From 4bb9bc738c9008055fbc9347f46da70ee60fdad3 Mon Sep 17 00:00:00 2001 From: RunningLeon Date: Thu, 6 Apr 2023 12:07:42 +0800 Subject: [PATCH] bump version to v1.0.0 (#1960) * change docs from 1.x to main * bump version * update readme status info and highlights * revert version change * fix dead links * fix script * fix docs * fix building status * fix md lint error * upgrade to ubuntu20.04 for github ci * Revert "upgrade to ubuntu20.04 for github ci" This reverts commit 9c598f4857633dfb96b116ca9fb9a5d15b5fa6b4. * update codebase md files * upgrade to ubuntu20.04 for github ci * fix * fix requirements * fix * fix ci * bump version * fix * fix pplnn torchscript * fix building status * fix ncnn * fix * remove circileci hold * fix pytorch image --- .circleci/config.yml | 2 +- .circleci/test.yml | 14 +--- .github/ISSUE_TEMPLATE/1-bug-report.yml | 2 +- .github/ISSUE_TEMPLATE/config.yml | 2 +- .github/workflows/backend-ascend.yml | 4 +- .github/workflows/backend-ncnn.yml | 14 ++-- .github/workflows/backend-ort.yml | 4 +- .github/workflows/backend-pplnn.yml | 46 ++++++++++--- .github/workflows/backend-rknn.yml | 4 +- .github/workflows/backend-snpe.yml | 4 +- .github/workflows/backend-torchscript.yml | 10 +-- .github/workflows/build.yml | 68 +++++++++---------- .github/workflows/java_api.yml | 2 +- .github/workflows/lint.yml | 2 +- .github/workflows/prebuild.yml | 1 - .github/workflows/quantize.yml | 13 +--- .github/workflows/rust_api.yml | 2 +- .pre-commit-config.yaml | 2 +- README.md | 42 +++++++----- README_zh-CN.md | 50 ++++++++------ csrc/mmdeploy/apis/csharp/README.md | 4 +- .../image_classification.csproj | 2 +- .../image_restorer/image_restorer.csproj | 2 +- .../image_segmentation.csproj | 2 +- .../object_detection/object_detection.csproj | 2 +- .../csharp/ocr_detection/ocr_detection.csproj | 2 +- .../ocr_recognition/ocr_recognition.csproj | 2 +- .../pose_detection/pose_detection.csproj | 2 +- demo/tutorials/tutorials_1.ipynb | 2 +- docker/CPU/Dockerfile | 6 +- docker/GPU/Dockerfile | 6 +- docs/en/01-how-to-build/android.md | 2 +- docs/en/01-how-to-build/build_from_docker.md | 2 +- docs/en/01-how-to-build/build_from_source.md | 4 +- docs/en/01-how-to-build/jetsons.md | 4 +- docs/en/01-how-to-build/rockchip.md | 6 +- .../02-how-to-run/prebuilt_package_windows.md | 30 ++++---- docs/en/02-how-to-run/useful_tools.md | 2 +- docs/en/03-benchmark/benchmark.md | 4 +- docs/en/04-supported-codebases/mmaction2.md | 20 +++--- docs/en/04-supported-codebases/mmcls.md | 10 +-- docs/en/04-supported-codebases/mmdet.md | 12 ++-- docs/en/04-supported-codebases/mmedit.md | 12 ++-- docs/en/04-supported-codebases/mmocr.md | 14 ++-- docs/en/04-supported-codebases/mmpose.md | 10 +-- docs/en/04-supported-codebases/mmrotate.md | 14 ++-- docs/en/04-supported-codebases/mmseg.md | 14 ++-- docs/en/05-supported-backends/rknn.md | 2 +- docs/en/06-custom-ops/tensorrt.md | 2 +- docs/en/conf.py | 2 +- docs/en/faq.md | 4 +- docs/en/get_started.md | 20 +++--- docs/en/switch_language.md | 4 +- .../01-how-to-build/build_from_docker.md | 2 +- docs/zh_cn/01-how-to-build/rockchip.md | 6 +- .../02-how-to-run/prebuilt_package_windows.md | 26 +++---- docs/zh_cn/02-how-to-run/useful_tools.md | 2 +- docs/zh_cn/03-benchmark/benchmark.md | 4 +- .../zh_cn/04-supported-codebases/mmaction2.md | 22 +++--- docs/zh_cn/04-supported-codebases/mmcls.md | 12 ++-- docs/zh_cn/04-supported-codebases/mmdet.md | 12 ++-- docs/zh_cn/04-supported-codebases/mmedit.md | 12 ++-- docs/zh_cn/04-supported-codebases/mmocr.md | 14 ++-- docs/zh_cn/04-supported-codebases/mmpose.md | 10 +-- docs/zh_cn/04-supported-codebases/mmrotate.md | 12 ++-- docs/zh_cn/04-supported-codebases/mmseg.md | 14 ++-- docs/zh_cn/05-supported-backends/rknn.md | 2 +- docs/zh_cn/06-custom-ops/tensorrt.md | 2 +- docs/zh_cn/conf.py | 2 +- docs/zh_cn/faq.md | 4 +- docs/zh_cn/get_started.md | 20 +++--- docs/zh_cn/switch_language.md | 4 +- docs/zh_cn/tutorial/02_challenges.md | 14 ++-- docs/zh_cn/tutorial/03_pytorch2onnx.md | 2 +- .../tutorial/06_introduction_to_tensorrt.md | 2 +- mmdeploy/version.py | 2 +- requirements.txt | 1 + requirements/backends.txt | 2 +- requirements/codebases.txt | 2 +- requirements/optional.txt | 2 - .../packaging/mmdeploy_runtime/version.py | 2 +- tools/package_tools/test/test_sdk.sh | 2 +- tools/scripts/ubuntu_utils.py | 2 - 83 files changed, 372 insertions(+), 357 deletions(-) diff --git a/.circleci/config.yml b/.circleci/config.yml index 61774beb06..e02083434f 100644 --- a/.circleci/config.yml +++ b/.circleci/config.yml @@ -33,7 +33,7 @@ workflows: third_party/.* lint_only false tools/.* lint_only false setup.py lint_only false - base-revision: dev-1.x + base-revision: main # this is the path of the configuration we should trigger once # path filtering and pipeline parameter value updates are # complete. In this case, we are using the parent dynamic diff --git a/.circleci/test.yml b/.circleci/test.yml index 12209b062b..a94dcb4d74 100644 --- a/.circleci/test.yml +++ b/.circleci/test.yml @@ -84,8 +84,7 @@ commands: command: | cd mmdeploy python -m mim install -r requirements/codebases.txt - python -m pip install -r requirements/tests.txt - python -m pip install -r requirements/runtime.txt + python -m pip install -r requirements.txt python -m pip install -U numpy clip numba cd .. perform_model_converter_ut: @@ -145,8 +144,7 @@ jobs: command: | docker exec mmdeploy pip install onnxruntime==1.8.1 docker exec mmdeploy mim install -r mmdeploy/requirements/codebases.txt - docker exec mmdeploy pip install -r mmdeploy/requirements/tests.txt - docker exec mmdeploy pip install -r mmdeploy/requirements/runtime.txt + docker exec mmdeploy pip install -r mmdeploy/requirements.txt docker exec mmdeploy pip install -U numpy clip numba - run: name: Perform Model Converter unittests @@ -272,11 +270,3 @@ workflows: version: 1.8.1 requires: - lint - - hold: - type: approval - requires: - - test_linux_onnxruntime - - test_windows_onnxruntime - - test_linux_tensorrt: - requires: - - hold diff --git a/.github/ISSUE_TEMPLATE/1-bug-report.yml b/.github/ISSUE_TEMPLATE/1-bug-report.yml index b1ed89775e..85f7d05566 100644 --- a/.github/ISSUE_TEMPLATE/1-bug-report.yml +++ b/.github/ISSUE_TEMPLATE/1-bug-report.yml @@ -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/tree/1.x/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/main/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: diff --git a/.github/ISSUE_TEMPLATE/config.yml b/.github/ISSUE_TEMPLATE/config.yml index 94287d30f6..fd41553b89 100644 --- a/.github/ISSUE_TEMPLATE/config.yml +++ b/.github/ISSUE_TEMPLATE/config.yml @@ -2,7 +2,7 @@ blank_issues_enabled: false contact_links: - name: 💥 FAQ - url: https://github.com/open-mmlab/mmdeploy/tree/1.x/docs/en/faq.md + url: https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md about: Check if your issue already has solutions - name: 💬 Forum url: https://github.com/open-mmlab/mmdeploy/discussions diff --git a/.github/workflows/backend-ascend.yml b/.github/workflows/backend-ascend.yml index 9eb7b9a649..f5817af983 100644 --- a/.github/workflows/backend-ascend.yml +++ b/.github/workflows/backend-ascend.yml @@ -18,7 +18,7 @@ concurrency: jobs: build_sdk_demo: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 strategy: matrix: python-version: [3.7] @@ -37,9 +37,7 @@ jobs: run: | sudo apt update sudo apt install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev libc++1-9 libc++abi1-9 - sudo add-apt-repository ppa:ignaciovizzo/opencv3-nonfree sudo apt install libopencv-dev - pkg-config --libs opencv - name: Install Ascend Toolkit run: | mkdir -p $GITHUB_WORKSPACE/Ascend diff --git a/.github/workflows/backend-ncnn.yml b/.github/workflows/backend-ncnn.yml index 15b1a503a8..2fb2bb8ea7 100644 --- a/.github/workflows/backend-ncnn.yml +++ b/.github/workflows/backend-ncnn.yml @@ -18,7 +18,7 @@ concurrency: jobs: test_onnx2ncnn: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 strategy: matrix: python-version: [3.7] @@ -31,13 +31,11 @@ jobs: uses: actions/setup-python@v2 with: python-version: ${{ matrix.python-version }} - - name: Install unittest dependencies + - name: Install dependencies run: | + sudo apt update + sudo apt install wget gcc-multilib g++-multilib wget libprotobuf-dev protobuf-compiler python -m pip install cmake onnx - - name: update - run: sudo apt update - - name: gcc-multilib - run: sudo apt install gcc-multilib g++-multilib wget libprotobuf-dev protobuf-compiler - name: Install ncnn run: | wget https://github.com/Tencent/ncnn/archive/refs/tags/20220420.tar.gz @@ -60,7 +58,7 @@ jobs: echo $(pwd) ln -s build/bin/mmdeploy_onnx2ncnn ./ python .github/scripts/test_onnx2ncnn.py --run 1 - script_install: + build_ncnn: runs-on: ubuntu-20.04 strategy: matrix: @@ -78,5 +76,5 @@ jobs: run: | python -m pip install torch==1.8.2 torchvision==0.9.2 --extra-index-url https://download.pytorch.org/whl/lts/1.8/cpu python -m pip install mmcv-lite - python tools/scripts/build_ubuntu_x64_ncnn.py + python tools/scripts/build_ubuntu_x64_ncnn.py 8 python -c 'import mmdeploy.apis.ncnn as ncnn_api; assert ncnn_api.is_available(with_custom_ops=True)' diff --git a/.github/workflows/backend-ort.yml b/.github/workflows/backend-ort.yml index c36a3ad0a8..d296270c7b 100644 --- a/.github/workflows/backend-ort.yml +++ b/.github/workflows/backend-ort.yml @@ -17,7 +17,7 @@ concurrency: cancel-in-progress: true jobs: - script_install: + buils_ort: runs-on: ubuntu-20.04 strategy: matrix: @@ -35,7 +35,7 @@ jobs: run: | python -m pip install torch==1.8.2 torchvision==0.9.2 --extra-index-url https://download.pytorch.org/whl/lts/1.8/cpu python -m pip install mmcv-lite openmim - python tools/scripts/build_ubuntu_x64_ort.py + python tools/scripts/build_ubuntu_x64_ort.py 8 python -c 'import mmdeploy.apis.onnxruntime as ort_api; assert ort_api.is_available(with_custom_ops=True)' - name: test mmcls full pipeline run: | diff --git a/.github/workflows/backend-pplnn.yml b/.github/workflows/backend-pplnn.yml index a6cda40936..c9daeb2712 100644 --- a/.github/workflows/backend-pplnn.yml +++ b/.github/workflows/backend-pplnn.yml @@ -17,23 +17,47 @@ concurrency: cancel-in-progress: true jobs: - script_install: - runs-on: ubuntu-18.04 - strategy: - matrix: - python-version: [3.7] + build_pplnn_cuda: + runs-on: [self-hosted, linux-3090] + container: + image: openmmlab/mmdeploy:ubuntu20.04-cuda11.3 + options: "--gpus=all --ipc=host" steps: - name: Checkout repository uses: actions/checkout@v3 with: submodules: 'recursive' - - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v2 + - name: Install dependencies + run: | + apt update && apt install unzip wget + python3 -V + python3 -m pip install openmim numpy + python3 -m pip install -r requirements.txt + python3 -m mim install $(cat requirements/codebases.txt | grep mmcls) + python3 -m pip list + - name: Build SDK + run: | + bash .circleci/scripts/linux/build.sh "cuda" "pplnn" \ + -Dpplcv_DIR=${pplcv_DIR} \ + -Dpplnn_DIR=${pplnn_DIR} + ls build/lib + - name: Install mmdeploy with pplnn + run: | + rm -rf .eggs && python3 -m pip install -e . + export LD_LIBRARY_PATH="/root/workspace/mmdeploy/build/lib:${LD_LIBRARY_PATH}" + python3 tools/check_env.py + python3 -c 'import mmdeploy.apis.pplnn as pplnn_api; assert pplnn_api.is_available()' + + build_pplnn_cpu: + runs-on: ubuntu-20.04 + steps: + - name: Checkout repository + uses: actions/checkout@v3 with: - python-version: ${{ matrix.python-version }} - - name: Install mmdeploy + submodules: 'recursive' + - name: Install mmdeploy with pplnn run: | python -m pip install torch==1.8.2 torchvision==0.9.2 --extra-index-url https://download.pytorch.org/whl/lts/1.8/cpu - python -m pip install mmcv-lite - python tools/scripts/build_ubuntu_x64_pplnn.py + python -m pip install mmcv-lite protobuf==3.20.2 + python tools/scripts/build_ubuntu_x64_pplnn.py 8 python -c 'import mmdeploy.apis.pplnn as pplnn_api; assert pplnn_api.is_available()' diff --git a/.github/workflows/backend-rknn.yml b/.github/workflows/backend-rknn.yml index 01a8e3a7b5..4a8b804c80 100644 --- a/.github/workflows/backend-rknn.yml +++ b/.github/workflows/backend-rknn.yml @@ -19,7 +19,7 @@ concurrency: jobs: build_rknpu2: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 steps: - name: Checkout repository uses: actions/checkout@v3 @@ -31,7 +31,7 @@ jobs: run: | sh -x tools/scripts/ubuntu_cross_build_rknn.sh rk3588 build_rknpu: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 steps: - name: Checkout repository uses: actions/checkout@v3 diff --git a/.github/workflows/backend-snpe.yml b/.github/workflows/backend-snpe.yml index b74de51fcd..1fec2afffd 100644 --- a/.github/workflows/backend-snpe.yml +++ b/.github/workflows/backend-snpe.yml @@ -18,7 +18,7 @@ concurrency: jobs: build_sdk_demo: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 steps: - name: Checkout repository uses: actions/checkout@v3 @@ -31,9 +31,7 @@ jobs: sudo apt install wget libprotobuf-dev protobuf-compiler sudo apt update sudo apt install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev libc++1-9 libc++abi1-9 - sudo add-apt-repository ppa:ignaciovizzo/opencv3-nonfree sudo apt install libopencv-dev - pkg-config --libs opencv - name: Install snpe run: | wget https://media.githubusercontent.com/media/tpoisonooo/mmdeploy_snpe_testdata/main/snpe-1.59.tar.gz diff --git a/.github/workflows/backend-torchscript.yml b/.github/workflows/backend-torchscript.yml index 2cc149e743..56cb701b4e 100644 --- a/.github/workflows/backend-torchscript.yml +++ b/.github/workflows/backend-torchscript.yml @@ -1,4 +1,4 @@ -name: backend-ort +name: backend-torchscript on: push: @@ -17,8 +17,8 @@ concurrency: cancel-in-progress: true jobs: - script_install: - runs-on: ubuntu-18.04 + build_torchscript: + runs-on: ubuntu-20.04 strategy: matrix: python-version: [3.7] @@ -33,5 +33,7 @@ jobs: python-version: ${{ matrix.python-version }} - name: Install mmdeploy run: | + python -m pip install torch==1.11.0 torchvision==0.12.0 --extra-index-url https://download.pytorch.org/whl/lts/1.11/cpu python -m pip install mmcv-lite - python tools/scripts/build_ubuntu_x64_torchscript.py + python tools/scripts/build_ubuntu_x64_torchscript.py 8 + python -c 'from mmdeploy.backend.torchscript import is_available; assert is_available()' diff --git a/.github/workflows/build.yml b/.github/workflows/build.yml index 5a9afee1bc..14f05e3a7e 100644 --- a/.github/workflows/build.yml +++ b/.github/workflows/build.yml @@ -22,7 +22,7 @@ concurrency: jobs: build_cpu_model_convert: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 strategy: matrix: python-version: [3.7] @@ -45,10 +45,11 @@ jobs: - name: Install unittest dependencies run: | python -m pip install openmim - python -m pip install -r requirements.txt -r requirements/backends.txt + python -m pip install -r requirements.txt + python -m pip install -r requirements/backends.txt python -m mim install "mmcv>=2.0.0rc1" python -m mim install -r requirements/codebases.txt - python -m pip install -U numpy clip + python -m pip install -U numpy clip numba python -m pip list - name: Install mmyolo run: | @@ -70,7 +71,7 @@ jobs: pytest tests/test_deploy build_cpu_sdk: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 steps: - name: Checkout repository uses: actions/checkout@v3 @@ -83,13 +84,11 @@ jobs: sudo apt install gcc-multilib g++-multilib wget libprotobuf-dev protobuf-compiler sudo apt update sudo apt install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev libc++1-9 libc++abi1-9 - sudo add-apt-repository ppa:ignaciovizzo/opencv3-nonfree sudo apt install libopencv-dev lcov wget - pkg-config --libs opencv - name: Build and run SDK unit test without backend run: | mkdir -p build && pushd build - cmake .. -DCMAKE_CXX_COMPILER=g++-7 -DMMDEPLOY_CODEBASES=all -DMMDEPLOY_BUILD_SDK=ON -DMMDEPLOY_BUILD_SDK_PYTHON_API=OFF -DMMDEPLOY_TARGET_DEVICES=cpu -DMMDEPLOY_COVERAGE=ON -DMMDEPLOY_BUILD_TEST=ON + cmake .. -DCMAKE_CXX_COMPILER=g++ -DMMDEPLOY_CODEBASES=all -DMMDEPLOY_BUILD_SDK=ON -DMMDEPLOY_BUILD_SDK_PYTHON_API=OFF -DMMDEPLOY_TARGET_DEVICES=cpu -DMMDEPLOY_COVERAGE=ON -DMMDEPLOY_BUILD_TEST=ON make -j2 mkdir -p mmdeploy_test_resources/transform cp ../tests/data/tiger.jpeg mmdeploy_test_resources/transform/ @@ -116,14 +115,13 @@ jobs: sh -x tools/scripts/ubuntu_cross_build_aarch64.sh build_cuda102: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 container: image: pytorch/pytorch:1.9.0-cuda10.2-cudnn7-devel env: FORCE_CUDA: 1 strategy: matrix: - python-version: [3.7] torch: [1.9.0+cu102] include: - torch: 1.9.0+cu102 @@ -131,27 +129,27 @@ jobs: torchvision: 0.10.0+cu102 steps: - uses: actions/checkout@v2 - - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v2 - with: - python-version: ${{ matrix.python-version }} - name: Install system dependencies run: | apt-key adv --keyserver keyserver.ubuntu.com --recv-keys A4B469963BF863CC - apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev python${{matrix.python-version}}-dev + apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev apt-get clean rm -rf /var/lib/apt/lists/* - name: Install PyTorch - run: python -m pip install torch==${{matrix.torch}} torchvision==${{matrix.torchvision}} -f https://download.pytorch.org/whl/torch_stable.html + run: | + python -V + python -m pip install --upgrade pip + python -m pip install torch==${{matrix.torch}} torchvision==${{matrix.torchvision}} -f https://download.pytorch.org/whl/torch_stable.html - name: Install dependencies run: | python -V export CFLAGS=`python -c 'import sysconfig;print("-I"+sysconfig.get_paths()["include"])'` python -m pip install openmim - python -m pip install -r requirements.txt -r requirements/backends.txt + python -m pip install -r requirements.txt + python -m pip install -r requirements/backends.txt python -m mim install "mmcv>=2.0.0rc1" CFLAGS=$CFLAGS python -m mim install -r requirements/codebases.txt - python -m pip install -U pycuda numpy clip + python -m pip install -U pycuda numpy clip numba python -m pip list - name: Build and install run: | @@ -163,43 +161,40 @@ jobs: coverage xml coverage report -m - build_cuda111: - runs-on: ubuntu-18.04 + build_cuda113: + runs-on: ubuntu-20.04 container: - image: pytorch/pytorch:1.8.0-cuda11.1-cudnn8-devel - + image: pytorch/pytorch:1.10.0-cuda11.3-cudnn8-devel strategy: matrix: - python-version: [3.7] - torch: [1.8.0+cu111] + torch: [1.10.0+cu113] include: - - torch: 1.8.0+cu111 - torch_version: torch1.8 - torchvision: 0.9.0+cu111 - + - torch: 1.10.0+cu113 + torch_version: torch1.10 + torchvision: 0.11.0+cu113 steps: - uses: actions/checkout@v2 - - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v2 - with: - python-version: ${{ matrix.python-version }} - name: Install system dependencies run: | apt-key adv --keyserver keyserver.ubuntu.com --recv-keys A4B469963BF863CC - apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev python${{matrix.python-version}}-dev + apt-get update && apt-get install -y ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev apt-get clean rm -rf /var/lib/apt/lists/* - name: Install PyTorch - run: python -m pip install torch==${{matrix.torch}} torchvision==${{matrix.torchvision}} -f https://download.pytorch.org/whl/torch_stable.html + run: | + python -V + python -m pip install --upgrade pip + python -m pip install torch==${{matrix.torch}} torchvision==${{matrix.torchvision}} -f https://download.pytorch.org/whl/torch_stable.html - name: Install dependencies run: | python -V export CFLAGS=`python -c 'import sysconfig;print("-I"+sysconfig.get_paths()["include"])'` python -m pip install openmim - python -m pip install -r requirements.txt -r requirements/backends.txt + python -m pip install -r requirements.txt + python -m pip install -r requirements/backends.txt python -m mim install "mmcv>=2.0.0rc1" python -m mim install -r requirements/codebases.txt - python -m pip install -U pycuda numpy clip + python -m pip install -U pycuda numpy clip numba python -m pip list - name: Build and install run: | @@ -285,7 +280,8 @@ jobs: conda activate $pwd\tmp_env python -V python -m pip install openmim - python -m pip install -r requirements.txt -r requirements/backends.txt + python -m pip install -r requirements.txt + python -m pip install -r requirements/backends.txt python -m mim install "mmcls>=1.0.0rc2" python -m pip list - name: Build mmdeploy diff --git a/.github/workflows/java_api.yml b/.github/workflows/java_api.yml index 984e27c0f8..8c7f0544c5 100644 --- a/.github/workflows/java_api.yml +++ b/.github/workflows/java_api.yml @@ -16,7 +16,7 @@ concurrency: jobs: test_java_api: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 steps: - name: Checkout repository uses: actions/checkout@v3 diff --git a/.github/workflows/lint.yml b/.github/workflows/lint.yml index c3045171ef..0b05c42a64 100644 --- a/.github/workflows/lint.yml +++ b/.github/workflows/lint.yml @@ -4,7 +4,7 @@ on: [push, pull_request] jobs: lint: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 steps: - uses: actions/checkout@v2 - name: Set up Python 3.7 diff --git a/.github/workflows/prebuild.yml b/.github/workflows/prebuild.yml index