list(python_version) * fix according to review results * rebase master * rollback cmake.in and apis/python/CMakeLists.txt * reorganize files in install/example * let cmake detect visual studio instead of specifying 2019 * rename whl name of precompiled package * fix according to review results * Fix SDK backend (#844) * fix mmpose python api (#852) * add prebuild package usage docs on windows (#816) * add prebuild package usage docs on windows * fix lint * update * try fix lint * add en docs * update * update * udpate faq * fix typo (#862) * [Enhancement] Improve get_started documents and bump version to 0.7.0 (#813) * simplify commands in get_started * add installation commands for Windows * fix typo * limit markdown and sphinx_markdown_tables version * adopt html <details open> tag * bump mmdeploy version * bump mmdeploy version * update get_started * update get_started * use python3.8 instead of python3.7 * remove duplicate section * resolve issue #856 * update according to review results * add reference to prebuilt_package_windows.md * fix error when build sdk demos * fix mmcls Co-authored-by: Ryan_Huang <44900829+DrRyanHuang@users.noreply.github.com> Co-authored-by: Chen Xin <xinchen.tju@gmail.com> Co-authored-by: q.yao <yaoqian@sensetime.com> Co-authored-by: zytx121 <592267829@qq.com> Co-authored-by: Li Zhang <lzhang329@gmail.com> Co-authored-by: tripleMu <gpu@163.com> Co-authored-by: tripleMu <865626@163.com> Co-authored-by: hanrui1sensetime <83800577+hanrui1sensetime@users.noreply.github.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: Bryan Glen Suello <11388006+bgsuello@users.noreply.github.com> Co-authored-by: zambranohally <63218980+zambranohally@users.noreply.github.com> Co-authored-by: AllentDan <41138331+AllentDan@users.noreply.github.com> Co-authored-by: tpoisonooo <khj.application@aliyun.com> Co-authored-by: Hakjin Lee <nijkah@gmail.com> Co-authored-by: 孙德伟 <5899962+dwSun@users.noreply.github.com> Co-authored-by: dwSun <dwsunny@icloud.com> Co-authored-by: Chen Xin <irexyc@gmail.com>
6.6 KiB
6.6 KiB
支持 SNPE
mmdeploy 集成 snpe 的方式简单且有效: Client/Server 模式。
这种模式
- 能剥离
模型转换
和推理
环境:
- 推理无关事项在算力更高的设备上完成;
- 对于推理计算,能拿到 gpu/npu 真实运行结果,而非 cpu 模拟数值。
-
能覆盖成本敏感的设备。armv7/risc-v/mips 芯片满足产品需求,但往往对 Python 支持有限;
-
能简化 mmdeploy 安装步骤。如果只想转 snpe 模型测试精度,不需要编译 .whl 包。
一、运行推理服务
下载预编译 snpe 推理服务包, adb push
到手机、执行。
注意手机要有 qcom 芯片。
$ wget https://media.githubusercontent.com/media/tpoisonooo/mmdeploy_snpe_testdata/main/snpe-inference-server-1.59.tar.gz
...
$ sudo apt install adb
$ adb push snpe-inference-server-1.59.tar.gz /data/local/tmp/
# 解压运行
$ adb shell
venus:/ $ cd /data/local/tmp
130|venus:/data/local/tmp $ tar xvf snpe-inference-server-1.59.tar.gz
...
130|venus:/data/local/tmp $ source export1.59.sh
130|venus:/data/local/tmp $ ./inference_server 60000
...
Server listening on [::]:60000
此时推理服务应打印设备所有 ipv6 和 ipv4 地址,并监听端口。
tips:
- 如果
adb devices
找不到设备,可能因为:- 有些廉价线只能充电、不能传输数据
- 或者没有打开手机的“开发者模式”
- 如果需要自己编译,可参照 NDK 交叉编译 snpe 推理服务
- 如果监听端口时
segmentation fault
,可能是因为:- 端口号已占用,换一个端口
二、安装 mmdeploy
- 环境要求
事项 | 版本 | 备注 |
---|---|---|
host OS | ubuntu18.04 x86_64 | snpe 指定版本 |
Python | 3.6.0 | snpe 指定版本 |
- 安装
官网下载 snpe-1.59,解压设置环境变量
$ unzip snpe-1.59.0.zip
$ export SNPE_ROOT=${PWD}/snpe-1.59.0.3230
$ cd /path/to/mmdeploy
$ export PYTHONPATH=${PWD}/service/snpe/client:${SNPE_ROOT}/lib/python:${PYTHONPATH}
$ export LD_LIBRARY_PATH=${SNPE_ROOT}/lib/x86_64-linux-clang:${LD_LIBRARY_PATH}
$ export PATH=${SNPE_ROOT}/bin/x86_64-linux-clang:${PATH}
$ python3 -m pip install -e .