d1b068134c..6e7f6de4ba 100644 --- a/.github/workflows/prebuild.yml +++ b/.github/workflows/prebuild.yml @@ -4,7 +4,6 @@ on: push: branches: - main - - dev-1.x paths: - "mmdeploy/version.py" diff --git a/.github/workflows/quantize.yml b/.github/workflows/quantize.yml index 361b5cdce3..c1f4625be5 100644 --- a/.github/workflows/quantize.yml +++ b/.github/workflows/quantize.yml @@ -18,29 +18,22 @@ concurrency: jobs: test_ncnn_PTQ: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 container: image: pytorch/pytorch:1.8.0-cuda11.1-cudnn8-devel - strategy: matrix: - python-version: [3.7] torch: [1.8.0+cu111] include: - torch: 1.8.0+cu111 torch_version: torch1.8 torchvision: 0.9.0+cu111 - steps: - uses: actions/checkout@v2 - - name: Set up Python ${{ matrix.python-version }} - uses: actions/setup-python@v2 - with: - python-version: ${{ matrix.python-version }} - name: Install system dependencies run: | apt-key adv --keyserver keyserver.ubuntu.com --recv-keys A4B469963BF863CC - apt-get update && apt-get install -y wget ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev python${{matrix.python-version}}-dev + apt-get update && apt-get install -y wget ffmpeg libsm6 libxext6 git ninja-build libglib2.0-0 libxrender-dev apt-get clean rm -rf /var/lib/apt/lists/* - name: Install PyTorch @@ -48,7 +41,7 @@ jobs: - name: Install dependencies run: | python -V - + python -m pip install --upgrade pip python -m pip install -r requirements.txt python -m pip install -U numpy diff --git a/.github/workflows/rust_api.yml b/.github/workflows/rust_api.yml index a5ed43fd7f..24cd6e9e82 100644 --- a/.github/workflows/rust_api.yml +++ b/.github/workflows/rust_api.yml @@ -16,7 +16,7 @@ concurrency: jobs: test_rust_api: - runs-on: ubuntu-18.04 + runs-on: ubuntu-20.04 steps: - name: Checkout repository uses: actions/checkout@v3 diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index dd2359b1f6..ce3dd5287c 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -31,7 +31,7 @@ repos: rev: 0.7.9 hooks: - id: mdformat - args: ["--number"] + args: ["--number", "--disable-escape", "link-enclosure"] additional_dependencies: - mdformat-openmmlab - mdformat_frontmatter diff --git a/README.md b/README.md index 263c266903..07704eec9d 100644 --- a/README.md +++ b/README.md @@ -18,10 +18,10 @@
 
-[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdeploy.readthedocs.io/en/1.x/) +[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdeploy.readthedocs.io/en/latest/) [![badge](https://github.com/open-mmlab/mmdeploy/workflows/build/badge.svg)](https://github.com/open-mmlab/mmdeploy/actions) -[![codecov](https://codecov.io/gh/open-mmlab/mmdeploy/branch/1.x/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmdeploy) -[![license](https://img.shields.io/github/license/open-mmlab/mmdeploy.svg)](https://github.com/open-mmlab/mmdeploy/tree/1.x/LICENSE) +[![codecov](https://codecov.io/gh/open-mmlab/mmdeploy/branch/main/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmdeploy) +[![license](https://img.shields.io/github/license/open-mmlab/mmdeploy.svg)](https://github.com/open-mmlab/mmdeploy/tree/main/LICENSE) [![issue resolution](https://img.shields.io/github/issues-closed-raw/open-mmlab/mmdeploy)](https://github.com/open-mmlab/mmdeploy/issues) [![open issues](https://img.shields.io/github/issues-raw/open-mmlab/mmdeploy)](https://github.com/open-mmlab/mmdeploy/issues) @@ -43,6 +43,16 @@ English | [简体中文](README_zh-CN.md) +## Highlights + +The MMDeploy 1.x has been released, which is adapted to upstream codebases from OpenMMLab 2.0. Please **align the version** when using it. +The default branch has been switched to `main` from `master`. MMDeploy 0.x (`master`) will be deprecated and new features will only be added to MMDeploy 1.x (`main`) in future. + +| mmdeploy | mmengine | mmcv | mmdet | others | +| :------: | :------: | :------: | :------: | :----: | +| 0.x.y | - | \<=1.x.y | \<=2.x.y | 0.x.y | +| 1.x.y | 0.x.y | 2.x.y | 3.x.y | 1.x.y | + ## Introduction MMDeploy is an open-source deep learning model deployment toolset. It is a part of the [OpenMMLab](https://openmmlab.com/) project. @@ -73,24 +83,24 @@ The supported Device-Platform-InferenceBackend matrix is presented as following, The benchmark can be found from [here](docs/en/03-benchmark/benchmark.md) -| Device / Platform | Linux | Windows | macOS | Android | -| ----------------- | ------------------------------------------------------------------------ | --------------------------------------- | -------- | ---------------- | -| x86_64 CPU | ✔️ONNX Runtime
✔️pplnn
✔️ncnn
✔️OpenVINO
✔️LibTorch
✔️TVM | ✔️ONNX Runtime
✔️OpenVINO | - | - | -| ARM CPU | ✔️ncnn | - | - | ✔️ncnn | -| RISC-V | ✔️ncnn | - | - | - | -| NVIDIA GPU | ✔️ONNX Runtime
✔️TensorRT
✔️pplnn
✔️LibTorch
✔️TVM | ✔️ONNX Runtime
✔️TensorRT
✔️pplnn | - | - | -| NVIDIA Jetson | ✔️TensorRT | ✔️TensorRT | - | - | -| Huawei ascend310 | ✔️CANN | - | - | - | -| Rockchip | ✔️RKNN | - | - | - | -| Apple M1 | - | - | ✔️CoreML | - | -| Adreno GPU | - | - | - | ✔️ncnn
✔️SNPE | -| Hexagon DSP | - | - | - | ✔️SNPE | +| Device / Platform | Linux | Windows | macOS | Android | +| ----------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| x86_64 CPU | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-ort.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-ort.yml)ONNXRuntime
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-pplnn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-pplnn.yml)pplnn
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-ncnn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-ncnn.yml)ncnn
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-torchscript.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-torchscript.yml)LibTorch
![](https://img.shields.io/badge/build-no%20status-lightgrey)OpenVINO
![](https://img.shields.io/badge/build-no%20status-lightgrey)TVM
| [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ONNXRuntime
![](https://img.shields.io/badge/build-no%20status-lightgrey)OpenVINO
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ncnn
| - | - | +| ARM CPU | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ncnn
| - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-rknn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-rknn.yml)ncnn
| +| RISC-V | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/linux-riscv64-gcc.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/linux-riscv64-gcc.yml)ncnn
| - | - | - | +| NVIDIA GPU | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ONNXRuntime
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)TensorRT
![](https://img.shields.io/badge/build-no%20status-lightgrey)LibTorch
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-pplnn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-pplnn.yml)pplnn
| [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ONNXRuntime
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)TensorRT
| - | - | +| NVIDIA Jetson | ![](https://img.shields.io/badge/build-no%20status-lightgrey)TensorRT
| - | - | - | +| Huawei ascend310 | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-ascend.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-ascend.yml)CANN
| - | - | - | +| Rockchip | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-rknn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-rknn.yml)RKNN
| - | - | - | +| Apple M1 | - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-coreml.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-coreml.yml)CoreML
| - | +| Adreno GPU | - | - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-snpe.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-snpe.yml)SNPE
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-rknn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-rknn.yml)ncnn
| +| Hexagon DSP | - | - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-snpe.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-snpe.yml)SNPE
| ### Efficient and scalable C/C++ SDK Framework 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/1.x/) +## [Documentation](https://mmdeploy.readthedocs.io/en/latest/) Please read [getting_started](docs/en/get_started.md) for the basic usage of MMDeploy. We also provide tutoials about: diff --git a/README_zh-CN.md b/README_zh-CN.md index 068ff89442..9889741cf7 100644 --- a/README_zh-CN.md +++ b/README_zh-CN.md @@ -19,15 +19,25 @@
 
-[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdeploy.readthedocs.io/zh_CN/1.x/) +[![docs](https://img.shields.io/badge/docs-latest-blue)](https://mmdeploy.readthedocs.io/zh_CN/latest/) [![badge](https://github.com/open-mmlab/mmdeploy/workflows/build/badge.svg)](https://github.com/open-mmlab/mmdeploy/actions) -[![codecov](https://codecov.io/gh/open-mmlab/mmdeploy/branch/1.x/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmdeploy) -[![license](https://img.shields.io/github/license/open-mmlab/mmdeploy.svg)](https://github.com/open-mmlab/mmdeploy/tree/1.x/LICENSE) +[![codecov](https://codecov.io/gh/open-mmlab/mmdeploy/branch/main/graph/badge.svg)](https://codecov.io/gh/open-mmlab/mmdeploy) +[![license](https://img.shields.io/github/license/open-mmlab/mmdeploy.svg)](https://github.com/open-mmlab/mmdeploy/tree/main/LICENSE) [![issue resolution](https://img.shields.io/github/issues-closed-raw/open-mmlab/mmdeploy)](https://github.com/open-mmlab/mmdeploy/issues) [![open issues](https://img.shields.io/github/issues-raw/open-mmlab/mmdeploy)](https://github.com/open-mmlab/mmdeploy/issues) [English](README.md) | 简体中文 +## MMDeploy 1.x 版本 + +全新的 MMDeploy 1.x 已发布，该版本适配OpenMMLab 2.0生态体系，使用时务必**对齐版本**。 +MMDeploy 代码库默认分支从`master`切换至`main`。 MMDeploy 0.x (`master`)将逐步废弃，新特性将只添加到 MMDeploy 1.x (`main`)。 + +| mmdeploy | mmengine | mmcv | mmdet | mmcls and others | +| :------: | :------: | :------: | :------: | :--------------: | +| 0.x.y | - | \<=1.x.y | \<=2.x.y | 0.x.y | +| 1.x.y | 0.x.y | 2.x.y | 3.x.y | 1.x.y | + ## 介绍 MMDeploy 是 [OpenMMLab](https://openmmlab.com/) 模型部署工具箱，**为各算法库提供统一的部署体验**。基于 MMDeploy，开发者可以轻松从训练 repo 生成指定硬件所需 SDK，省去大量适配时间。 @@ -56,18 +66,18 @@ MMDeploy 是 [OpenMMLab](https://openmmlab.com/) 模型部署工具箱，**为 支持的设备平台和推理引擎如下表所示。benchmark请参考[这里](docs/zh_cn/03-benchmark/benchmark.md) -| Device / Platform | Linux | Windows | macOS | Android | -| ----------------- | ------------------------------------------------------------------------ | --------------------------------------- | -------- | ---------------- | -| x86_64 CPU | ✔️ONNX Runtime
✔️pplnn
✔️ncnn
✔️OpenVINO
✔️LibTorch
✔️TVM | ✔️ONNX Runtime
✔️OpenVINO | - | - | -| ARM CPU | ✔️ncnn | - | - | ✔️ncnn | -| RISC-V | ✔️ncnn | - | - | - | -| NVIDIA GPU | ✔️ONNX Runtime
✔️TensorRT
✔️pplnn
✔️LibTorch
✔️TVM | ✔️ONNX Runtime
✔️TensorRT
✔️pplnn | - | - | -| NVIDIA Jetson | ✔️TensorRT | ✔️TensorRT | - | - | -| Huawei ascend310 | ✔️CANN | - | - | - | -| Rockchip | ✔️RKNN | - | - | - | -| Apple M1 | - | - | ✔️CoreML | - | -| Adreno GPU | - | - | - | ✔️ncnn
✔️SNPE | -| Hexagon DSP | - | - | - | ✔️SNPE | +| Device / Platform | Linux | Windows | macOS | Android | +| ----------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------ | +| x86_64 CPU | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-ort.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-ort.yml)ONNXRuntime
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-pplnn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-pplnn.yml)pplnn
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-ncnn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-ncnn.yml)ncnn
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-torchscript.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-torchscript.yml)LibTorch
![](https://img.shields.io/badge/build-no%20status-lightgrey)OpenVINO
![](https://img.shields.io/badge/build-no%20status-lightgrey)TVM
| [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ONNXRuntime
![](https://img.shields.io/badge/build-no%20status-lightgrey)OpenVINO
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ncnn
| - | - | +| ARM CPU | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ncnn
| - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-rknn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-rknn.yml)ncnn
| +| RISC-V | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/linux-riscv64-gcc.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/linux-riscv64-gcc.yml)ncnn
| - | - | - | +| NVIDIA GPU | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ONNXRuntime
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)TensorRT
![](https://img.shields.io/badge/build-no%20status-lightgrey)LibTorch
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-pplnn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-pplnn.yml)pplnn
| [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)ONNXRuntime
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/build.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/build.yml)TensorRT
| - | - | +| NVIDIA Jetson | ![](https://img.shields.io/badge/build-no%20status-lightgrey)TensorRT
| - | - | - | +| Huawei ascend310 | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-ascend.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-ascend.yml)CANN
| - | - | - | +| Rockchip | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-rknn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-rknn.yml)RKNN
| - | - | - | +| Apple M1 | - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-coreml.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-coreml.yml)CoreML
| - | +| Adreno GPU | - | - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-snpe.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-snpe.yml)SNPE
[![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-rknn.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-rknn.yml)ncnn
| +| Hexagon DSP | - | - | - | [![](https://img.shields.io/github/actions/workflow/status/open-mmlab/mmdeploy/backend-snpe.yml)](https://github.com/open-mmlab/mmdeploy/actions/workflows/backend-snpe.yml)SNPE
| ### SDK 可高度定制化 @@ -75,7 +85,7 @@ 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/1.x/) +## [中文文档](https://mmdeploy.readthedocs.io/zh_CN/latest/) - [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 +129,7 @@ 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/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。 +基准和支持的模型列表可以在[基准](https://mmdeploy.readthedocs.io/zh_CN/latest/03-benchmark/benchmark.html)和[模型列表](https://mmdeploy.readthedocs.io/en/latest/03-benchmark/supported_models.html)中获得。 ## 贡献指南 @@ -176,9 +186,9 @@ MMDeploy 是 [OpenMMLab](https://openmmlab.com/) 模型部署工具箱，**为 扫描下方的二维码可关注 OpenMMLab 团队的 [知乎官方账号](https://www.zhihu.com/people/openmmlab)，加入 OpenMMLab 团队的 [官方交流 QQ 群](https://jq.qq.com/?_wv=1027&k=MSMAfWOe)，或添加微信小助手”OpenMMLabwx“加入官方交流微信群。
- - - + + +
我们会在 OpenMMLab 社区为大家 diff --git a/csrc/mmdeploy/apis/csharp/README.md b/csrc/mmdeploy/apis/csharp/README.md index 16b345d8ff..241efdf601 100644 --- a/csrc/mmdeploy/apis/csharp/README.md +++ b/csrc/mmdeploy/apis/csharp/README.md @@ -33,10 +33,10 @@ There are two methods to build the nuget package. (*option 1*) Use the command. -If your environment is well prepared, you can just go to the `csrc\apis\csharp` folder, open a terminal and type the following command, the nupkg will be built in `csrc\apis\csharp\MMDeploy\bin\Release\MMDeployCSharp.1.0.0-rc2.nupkg`. +If your environment is well prepared, you can just go to the `csrc\apis\csharp` folder, open a terminal and type the following command, the nupkg will be built in `csrc\apis\csharp\MMDeploy\bin\Release\MMDeployCSharp.1.0.0.nupkg`. ```shell -dotnet build --configuration Release -p:Version=1.0.0-rc2 +dotnet build --configuration Release -p:Version=1.0.0 ``` (*option 2*) Open MMDeploy.sln && Build. diff --git a/demo/csharp/image_classification/image_classification.csproj b/demo/csharp/image_classification/image_classification.csproj index de0494c844..a0e86ea43f 100644 --- a/demo/csharp/image_classification/image_classification.csproj +++ b/demo/csharp/image_classification/image_classification.csproj @@ -14,7 +14,7 @@ - + diff --git a/demo/csharp/image_restorer/image_restorer.csproj b/demo/csharp/image_restorer/image_restorer.csproj index 15b887841a..0c23d8d4cf 100644 --- a/demo/csharp/image_restorer/image_restorer.csproj +++ b/demo/csharp/image_restorer/image_restorer.csproj @@ -14,7 +14,7 @@ - + diff --git a/demo/csharp/image_segmentation/image_segmentation.csproj b/demo/csharp/image_segmentation/image_segmentation.csproj index 15b887841a..0c23d8d4cf 100644 --- a/demo/csharp/image_segmentation/image_segmentation.csproj +++ b/demo/csharp/image_segmentation/image_segmentation.csproj @@ -14,7 +14,7 @@ - + diff --git a/demo/csharp/object_detection/object_detection.csproj b/demo/csharp/object_detection/object_detection.csproj index 259e635c94..f52ab3532c 100644 --- a/demo/csharp/object_detection/object_detection.csproj +++ b/demo/csharp/object_detection/object_detection.csproj @@ -14,7 +14,7 @@ - + diff --git a/demo/csharp/ocr_detection/ocr_detection.csproj b/demo/csharp/ocr_detection/ocr_detection.csproj index 15b887841a..0c23d8d4cf 100644 --- a/demo/csharp/ocr_detection/ocr_detection.csproj +++ b/demo/csharp/ocr_detection/ocr_detection.csproj @@ -14,7 +14,7 @@ - + diff --git a/demo/csharp/ocr_recognition/ocr_recognition.csproj b/demo/csharp/ocr_recognition/ocr_recognition.csproj index 15b887841a..0c23d8d4cf 100644 --- a/demo/csharp/ocr_recognition/ocr_recognition.csproj +++ b/demo/csharp/ocr_recognition/ocr_recognition.csproj @@ -14,7 +14,7 @@ - + diff --git a/demo/csharp/pose_detection/pose_detection.csproj b/demo/csharp/pose_detection/pose_detection.csproj index 15b887841a..0c23d8d4cf 100644 --- a/demo/csharp/pose_detection/pose_detection.csproj +++ b/demo/csharp/pose_detection/pose_detection.csproj @@ -14,7 +14,7 @@ - + diff --git a/demo/tutorials/tutorials_1.ipynb b/demo/tutorials/tutorials_1.ipynb index c5644ae00e..bfa561e024 100755 --- a/demo/tutorials/tutorials_1.ipynb +++ b/demo/tutorials/tutorials_1.ipynb @@ -6,7 +6,7 @@ "id": "mAWHDEbr6Q2i" }, "source": [ - "[![Open in colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-mmlab/mmdeploy/tree/1.x/demo/tutorials_1.ipynb)\n", + "[![Open in colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/open-mmlab/mmdeploy/tree/main/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", diff --git a/docker/CPU/Dockerfile b/docker/CPU/Dockerfile index 87a068fd9e..7cf6d36f43 100644 --- a/docker/CPU/Dockerfile +++ b/docker/CPU/Dockerfile @@ -85,9 +85,9 @@ ENV PATH="/root/workspace/ncnn/build/tools/quantize/:${PATH}" ### install mmdeploy WORKDIR /root/workspace ARG VERSION -RUN git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git &&\ +RUN git clone -b main https://github.com/open-mmlab/mmdeploy.git &&\ cd mmdeploy &&\ - 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 &&\ + if [ -z ${VERSION} ] ; then echo "No MMDeploy version passed in, building on main" ; else git checkout tags/v${VERSION} -b tag_v${VERSION} ; fi &&\ git submodule update --init --recursive &&\ rm -rf build &&\ mkdir build &&\ @@ -114,4 +114,4 @@ RUN cd mmdeploy && rm -rf build/CM* && mkdir -p build && cd build && cmake .. \ -DMMDEPLOY_CODEBASES=all &&\ cmake --build . -- -j$(nproc) && cmake --install . &&\ export SPDLOG_LEVEL=warn &&\ - if [ -z ${VERSION} ] ; then echo "Built MMDeploy 1.x for CPU devices successfully!" ; else echo "Built MMDeploy version v${VERSION} for CPU devices successfully!" ; fi + if [ -z ${VERSION} ] ; then echo "Built MMDeploy main for CPU devices successfully!" ; else echo "Built MMDeploy version v${VERSION} for CPU devices successfully!" ; fi diff --git a/docker/GPU/Dockerfile b/docker/GPU/Dockerfile index e39b7d71bf..e552fd44ad 100644 --- a/docker/GPU/Dockerfile +++ b/docker/GPU/Dockerfile @@ -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 1.x https://github.com/open-mmlab/mmdeploy &&\ +RUN git clone -b main https://github.com/open-mmlab/mmdeploy &&\ cd mmdeploy &&\ - 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 &&\ + if [ -z ${VERSION} ] ; then echo "No MMDeploy version passed in, building on main" ; else git checkout tags/v${VERSION} -b tag_v${VERSION} ; fi &&\ git submodule update --init --recursive &&\ mkdir -p build &&\ cd build &&\ @@ -101,6 +101,6 @@ RUN cd /root/workspace/mmdeploy &&\ -DMMDEPLOY_CODEBASES=all &&\ make -j$(nproc) && make install &&\ export SPDLOG_LEVEL=warn &&\ - if [ -z ${VERSION} ] ; then echo "Built MMDeploy dev-1.x for GPU devices successfully!" ; else echo "Built MMDeploy version v${VERSION} for GPU devices successfully!" ; fi + if [ -z ${VERSION} ] ; then echo "Built MMDeploy for GPU devices successfully!" ; else echo "Built MMDeploy version v${VERSION} for GPU devices successfully!" ; fi ENV LD_LIBRARY_PATH="/root/workspace/mmdeploy/build/lib:${BACKUP_LD_LIBRARY_PATH}" diff --git a/docs/en/01-how-to-build/android.md b/docs/en/01-how-to-build/android.md index a153c34567..ab1081bbc6 100644 --- a/docs/en/01-how-to-build/android.md +++ b/docs/en/01-how-to-build/android.md @@ -97,7 +97,7 @@ make -j$(nproc) install OpenJDK It is necessary for building Java API.