tips:
- 如果网络不好,这个 .tar.gz 仅减小官方包体积,没有修改原始内容。
三、测试模型
以 Resnet-18 为例。先参照文档安装 mmcls,然后使用 tools/deploy.py
转换模型。
$ export MODEL_CONFIG=/path/to/mmclassification/configs/resnet/resnet18_8xb16_cifar10.py
$ export MODEL_PATH=https://download.openmmlab.com/mmclassification/v0/resnet/resnet18_b16x8_cifar10_20210528-bd6371c8.pth
# 模型转换
$ cd /path/to/mmdeploy
$ python3 tools/deploy.py configs/mmcls/classification_snpe_static.py $MODEL_CONFIG $MODEL_PATH /path/to/test.png --work-dir resnet18 --device cpu --uri 192.168.1.1\:60000 --dump-info
# 精度测试
$ python3 tools/test.py configs/mmcls/classification_snpe_static.py $MODEL_CONFIG --model reset18/end2end.dlc --metrics accuracy precision f1_score recall --uri 192.168.1.1\:60000
注意需要 --uri
指明 snpe 推理服务的 ip 和端口号,可以使用 ipv4 和 ipv6 地址。
四、Android NDK 编译 SDK
如果你还需要用 Android NDK 编译 mmdeploy SDK,请继续阅读本章节。
1. 下载 OCV、NDK,设置环境变量
# 下载 android OCV
$ export OPENCV_VERSION=4.5.4
$ wget https://github.com/opencv/opencv/releases/download/${OPENCV_VERSION}/opencv-${OPENCV_VERSION}-android-sdk.zip
$ unzip opencv-${OPENCV_VERSION}-android-sdk.zip
$ export ANDROID_OCV_ROOT=`realpath opencv-${OPENCV_VERSION}-android-sdk`
# 下载 ndk r23b
$ wget https://dl.google.com/android/repository/android-ndk-r23b-linux.zip
$ unzip android-ndk-r23b-linux.zip
$ export ANDROID_NDK_ROOT=`realpath android-ndk-r23b`
2. 编译 mmdeploy SDK
$ cd /path/to/mmdeploy
$ mkdir build && cd build
$ cmake .. \
-DMMDEPLOY_BUILD_SDK=ON -DMMDEPLOY_CODEBASES=all \
-DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake \
-DMMDEPLOY_CODEBASES=all -DMMDEPLOY_TARGET_BACKENDS=snpe \
-DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=android-30 \
-DANDROID_STL=c++_static \
-DOpenCV_DIR=${ANDROID_OCV_ROOT}/sdk/native/jni/abi-arm64-v8a \
-DMMDEPLOY_SHARED_LIBS=ON
$ make && make install
选项说明
选项 | 说明 |
---|---|
DMMDEPLOY_CODEBASES=all | 编译所有算法后处理 |
CMAKE_TOOLCHAIN_FILE | 加载 NDK 参数,主要用于选择编译器版本 |
MMDEPLOY_TARGET_BACKENDS=snpe | 使用 snpe 推理 |
ANDROID_STL=c++_static | 避免 NDK 环境找不到合适的 c++ lib |
MMDEPLOY_SHARED_LIBS=ON | 官方 snpe 没有提供静态库 |
3. 编译 demo
$ cd /path/to/install/example
$ mkdir build && cd build
$ cmake .. \
-DMMDEPLOY_CODEBASES=all \
-DCMAKE_TOOLCHAIN_FILE=${ANDROID_NDK_ROOT}/build/cmake/android.toolchain.cmake \
-DMMDEPLOY_CODEBASES=all -DMMDEPLOY_TARGET_BACKENDS=snpe \
-DANDROID_ABI=arm64-v8a -DANDROID_PLATFORM=android-30 \
-DANDROID_STL=c++_static \
-DOpenCV_DIR=${ANDROID_OCV_ROOT}/sdk/native/jni/abi-arm64-v8a \
-DMMDeploy_DIR=${PWD}/../../lib/cmake/MMDeploy
$ make
$ tree -L 1
.
├── image_classification
├── image_restorer
├── image_segmentation
├── object_detection
├── ocr
├── pose_detection
└── rotated_object_detection
4. 运行 demo
先确认测试模型用了 --dump-info
,这样 resnet18
目录才有 pipeline.json
等 SDK 所需文件。
把 dump 好的模型目录、可执行文件和 lib 都 adb push
到设备里
$ cd /path/to/mmdeploy
$ adb push resnet18 /data/local/tmp
$ adb push tests/data/tiger.jpeg /data/local/tmp/resnet18/
$ cd /path/to/install/
$ adb push lib /data/local/tmp
$ cd /path/to/install/example/build
$ adb push image_classification /data/local/tmp/resnet18/
设置环境变量,执行样例
$ adb push /path/to/mmcls/demo/demo.JPEG /data/local/tmp
$ adb shell
venus:/ $ cd /data/local/tmp/resnet18
venus:/data/local/tmp/resnet18 $ export LD_LIBRARY_PATH=${LD_LIBRARY_PATH}:/data/local/tmp/lib
venus:/data/local/tmp/resnet18 $ ./image_classification cpu ./ tiger.jpeg
..
label: 3, score: 0.3214