- See Java API build for building tutorials. + See Java API build for building tutorials. diff --git a/docs/en/01-how-to-build/build_from_docker.md b/docs/en/01-how-to-build/build_from_docker.md index 816c2c77b1..22d9acbab7 100644 --- a/docs/en/01-how-to-build/build_from_docker.md +++ b/docs/en/01-how-to-build/build_from_docker.md @@ -51,7 +51,7 @@ docker run --gpus all -it mmdeploy:master-gpu As described [here](https://forums.developer.nvidia.com/t/cuda-error-the-provided-ptx-was-compiled-with-an-unsupported-toolchain/185754), update the GPU driver to the latest one for your GPU. -2. docker: Error response from daemon: could not select device driver "" with capabilities: \[gpu\]. +2. docker: Error response from daemon: could not select device driver "" with capabilities: [gpu]. ``` # Add the package repositories diff --git a/docs/en/01-how-to-build/build_from_source.md b/docs/en/01-how-to-build/build_from_source.md index 6fa742c7dd..2c272e3db7 100644 --- a/docs/en/01-how-to-build/build_from_source.md +++ b/docs/en/01-how-to-build/build_from_source.md @@ -3,7 +3,7 @@ ## Download ```shell -git clone -b 1.x git@github.com:open-mmlab/mmdeploy.git --recursive +git clone -b main git@github.com:open-mmlab/mmdeploy.git --recursive ``` Note: @@ -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 1.x https://github.com/open-mmlab/mmdeploy.git --recursive + git clone -b main https://github.com/open-mmlab/mmdeploy.git --recursive ``` ## Build diff --git a/docs/en/01-how-to-build/jetsons.md b/docs/en/01-how-to-build/jetsons.md index 03ce9db7b2..01a5b049e0 100644 --- a/docs/en/01-how-to-build/jetsons.md +++ b/docs/en/01-how-to-build/jetsons.md @@ -237,7 +237,7 @@ It takes about 15 minutes to install ppl.cv on a Jetson Nano. So, please be pati ## Install MMDeploy ```shell -git clone -b 1.x --recursive https://github.com/open-mmlab/mmdeploy.git +git clone -b main --recursive https://github.com/open-mmlab/mmdeploy.git cd mmdeploy export MMDEPLOY_DIR=$(pwd) ``` @@ -305,7 +305,7 @@ pip install -v -e . # or "python setup.py develop" 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/tree/1.x/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/main/configs/mmdet/detection/detection_tensorrt_dynamic-320x320-1344x1344.py) ```shell python ./tools/deploy.py \ diff --git a/docs/en/01-how-to-build/rockchip.md b/docs/en/01-how-to-build/rockchip.md index 3ecb645490..431b5d346d 100644 --- a/docs/en/01-how-to-build/rockchip.md +++ b/docs/en/01-how-to-build/rockchip.md @@ -140,7 +140,7 @@ 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/1.x/configs/mmdet/detection/detection_rknn-int8_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/main/configs/mmdet/detection/detection_rknn-int8_static-320x320.py): ```python # yolov3, yolox for rknn-toolkit and rknn-toolkit2 @@ -156,7 +156,7 @@ label: 65, score: 0.95 ]) ``` - RTMDet: you may paste the following partition configuration into [detection_rknn-int8_static-640x640.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/configs/mmdet/detection/detection_rknn-int8_static-640x640.py): + RTMDet: you may paste the following partition configuration into [detection_rknn-int8_static-640x640.py](https://github.com/open-mmlab/mmdeploy/blob/main/configs/mmdet/detection/detection_rknn-int8_static-640x640.py): ```python # rtmdet for rknn-toolkit and rknn-toolkit2 @@ -172,7 +172,7 @@ 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/dev-1.x/configs/mmdet/detection/detection_rknn-int8_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/blob/main/configs/mmdet/detection/detection_rknn-int8_static-320x320.py). Users with rknn-toolkit can directly use default config. ```python # retinanet, ssd for rknn-toolkit2 diff --git a/docs/en/02-how-to-run/prebuilt_package_windows.md b/docs/en/02-how-to-run/prebuilt_package_windows.md index 6952ad4b7b..5cb513f806 100644 --- a/docs/en/02-how-to-run/prebuilt_package_windows.md +++ b/docs/en/02-how-to-run/prebuilt_package_windows.md @@ -21,7 +21,7 @@ ______________________________________________________________________ -This tutorial takes `mmdeploy-1.0.0rc3-windows-amd64.zip` and `mmdeploy-1.0.0rc3-windows-amd64-cuda11.3.zip` as examples to show how to use the prebuilt packages. The former support onnxruntime cpu inference, the latter support onnxruntime-gpu and tensorrt inference. +This tutorial takes `mmdeploy-1.0.0-windows-amd64.zip` and `mmdeploy-1.0.0-windows-amd64-cuda11.3.zip` as examples to show how to use the prebuilt packages. The former support onnxruntime cpu inference, the latter support onnxruntime-gpu and tensorrt inference. The directory structure of the prebuilt package is as follows, where the `dist` folder is about model converter, and the `sdk` folder is related to model inference. @@ -48,7 +48,7 @@ In order to use the prebuilt package, you need to install some third-party depen 2. Clone the mmdeploy repository ```bash - git clone -b 1.x https://github.com/open-mmlab/mmdeploy.git + git clone -b main 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`. @@ -56,7 +56,7 @@ In order to use the prebuilt package, you need to install some third-party depen 3. Install mmclassification ```bash - git clone -b 1.x https://github.com/open-mmlab/mmclassification.git + git clone -b main https://github.com/open-mmlab/mmclassification.git cd mmclassification pip install -e . ``` @@ -81,8 +81,8 @@ In order to use `ONNX Runtime` backend, you should also do the following steps. 5. Install `mmdeploy` (Model Converter) and `mmdeploy_runtime` (SDK Python API). ```bash - pip install mmdeploy==1.0.0rc3 - pip install mmdeploy-runtime==1.0.0rc3 + pip install mmdeploy==1.0.0 + pip install mmdeploy-runtime==1.0.0 ``` :point_right: If you have installed it before, please uninstall it first. @@ -100,7 +100,7 @@ In order to use `ONNX Runtime` backend, you should also do the following steps. ![sys-path](https://user-images.githubusercontent.com/16019484/181463801-1d7814a8-b256-46e9-86f2-c08de0bc150b.png) :exclamation: Restart powershell to make the environment variables setting take effect. You can check whether the settings are in effect by `echo $env:PATH`. -8. Download SDK C/cpp Library mmdeploy-1.0.0rc3-windows-amd64.zip +8. Download SDK C/cpp Library mmdeploy-1.0.0-windows-amd64.zip ### TensorRT @@ -109,8 +109,8 @@ In order to use `TensorRT` backend, you should also do the following steps. 5. Install `mmdeploy` (Model Converter) and `mmdeploy_runtime` (SDK Python API). ```bash - pip install mmdeploy==1.0.0rc3 - pip install mmdeploy-runtime-gpu==1.0.0rc3 + pip install mmdeploy==1.0.0 + pip install mmdeploy-runtime-gpu==1.0.0 ``` :point_right: If you have installed it before, please uninstall it first. @@ -129,7 +129,7 @@ In order to use `TensorRT` backend, you should also do the following steps. 7. Install pycuda by `pip install pycuda` -8. Download SDK C/cpp Library mmdeploy-1.0.0rc3-windows-amd64-cuda11.3.zip +8. Download SDK C/cpp Library mmdeploy-1.0.0-windows-amd64-cuda11.3.zip ## Model Convert @@ -141,7 +141,7 @@ After preparation work, the structure of the current working directory should be ``` .. -|-- mmdeploy-1.0.0rc3-windows-amd64 +|-- mmdeploy-1.0.0-windows-amd64 |-- mmclassification |-- mmdeploy `-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth @@ -189,7 +189,7 @@ After installation of mmdeploy-tensorrt prebuilt package, the structure of the c ``` .. -|-- mmdeploy-1.0.0rc3-windows-amd64-cuda11.3 +|-- mmdeploy-1.0.0-windows-amd64-cuda11.3 |-- mmclassification |-- mmdeploy `-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth @@ -252,8 +252,8 @@ The structure of current working directory： ``` . -|-- mmdeploy-1.0.0rc3-windows-amd64-cuda11.1-tensorrt8.2.3.0 -|-- mmdeploy-1.0.0rc3-windows-amd64-onnxruntime1.8.1 +|-- mmdeploy-1.0.0-windows-amd64 +|-- mmdeploy-1.0.0-windows-amd64-cuda11.3 |-- mmclassification |-- mmdeploy |-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth @@ -324,7 +324,7 @@ The following describes how to use the SDK's C API for inference It is recommended to use `CMD` here. - Under `mmdeploy-1.0.0rc3-windows-amd64\\example\\cpp\\build\\Release` directory： + Under `mmdeploy-1.0.0-windows-amd64\\example\\cpp\\build\\Release` directory： ``` .\image_classification.exe cpu C:\workspace\work_dir\onnx\resnet\ C:\workspace\mmclassification\demo\demo.JPEG @@ -344,7 +344,7 @@ The following describes how to use the SDK's C API for inference It is recommended to use `CMD` here. - Under `mmdeploy-1.0.0rc3-windows-amd64-cuda11.3\\example\\cpp\\build\\Release` directory + Under `mmdeploy-1.0.0-windows-amd64-cuda11.3\\example\\cpp\\build\\Release` directory ``` .\image_classification.exe cuda C:\workspace\work_dir\trt\resnet C:\workspace\mmclassification\demo\demo.JPEG diff --git a/docs/en/02-how-to-run/useful_tools.md b/docs/en/02-how-to-run/useful_tools.md index ee69c51a2b..a402f2113d 100644 --- a/docs/en/02-how-to-run/useful_tools.md +++ b/docs/en/02-how-to-run/useful_tools.md @@ -83,7 +83,7 @@ python tools/onnx2pplnn.py \ - `onnx_path`: The path of the `ONNX` model to convert. - `output_path`: The converted `PPLNN` algorithm path in json format. - `device`: The device of the model during conversion. -- `opt-shapes`: Optimal shapes for PPLNN optimization. The shape of each tensor should be wrap with "\[\]" or "()" and the shapes of tensors should be separated by ",". +- `opt-shapes`: Optimal shapes for PPLNN optimization. The shape of each tensor should be wrap with "[]" or "()" and the shapes of tensors should be separated by ",". - `--log-level`: To set log level which in `'CRITICAL', 'FATAL', 'ERROR', 'WARN', 'WARNING', 'INFO', 'DEBUG', 'NOTSET'`. If not specified, it will be set to `INFO`. ## onnx2tensorrt diff --git a/docs/en/03-benchmark/benchmark.md b/docs/en/03-benchmark/benchmark.md index 18ef2faa3b..933b8519f4 100644 --- a/docs/en/03-benchmark/benchmark.md +++ b/docs/en/03-benchmark/benchmark.md @@ -2009,7 +2009,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../ fp32 - TSN + TSN Recognition Kinetics-400 top-1 @@ -2030,7 +2030,7 @@ Users can directly test the performance through [how_to_evaluate_a_model.md](../ - - SlowFast + SlowFast Recognition Kinetics-400 top-1 diff --git a/docs/en/04-supported-codebases/mmaction2.md b/docs/en/04-supported-codebases/mmaction2.md index 2ccf7c1ccf..f33ffdfe4d 100644 --- a/docs/en/04-supported-codebases/mmaction2.md +++ b/docs/en/04-supported-codebases/mmaction2.md @@ -21,7 +21,7 @@ ______________________________________________________________________ ### Install mmaction2 -Please follow the [installation guide](https://github.com/open-mmlab/mmaction2/tree/dev-1.x#installation) to install mmaction2. +Please follow the [installation guide](https://github.com/open-mmlab/mmaction2/tree/1.x#installation) to install mmaction2. ### Install mmdeploy @@ -29,7 +29,7 @@ There are several methods to install mmdeploy, among which you can choose an app **Method I：** Install precompiled package -You can download the latest release package from [here](https://github.com/open-mmlab/mmdeploy/releases) +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **Method II：** Build using scripts @@ -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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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 @@ -178,13 +178,13 @@ 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/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/main/demo). > MMAction2 only API of c, c++ and python for now. ## Supported models -| Model | TorchScript | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO | -| :-------------------------------------------------------------------------------------------- | :---------: | :----------: | :------: | :--: | :---: | :------: | -| [TSN](https://github.com/open-mmlab/mmaction2/tree/dev-1.x/configs/recognition/tsn) | N | Y | Y | N | N | N | -| [SlowFast](https://github.com/open-mmlab/mmaction2/tree/dev-1.x/configs/recognition/slowfast) | N | Y | Y | N | N | N | +| Model | TorchScript | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO | +| :---------------------------------------------------------------------------------------- | :---------: | :----------: | :------: | :--: | :---: | :------: | +| [TSN](https://github.com/open-mmlab/mmaction2/tree/1.x/configs/recognition/tsn) | N | Y | Y | N | N | N | +| [SlowFast](https://github.com/open-mmlab/mmaction2/tree/1.x/configs/recognition/slowfast) | N | Y | Y | N | N | N | diff --git a/docs/en/04-supported-codebases/mmcls.md b/docs/en/04-supported-codebases/mmcls.md index 1c39f6ba58..847ea33c57 100644 --- a/docs/en/04-supported-codebases/mmcls.md +++ b/docs/en/04-supported-codebases/mmcls.md @@ -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 1.x branch. +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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/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/main/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" diff --git a/docs/en/04-supported-codebases/mmdet.md b/docs/en/04-supported-codebases/mmdet.md index 92d822e2ea..5d43a77f48 100644 --- a/docs/en/04-supported-codebases/mmdet.md +++ b/docs/en/04-supported-codebases/mmdet.md @@ -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 1.x branch. +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/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/main/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/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/main/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/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/main/demo). ## Supported models diff --git a/docs/en/04-supported-codebases/mmedit.md b/docs/en/04-supported-codebases/mmedit.md index f70ec726c2..298cbf03e3 100644 --- a/docs/en/04-supported-codebases/mmedit.md +++ b/docs/en/04-supported-codebases/mmedit.md @@ -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 1.x branch. +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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 @@ -91,7 +91,7 @@ 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/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/main/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" @@ -180,7 +180,7 @@ 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/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/main/demo). ## Supported models diff --git a/docs/en/04-supported-codebases/mmocr.md b/docs/en/04-supported-codebases/mmocr.md index 444abc91f9..447aae7fee 100644 --- a/docs/en/04-supported-codebases/mmocr.md +++ b/docs/en/04-supported-codebases/mmocr.md @@ -24,7 +24,7 @@ ______________________________________________________________________ ### Install mmocr -Please follow the [installation guide](https://mmocr.readthedocs.io/en/dev-1.x/get_started/install.html) to install mmocr. +Please follow the [installation guide](https://mmocr.readthedocs.io/en/latest/install.html) to install mmocr. ### Install mmdeploy @@ -32,7 +32,7 @@ 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 1.x branch. +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **Method II:** Build using scripts @@ -40,7 +40,7 @@ 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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main https://github.com/open-mmlab/mmdeploy.git cd mmdeploy python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc) export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH @@ -53,9 +53,9 @@ 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/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). +You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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 @@ -113,7 +113,7 @@ 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/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/main/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" @@ -230,7 +230,7 @@ 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/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/main/demo). ## Supported models diff --git a/docs/en/04-supported-codebases/mmpose.md b/docs/en/04-supported-codebases/mmpose.md index 350e45d809..98fd292531 100644 --- a/docs/en/04-supported-codebases/mmpose.md +++ b/docs/en/04-supported-codebases/mmpose.md @@ -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 1.x branch. +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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/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/main/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" diff --git a/docs/en/04-supported-codebases/mmrotate.md b/docs/en/04-supported-codebases/mmrotate.md index d228582910..712c727995 100644 --- a/docs/en/04-supported-codebases/mmrotate.md +++ b/docs/en/04-supported-codebases/mmrotate.md @@ -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. +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **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 main https://github.com/open-mmlab/mmdeploy.git cd mmdeploy python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc) export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH @@ -53,7 +53,7 @@ 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 mmrotate 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/blob/main/tools/deploy.py) to convert mmrotate models to the specified backend models. Its detailed usage can be learned from [here](https://github.com/open-mmlab/mmdeploy/blob/main/docs/en/02-how-to-run/convert_model.md#usage). The command below shows an example about converting `rotated-faster-rcnn` 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/mmrotate) of all supported backends for mmrotate. 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/main/configs/mmrotate) of all supported backends for mmrotate. The config filename pattern is: ``` rotated_detection-{backend}-{precision}_{static | dynamic}_{shape}.py @@ -87,7 +87,7 @@ rotated_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 `rotated-faster-rcnn` to other backend models by changing the deployment config file `rotated-detection_onnxruntime_dynamic` to [others](https://github.com/open-mmlab/mmdeploy/tree/dev-1.x/configs/mmrotate), e.g., converting to tensorrt-fp16 model by `rotated-detection_tensorrt-fp16_dynamic-320x320-1024x1024.py`. +Therefore, in the above example, you can also convert `rotated-faster-rcnn` to other backend models by changing the deployment config file `rotated-detection_onnxruntime_dynamic` to [others](https://github.com/open-mmlab/mmdeploy/tree/main/configs/mmrotate), e.g., converting to tensorrt-fp16 model by `rotated-detection_tensorrt-fp16_dynamic-320x320-1024x1024.py`. ```{tip} When converting mmrotate models to tensorrt models, --device should be set to "cuda" @@ -172,7 +172,7 @@ detector = RotatedDetector(model_path='./mmdeploy_models/mmrotate/ort', device_n det = detector(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/main/demo). ## Supported models @@ -182,4 +182,4 @@ Besides python API, mmdeploy SDK also provides other FFI (Foreign Function Inter | [Rotated FasterRCNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_faster_rcnn) | Y | Y | | [Oriented R-CNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/oriented_rcnn) | Y | Y | | [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/gliding_vertex) | Y | Y | -| [RTMDET-R](https://github.com/open-mmlab/mmrotate/blob/dev-1.x/configs/rotated_rtmdet) | Y | Y | +| [RTMDET-R](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_rtmdet) | Y | Y | diff --git a/docs/en/04-supported-codebases/mmseg.md b/docs/en/04-supported-codebases/mmseg.md index 003cde7067..3faeb5061e 100644 --- a/docs/en/04-supported-codebases/mmseg.md +++ b/docs/en/04-supported-codebases/mmseg.md @@ -20,7 +20,7 @@ ______________________________________________________________________ ### Install mmseg -Please follow the [installation guide](https://mmsegmentation.readthedocs.io/en/1.x/get_started.html) to install mmseg. +Please follow the [installation guide](https://mmsegmentation.readthedocs.io/en/latest/get_started.html) to install mmseg. ### Install mmdeploy @@ -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 1.x branch. +You can refer to [get_started](https://mmdeploy.readthedocs.io/en/latest/get_started.html#installation) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +You can use [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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/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/main/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/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/main/demo). ## Supported models diff --git a/docs/en/05-supported-backends/rknn.md b/docs/en/05-supported-backends/rknn.md index 28cb10e948..deacbf607a 100644 --- a/docs/en/05-supported-backends/rknn.md +++ b/docs/en/05-supported-backends/rknn.md @@ -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/tree/1.x/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/main/configs/_base_/backends/rknn.py). - target_platform other than default - quantization settings diff --git a/docs/en/06-custom-ops/tensorrt.md b/docs/en/06-custom-ops/tensorrt.md index f00f8c7f4c..b2a2af5b12 100644 --- a/docs/en/06-custom-ops/tensorrt.md +++ b/docs/en/06-custom-ops/tensorrt.md @@ -308,7 +308,7 @@ Perform RoIAlign on output feature, used in bbox_head of most two-stage detector #### Description -ScatterND takes three inputs `data` tensor of rank r >= 1, `indices` tensor of rank q >= 1, and `updates` tensor of rank q + r - indices.shape\[-1\] - 1. The output of the operation is produced by creating a copy of the input `data`, and then updating its value to values specified by updates at specific index positions specified by `indices`. Its output shape is the same as the shape of `data`. Note that `indices` should not have duplicate entries. That is, two or more updates for the same index-location is not supported. +ScatterND takes three inputs `data` tensor of rank r >= 1, `indices` tensor of rank q >= 1, and `updates` tensor of rank q + r - indices.shape[-1] - 1. The output of the operation is produced by creating a copy of the input `data`, and then updating its value to values specified by updates at specific index positions specified by `indices`. Its output shape is the same as the shape of `data`. Note that `indices` should not have duplicate entries. That is, two or more updates for the same index-location is not supported. The `output` is calculated via the following equation: diff --git a/docs/en/conf.py b/docs/en/conf.py index c130810b74..6dcaeb0c18 100644 --- a/docs/en/conf.py +++ b/docs/en/conf.py @@ -105,7 +105,7 @@ # documentation. # html_theme_options = { - 'logo_url': 'https://mmdeploy.readthedocs.io/en/1.x/', + 'logo_url': 'https://mmdeploy.readthedocs.io/en/latest/', 'menu': [{ 'name': 'GitHub', 'url': 'https://github.com/open-mmlab/mmdeploy' diff --git a/docs/en/faq.md b/docs/en/faq.md index 1eea9b08e3..d8143fa569 100644 --- a/docs/en/faq.md +++ b/docs/en/faq.md @@ -6,7 +6,7 @@ Fp16 mode requires a device with full-rate fp16 support. -- "error: parameter check failed at: engine.cpp::setBindingDimensions::1046, condition: profileMinDims.d\[i\] \<= dimensions.d\[i\]" +- "error: parameter check failed at: engine.cpp::setBindingDimensions::1046, condition: profileMinDims.d[i] \<= dimensions.d[i]" When building an `ICudaEngine` from an `INetworkDefinition` that has dynamically resizable inputs, users need to specify at least one optimization profile. Which can be set in deploy config: @@ -25,7 +25,7 @@ The input tensor shape should be limited between `min_shape` and `max_shape`. -- "error: \[TensorRT\] INTERNAL ERROR: Assertion failed: cublasStatus == CUBLAS_STATUS_SUCCESS" +- "error: [TensorRT] INTERNAL ERROR: Assertion failed: cublasStatus == CUBLAS_STATUS_SUCCESS" TRT 7.2.1 switches to use cuBLASLt (previously it was cuBLAS). cuBLASLt is the defaulted choice for SM version >= 7.0. You may need CUDA-10.2 Patch 1 (Released Aug 26, 2020) to resolve some cuBLASLt issues. Another option is to use the new TacticSource API and disable cuBLASLt tactics if you dont want to upgrade. diff --git a/docs/en/get_started.md b/docs/en/get_started.md index 07b0006931..9fce872ea1 100644 --- a/docs/en/get_started.md +++ b/docs/en/get_started.md @@ -118,14 +118,14 @@ Take the latest precompiled package as example, you can install it as follows: ```shell # 1. install MMDeploy model converter -pip install mmdeploy==1.0.0rc3 +pip install mmdeploy==1.0.0 # 2. install MMDeploy sdk inference # you can install one to install according whether you need gpu inference # 2.1 support onnxruntime -pip install mmdeploy-runtime==1.0.0rc3 +pip install mmdeploy-runtime==1.0.0 # 2.2 support onnxruntime-gpu, tensorrt -pip install mmdeploy-runtime-gpu==1.0.0rc3 +pip install mmdeploy-runtime-gpu==1.0.0 # 3. install inference engine # 3.1 install TensorRT @@ -170,7 +170,7 @@ Based on the above settings, we provide an example to convert the Faster R-CNN i ```shell # clone mmdeploy to get the deployment config. `--recursive` is not necessary -git clone -b dev-1.x https://github.com/open-mmlab/mmdeploy.git +git clone -b main https://github.com/open-mmlab/mmdeploy.git # clone mmdetection repo. We have to use the config file to build PyTorch nn module git clone -b 3.x https://github.com/open-mmlab/mmdetection.git @@ -230,9 +230,9 @@ result = inference_model( You can directly run MMDeploy demo programs in the precompiled package to get inference results. ```shell -wget https://github.com/open-mmlab/mmdeploy/releases/download/v1.0.0rc3/mmdeploy-1.0.0rc3-linux-x86_64-cuda11.3.tar.gz -tar xf mmdeploy-1.0.0rc3-linux-x86_64-cuda11.3 -cd mmdeploy-1.0.0rc3-linux-x86_64-cuda11.3 +wget https://github.com/open-mmlab/mmdeploy/releases/download/v1.0.0/mmdeploy-1.0.0-linux-x86_64-cuda11.3.tar.gz +tar xf mmdeploy-1.0.0-linux-x86_64-cuda11.3 +cd mmdeploy-1.0.0-linux-x86_64-cuda11.3 # run python demo python example/python/object_detection.py cuda ../mmdeploy_model/faster-rcnn ../mmdetection/demo/demo.jpg # run C/C++ demo @@ -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/1.x/demo/python). +You can find more examples from [here](https://github.com/open-mmlab/mmdeploy/tree/main/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/1.x/demo/csrc/cpp). +For more SDK C++ API usages, please read these [samples](https://github.com/open-mmlab/mmdeploy/tree/main/demo/csrc/cpp). -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. +For the rest C, C# and Java API usages, please read [C demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo/csrc/c), [C# demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo/csharp) and [Java demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo/java) respectively. We'll talk about them more in our next release. #### Accelerate preprocessing（Experimental） diff --git a/docs/en/switch_language.md b/docs/en/switch_language.md index 03bf778b72..1b5df42929 100644 --- a/docs/en/switch_language.md +++ b/docs/en/switch_language.md @@ -1,3 +1,3 @@ -## English +## English -## 简体中文 +## 简体中文 diff --git a/docs/zh_cn/01-how-to-build/build_from_docker.md b/docs/zh_cn/01-how-to-build/build_from_docker.md index 7cc44072f7..f98a1a6550 100644 --- a/docs/zh_cn/01-how-to-build/build_from_docker.md +++ b/docs/zh_cn/01-how-to-build/build_from_docker.md @@ -51,7 +51,7 @@ docker run --gpus all -it mmdeploy:master-gpu 如 [这里](https://forums.developer.nvidia.com/t/cuda-error-the-provided-ptx-was-compiled-with-an-unsupported-toolchain/185754)所说，更新 GPU 的驱动到您的GPU能使用的最新版本。 -2. docker: Error response from daemon: could not select device driver "" with capabilities: \[gpu\]. +2. docker: Error response from daemon: could not select device driver "" with capabilities: [gpu]. ``` # Add the package repositories diff --git a/docs/zh_cn/01-how-to-build/rockchip.md b/docs/zh_cn/01-how-to-build/rockchip.md index 4a371c543a..109ac2d5d8 100644 --- a/docs/zh_cn/01-how-to-build/rockchip.md +++ b/docs/zh_cn/01-how-to-build/rockchip.md @@ -105,7 +105,7 @@ 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/1.x/configs/mmdet/detection/detection_rknn-int8_static-320x320.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/main/configs/mmdet/detection/detection_rknn-int8_static-320x320.py) ```python # yolov3, yolox for rknn-toolkit and rknn-toolkit2 @@ -136,7 +136,7 @@ python tools/deploy.py \ - RTMDet -将下面的模型拆分配置写入到 [detection_rknn-int8_static-640x640.py](https://github.com/open-mmlab/mmdeploy/blob/dev-1.x/configs/mmdet/detection/detection_rknn-int8_static-640x640.py) +将下面的模型拆分配置写入到 [detection_rknn-int8_static-640x640.py](https://github.com/open-mmlab/mmdeploy/blob/main/configs/mmdet/detection/detection_rknn-int8_static-640x640.py) ```python # rtmdet for rknn-toolkit and rknn-toolkit2 @@ -154,7 +154,7 @@ partition_config = dict( - 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/1.x/configs/mmdet/detection/detection_rknn-int8_static-320x320.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/main/configs/mmdet/detection/detection_rknn-int8_static-320x320.py)。使用 rknn-toolkit 的用户则不用。 ```python # retinanet, ssd and fsaf for rknn-toolkit2 diff --git a/docs/zh_cn/02-how-to-run/prebuilt_package_windows.md b/docs/zh_cn/02-how-to-run/prebuilt_package_windows.md index 134bc260b7..c98848b176 100644 --- a/docs/zh_cn/02-how-to-run/prebuilt_package_windows.md +++ b/docs/zh_cn/02-how-to-run/prebuilt_package_windows.md @@ -23,7 +23,7 @@ ______________________________________________________________________ 目前，`MMDeploy`在`Windows`平台下提供`cpu`以及`cuda`两种Device的预编译包，其中`cpu`版支持使用onnxruntime cpu进行推理，`cuda`版支持使用onnxruntime-gpu以及tensorrt进行推理，可以从[Releases](https://github.com/open-mmlab/mmdeploy/releases)获取。。 -本篇教程以`mmdeploy-1.0.0rc3-windows-amd64.zip`和`mmdeploy-1.0.0rc3-windows-amd64-cuda11.3.zip`为例，展示预编译包的使用方法。 +本篇教程以`mmdeploy-1.0.0-windows-amd64.zip`和`mmdeploy-1.0.0-windows-amd64-cuda11.3.zip`为例，展示预编译包的使用方法。 为了方便使用者快速上手，本教程以分类模型(mmclassification)为例，展示两种预编译包的使用方法。 @@ -89,8 +89,8 @@ ______________________________________________________________________ 5. 安装`mmdeploy`（模型转换）以及`mmdeploy_runtime`（模型推理Python API）的预编译包 ```bash - pip install mmdeploy==1.0.0rc3 - pip install mmdeploy-runtime==1.0.0rc3 + pip install mmdeploy==1.0.0 + pip install mmdeploy-runtime==1.0.0 ``` :point_right: 如果之前安装过，需要先卸载后再安装。 @@ -108,7 +108,7 @@ ______________________________________________________________________ ![sys-path](https://user-images.githubusercontent.com/16019484/181463801-1d7814a8-b256-46e9-86f2-c08de0bc150b.png) :exclamation: 重启powershell让环境变量生效，可以通过 echo $env:PATH 来检查是否设置成功。 -8. 下载 SDK C/cpp Library mmdeploy-1.0.0rc3-windows-amd64.zip +8. 下载 SDK C/cpp Library mmdeploy-1.0.0-windows-amd64.zip ### TensorRT @@ -117,8 +117,8 @@ ______________________________________________________________________ 5. 安装`mmdeploy`（模型转换）以及`mmdeploy_runtime`（模型推理Python API）的预编译包 ```bash - pip install mmdeploy==1.0.0rc3 - pip install mmdeploy-runtime-gpu==1.0.0rc3 + pip install mmdeploy==1.0.0 + pip install mmdeploy-runtime-gpu==1.0.0 ``` :point_right: 如果之前安装过，需要先卸载后再安装 @@ -137,7 +137,7 @@ ______________________________________________________________________ 7. 安装pycuda `pip install pycuda` -8. 下载 SDK C/cpp Library mmdeploy-1.0.0rc3-windows-amd64-cuda11.3.zip +8. 下载 SDK C/cpp Library mmdeploy-1.0.0-windows-amd64-cuda11.3.zip ## 模型转换 @@ -149,7 +149,7 @@ ______________________________________________________________________ ``` .. -|-- mmdeploy-1.0.0rc3-windows-amd64 +|-- mmdeploy-1.0.0-windows-amd64 |-- mmclassification |-- mmdeploy `-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth @@ -197,7 +197,7 @@ export2SDK(deploy_cfg, model_cfg, work_dir, pth=model_checkpoint, device=device) ``` .. -|-- mmdeploy-1.0.0rc3-windows-amd64-cuda11.3 +|-- mmdeploy-1.0.0-windows-amd64-cuda11.3 |-- mmclassification |-- mmdeploy `-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth @@ -260,8 +260,8 @@ export2SDK(deploy_cfg, model_cfg, work_dir, pth=model_checkpoint, device=device) ``` . -|-- mmdeploy-1.0.0rc3-windows-amd64-cuda11.1-tensorrt8.2.3.0 -|-- mmdeploy-1.0.0rc3-windows-amd64-onnxruntime1.8.1 +|-- mmdeploy-1.0.0-windows-amd64 +|-- mmdeploy-1.0.0-windows-amd64-cuda11.3 |-- mmclassification |-- mmdeploy |-- resnet18_8xb32_in1k_20210831-fbbb1da6.pth @@ -340,7 +340,7 @@ python .\mmdeploy\demo\python\image_classification.py cpu .\work_dir\onnx\resnet 这里建议使用cmd，这样如果exe运行时如果找不到相关的dll的话会有弹窗 - 在mmdeploy-1.0.0rc3-windows-amd64-onnxruntime1.8.1\\example\\cpp\\build\\Release目录下： + 在mmdeploy-1.0.0-windows-amd64\\example\\cpp\\build\\Release目录下： ``` .\image_classification.exe cpu C:\workspace\work_dir\onnx\resnet\ C:\workspace\mmclassification\demo\demo.JPEG @@ -360,7 +360,7 @@ python .\mmdeploy\demo\python\image_classification.py cpu .\work_dir\onnx\resnet 这里建议使用cmd，这样如果exe运行时如果找不到相关的dll的话会有弹窗 - 在mmdeploy-1.0.0rc3-windows-amd64-cuda11.1-tensorrt8.2.3.0\\example\\cpp\\build\\Release目录下： + 在mmdeploy-1.0.0-windows-amd64-cuda11.3\\example\\cpp\\build\\Release目录下： ``` .\image_classification.exe cuda C:\workspace\work_dir\trt\resnet C:\workspace\mmclassification\demo\demo.JPEG diff --git a/docs/zh_cn/02-how-to-run/useful_tools.md b/docs/zh_cn/02-how-to-run/useful_tools.md index bbd823c697..2f08cefa9f 100644 --- a/docs/zh_cn/02-how-to-run/useful_tools.md +++ b/docs/zh_cn/02-how-to-run/useful_tools.md @@ -83,7 +83,7 @@ python tools/onnx2pplnn.py \ - `onnx_path`: The path of the `ONNX` model to convert. - `output_path`: The converted `PPLNN` algorithm path in json format. - `device`: The device of the model during conversion. -- `opt-shapes`: Optimal shapes for PPLNN optimization. The shape of each tensor should be wrap with "\[\]" or "()" and the shapes of tensors should be separated by ",". +- `opt-shapes`: Optimal shapes for PPLNN optimization. The shape of each tensor should be wrap with "[]" or "()" and the shapes of tensors should be separated by ",". - `--log-level`: To set log level which in `'CRITICAL', 'FATAL', 'ERROR', 'WARN', 'WARNING', 'INFO', 'DEBUG', 'NOTSET'`. If not specified, it will be set to `INFO`. ## onnx2tensorrt diff --git a/docs/zh_cn/03-benchmark/benchmark.md b/docs/zh_cn/03-benchmark/benchmark.md index 1e1a0c5d10..1a473cff9f 100644 --- a/docs/zh_cn/03-benchmark/benchmark.md +++ b/docs/zh_cn/03-benchmark/benchmark.md @@ -2004,7 +2004,7 @@ GPU: ncnn, TensorRT, PPLNN fp32 - TSN + TSN Recognition Kinetics-400 top-1 @@ -2025,7 +2025,7 @@ GPU: ncnn, TensorRT, PPLNN - - SlowFast + SlowFast Recognition Kinetics-400 top-1 diff --git a/docs/zh_cn/04-supported-codebases/mmaction2.md b/docs/zh_cn/04-supported-codebases/mmaction2.md index af299a0b7e..f1a42307e7 100644 --- a/docs/zh_cn/04-supported-codebases/mmaction2.md +++ b/docs/zh_cn/04-supported-codebases/mmaction2.md @@ -21,7 +21,7 @@ ______________________________________________________________________ ### 安装 mmaction2 -请参考[官网安装指南](https://github.com/open-mmlab/mmaction2/tree/dev-1.x#installation). +请参考[官网安装指南](https://github.com/open-mmlab/mmaction2/tree/1.x#installation). ### 安装 mmdeploy @@ -29,7 +29,7 @@ mmdeploy 有以下几种安装方式: **方式一：** 安装预编译包 -通过此[链接](https://github.com/open-mmlab/mmdeploy/releases)获取最新的预编译包 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **方式二：** 一键式脚本安装 @@ -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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/configs/mmaction)。 文件的命名模式是： ``` @@ -181,13 +181,13 @@ 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/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/main/demo)学习其他语言接口的使用方法。 > mmaction2 的 C#，Java接口待开发 ## 模型支持列表 -| Model | TorchScript | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO | -| :-------------------------------------------------------------------------------------------- | :---------: | :----------: | :------: | :--: | :---: | :------: | -| [TSN](https://github.com/open-mmlab/mmaction2/tree/dev-1.x/configs/recognition/tsn) | N | Y | Y | N | N | N | -| [SlowFast](https://github.com/open-mmlab/mmaction2/tree/dev-1.x/configs/recognition/slowfast) | N | Y | Y | N | N | N | +| Model | TorchScript | ONNX Runtime | TensorRT | ncnn | PPLNN | OpenVINO | +| :---------------------------------------------------------------------------------------- | :---------: | :----------: | :------: | :--: | :---: | :------: | +| [TSN](https://github.com/open-mmlab/mmaction2/tree/1.x/configs/recognition/tsn) | N | Y | Y | N | N | N | +| [SlowFast](https://github.com/open-mmlab/mmaction2/tree/1.x/configs/recognition/slowfast) | N | Y | Y | N | N | N | diff --git a/docs/zh_cn/04-supported-codebases/mmcls.md b/docs/zh_cn/04-supported-codebases/mmcls.md index 5ed7bfe6c8..ef906a178e 100644 --- a/docs/zh_cn/04-supported-codebases/mmcls.md +++ b/docs/zh_cn/04-supported-codebases/mmcls.md @@ -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 1.x，再补充 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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/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/main/demo)学习其他语言接口的使用方法。 ## 模型支持列表 diff --git a/docs/zh_cn/04-supported-codebases/mmdet.md b/docs/zh_cn/04-supported-codebases/mmdet.md index a1af645a98..c7b412c28d 100644 --- a/docs/zh_cn/04-supported-codebases/mmdet.md +++ b/docs/zh_cn/04-supported-codebases/mmdet.md @@ -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 1.x，再补充 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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/tree/1.x/docs/en/02-how-to-run/convert_model.md#usage). +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/main/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/tree/main/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。 @@ -69,7 +69,7 @@ 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/1.x/configs/mmdet)。 +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/main/configs/mmdet)。 文件的命名模式是： ``` @@ -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/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/main/demo)学习其他语言接口的使用方法。 ## 模型支持列表 diff --git a/docs/zh_cn/04-supported-codebases/mmedit.md b/docs/zh_cn/04-supported-codebases/mmedit.md index 382eb86f6d..58f4fb206f 100644 --- a/docs/zh_cn/04-supported-codebases/mmedit.md +++ b/docs/zh_cn/04-supported-codebases/mmedit.md @@ -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 1.x，再补充 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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/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/main/demo)学习其他语言接口的使用方法。 ## 模型支持列表 diff --git a/docs/zh_cn/04-supported-codebases/mmocr.md b/docs/zh_cn/04-supported-codebases/mmocr.md index 1e7948b321..dc6762131c 100644 --- a/docs/zh_cn/04-supported-codebases/mmocr.md +++ b/docs/zh_cn/04-supported-codebases/mmocr.md @@ -24,7 +24,7 @@ ______________________________________________________________________ ### 安装 mmocr -请参考[官网安装指南](https://mmocr.readthedocs.io/en/dev-1.x/get_started/install.html). +请参考[官网安装指南](https://mmocr.readthedocs.io/en/latest/install.html). ### 安装 mmdeploy @@ -32,7 +32,7 @@ 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 1.x，再补充 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **方式二：** 一键式脚本安装 @@ -40,7 +40,7 @@ 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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main https://github.com/open-mmlab/mmdeploy.git cd mmdeploy python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc) export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH @@ -53,10 +53,10 @@ export LD_LIBRARY_PATH=$(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/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). +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/configs/mmocr)。 文件的命名模式是： ``` @@ -234,7 +234,7 @@ 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/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/main/demo)学习其他语言接口的使用方法。 ## 模型支持列表 diff --git a/docs/zh_cn/04-supported-codebases/mmpose.md b/docs/zh_cn/04-supported-codebases/mmpose.md index ce5ea46574..cdddec6bac 100644 --- a/docs/zh_cn/04-supported-codebases/mmpose.md +++ b/docs/zh_cn/04-supported-codebases/mmpose.md @@ -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 1.x，再补充 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/configs/mmpose)。 文件的命名模式是： ``` diff --git a/docs/zh_cn/04-supported-codebases/mmrotate.md b/docs/zh_cn/04-supported-codebases/mmrotate.md index 8191ac4333..1100fed710 100644 --- a/docs/zh_cn/04-supported-codebases/mmrotate.md +++ b/docs/zh_cn/04-supported-codebases/mmrotate.md @@ -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 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **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 main https://github.com/open-mmlab/mmdeploy.git cd mmdeploy python3 tools/scripts/build_ubuntu_x64_ort.py $(nproc) export PYTHONPATH=$(pwd)/build/lib:$PYTHONPATH @@ -52,7 +52,7 @@ export LD_LIBRARY_PATH=$(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/dev-1.x/tools/deploy.py) 把 mmrotate 模型一键式转换为推理后端模型。 +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/blob/main/tools/deploy.py) 把 mmrotate 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). 以下，我们将演示如何把 `rotated-faster-rcnn` 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/mmrotate)。 +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/main/configs/mmrotate)。 文件的命名模式是： ``` @@ -176,7 +176,7 @@ det = detector(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/main/demo)学习其他语言接口的使用方法。 ## 模型支持列表 @@ -186,4 +186,4 @@ det = detector(img) | [Rotated FasterRCNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_faster_rcnn) | Y | Y | | [Oriented R-CNN](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/oriented_rcnn) | Y | Y | | [Gliding Vertex](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/gliding_vertex) | Y | Y | -| [RTMDET-R](https://github.com/open-mmlab/mmrotate/blob/dev-1.x/configs/rotated_rtmdet) | Y | Y | +| [RTMDET-R](https://github.com/open-mmlab/mmrotate/blob/1.x/configs/rotated_rtmdet) | Y | Y | diff --git a/docs/zh_cn/04-supported-codebases/mmseg.md b/docs/zh_cn/04-supported-codebases/mmseg.md index 2292259300..290e5c7723 100644 --- a/docs/zh_cn/04-supported-codebases/mmseg.md +++ b/docs/zh_cn/04-supported-codebases/mmseg.md @@ -20,7 +20,7 @@ ______________________________________________________________________ ### 安装 mmseg -请参考[官网安装指南](https://mmsegmentation.readthedocs.io/en/1.x/get_started.html)。 +请参考[官网安装指南](https://mmsegmentation.readthedocs.io/en/latest/get_started.html)。 ### 安装 mmdeploy @@ -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 1.x，再补充 +请参考[安装概述](https://mmdeploy.readthedocs.io/zh_CN/latest/get_started.html#mmdeploy) **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 1.x https://github.com/open-mmlab/mmdeploy.git +git clone --recursive -b main 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/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). +你可以使用 [tools/deploy.py](https://github.com/open-mmlab/mmdeploy/tree/main/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/main/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/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/main/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/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/main/demo)学习其他语言接口的使用方法。 ## 模型支持列表 diff --git a/docs/zh_cn/05-supported-backends/rknn.md b/docs/zh_cn/05-supported-backends/rknn.md index 165029e5b9..159d871866 100644 --- a/docs/zh_cn/05-supported-backends/rknn.md +++ b/docs/zh_cn/05-supported-backends/rknn.md @@ -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/tree/1.x/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/main/configs/_base_/backends/rknn.py). - target_platform ！= default - quantization settings diff --git a/docs/zh_cn/06-custom-ops/tensorrt.md b/docs/zh_cn/06-custom-ops/tensorrt.md index e11b837127..75f353dcb2 100644 --- a/docs/zh_cn/06-custom-ops/tensorrt.md +++ b/docs/zh_cn/06-custom-ops/tensorrt.md @@ -302,7 +302,7 @@ Perform RoIAlign on output feature, used in bbox_head of most two-stage detector #### Description -ScatterND takes three inputs `data` tensor of rank r >= 1, `indices` tensor of rank q >= 1, and `updates` tensor of rank q + r - indices.shape\[-1\] - 1. The output of the operation is produced by creating a copy of the input `data`, and then updating its value to values specified by updates at specific index positions specified by `indices`. Its output shape is the same as the shape of `data`. Note that `indices` should not have duplicate entries. That is, two or more updates for the same index-location is not supported. +ScatterND takes three inputs `data` tensor of rank r >= 1, `indices` tensor of rank q >= 1, and `updates` tensor of rank q + r - indices.shape[-1] - 1. The output of the operation is produced by creating a copy of the input `data`, and then updating its value to values specified by updates at specific index positions specified by `indices`. Its output shape is the same as the shape of `data`. Note that `indices` should not have duplicate entries. That is, two or more updates for the same index-location is not supported. The `output` is calculated via the following equation: diff --git a/docs/zh_cn/conf.py b/docs/zh_cn/conf.py index fd8ab6b95f..c060165f55 100644 --- a/docs/zh_cn/conf.py +++ b/docs/zh_cn/conf.py @@ -106,7 +106,7 @@ # documentation. # html_theme_options = { - 'logo_url': 'https://mmdeploy.readthedocs.io/zh_CN/1.x/', + 'logo_url': 'https://mmdeploy.readthedocs.io/zh_CN/latest/', 'menu': [{ 'name': 'GitHub', 'url': 'https://github.com/open-mmlab/mmdeploy' diff --git a/docs/zh_cn/faq.md b/docs/zh_cn/faq.md index 67615b1d14..92e6cb4ef6 100644 --- a/docs/zh_cn/faq.md +++ b/docs/zh_cn/faq.md @@ -6,7 +6,7 @@ Fp16 mode requires a device with full-rate fp16 support. -- "error: parameter check failed at: engine.cpp::setBindingDimensions::1046, condition: profileMinDims.d\[i\] \<= dimensions.d\[i\]" +- "error: parameter check failed at: engine.cpp::setBindingDimensions::1046, condition: profileMinDims.d[i] \<= dimensions.d[i]" When building an `ICudaEngine` from an `INetworkDefinition` that has dynamically resizable inputs, users need to specify at least one optimization profile. Which can be set in deploy config: @@ -25,7 +25,7 @@ The input tensor shape should be limited between `min_shape` and `max_shape`. -- "error: \[TensorRT\] INTERNAL ERROR: Assertion failed: cublasStatus == CUBLAS_STATUS_SUCCESS" +- "error: [TensorRT] INTERNAL ERROR: Assertion failed: cublasStatus == CUBLAS_STATUS_SUCCESS" TRT 7.2.1 switches to use cuBLASLt (previously it was cuBLAS). cuBLASLt is the defaulted choice for SM version >= 7.0. You may need CUDA-10.2 Patch 1 (Released Aug 26, 2020) to resolve some cuBLASLt issues. Another option is to use the new TacticSource API and disable cuBLASLt tactics if you dont want to upgrade. diff --git a/docs/zh_cn/get_started.md b/docs/zh_cn/get_started.md index 4402c6f0e7..27b4e55245 100644 --- a/docs/zh_cn/get_started.md +++ b/docs/zh_cn/get_started.md @@ -113,14 +113,14 @@ mim install "mmcv>=2.0.0rc2" ```shell # 1. 安装 MMDeploy 模型转换工具（含trt/ort自定义算子） -pip install mmdeploy==1.0.0rc3 +pip install mmdeploy==1.0.0 # 2. 安装 MMDeploy SDK推理工具 # 根据是否需要GPU推理可任选其一进行下载安装 # 2.1 支持 onnxruntime 推理 -pip install mmdeploy-runtime==1.0.0rc3 +pip install mmdeploy-runtime==1.0.0 # 2.2 支持 onnxruntime-gpu tensorrt 推理 -pip install mmdeploy-runtime-gpu==1.0.0rc3 +pip install mmdeploy-runtime-gpu==1.0.0 # 3. 安装推理引擎 # 3.1 安装推理引擎 TensorRT @@ -165,7 +165,7 @@ export LD_LIBRARY_PATH=$ONNXRUNTIME_DIR/lib:$LD_LIBRARY_PATH ```shell # 克隆 mmdeploy 仓库。转换时，需要使用 mmdeploy 仓库中的配置文件，建立转换流水线, `--recursive` 不是必须的 -git clone -b dev-1.x --recursive https://github.com/open-mmlab/mmdeploy.git +git clone -b main --recursive https://github.com/open-mmlab/mmdeploy.git # 安装 mmdetection。转换时，需要使用 mmdetection 仓库中的模型配置文件，构建 PyTorch nn module git clone -b 3.x https://github.com/open-mmlab/mmdetection.git @@ -223,10 +223,10 @@ result = inference_model( 你可以直接运行预编译包中的 demo 程序，输入 SDK Model 和图像，进行推理，并查看推理结果。 ```shell -wget https://github.com/open-mmlab/mmdeploy/releases/download/v1.0.0rc3/mmdeploy-1.0.0rc3-linux-x86_64-cuda11.3.tar.gz -tar xf mmdeploy-1.0.0rc3-linux-x86_64-cuda11.3 +wget https://github.com/open-mmlab/mmdeploy/releases/download/v1.0.0/mmdeploy-1.0.0-linux-x86_64-cuda11.3.tar.gz +tar xf mmdeploy-1.0.0-linux-x86_64-cuda11.3 -cd mmdeploy-1.0.0rc3-linux-x86_64-cuda11.3 +cd mmdeploy-1.0.0-linux-x86_64-cuda11.3 # 运行 python demo python example/python/object_detection.py cuda ../mmdeploy_model/faster-rcnn ../mmdetection/demo/demo.jpg # 运行 C/C++ demo @@ -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/1.x/demo/python)。 +更多示例，请查阅[这里](https://github.com/open-mmlab/mmdeploy/tree/main/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/1.x/demo/csrc/cpp)。 +更多示例，请查阅[此处](https://github.com/open-mmlab/mmdeploy/tree/main/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/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)。 +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/main/demo/csrc/c)， [C# demos](https://github.com/open-mmlab/mmdeploy/tree/main/demo/csharp) 和 [Java demos](https://github.com/open-mmlab/mmdeploy/tree/main/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） diff --git a/docs/zh_cn/switch_language.md b/docs/zh_cn/switch_language.md index 03bf778b72..1b5df42929 100644 --- a/docs/zh_cn/switch_language.md +++ b/docs/zh_cn/switch_language.md @@ -1,3 +1,3 @@ -## English +## English -## 简体中文 +## 简体中文 diff --git a/docs/zh_cn/tutorial/02_challenges.md b/docs/zh_cn/tutorial/02_challenges.md index e3d0e37970..85e4b0c23a 100644 --- a/docs/zh_cn/tutorial/02_challenges.md +++ b/docs/zh_cn/tutorial/02_challenges.md @@ -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/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。 +在[第一章](https://mmdeploy.readthedocs.io/zh_CN/latest/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/1.x/tutorial/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/latest/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/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： +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/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/1.x/tutorial/01_introduction_to_model_deployment.html#pytorch + # https://mmdeploy.readthedocs.io/zh_CN/latest/tutorial/01_introduction_to_model_deployment.html#pytorch state_dict = torch.load('srcnn.pth')['state_dict'] # Adapt the checkpoint @@ -173,7 +173,7 @@ with torch.no_grad(): ![image](https://user-images.githubusercontent.com/4560679/157626910-de33365c-b60a-49f4-ada7-157111afa6e2.png) -其中，展开 scales，可以看到 scales 是一个长度为 4 的一维张量，其内容为 \[1, 1, 3, 3\], 表示 Resize 操作每一个维度的缩放系数；其类型为 Initializer，表示这个值是根据常量直接初始化出来的。如果我们能够自己生成一个 ONNX 的 Resize 算子，让 scales 成为一个可变量而不是常量，就像它上面的 X 一样，那这个超分辨率模型就能动态缩放了。 +其中，展开 scales，可以看到 scales 是一个长度为 4 的一维张量，其内容为 [1, 1, 3, 3], 表示 Resize 操作每一个维度的缩放系数；其类型为 Initializer，表示这个值是根据常量直接初始化出来的。如果我们能够自己生成一个 ONNX 的 Resize 算子，让 scales 成为一个可变量而不是常量，就像它上面的 X 一样，那这个超分辨率模型就能动态缩放了。 现有实现插值的 PyTorch 算子有一套规定好的映射到 ONNX Resize 算子的方法，这些映射出的 Resize 算子的 scales 只能是常量，无法满足我们的需求。我们得自己定义一个实现插值的 PyTorch 算子，然后让它映射到一个我们期望的 ONNX Resize 算子上。 @@ -294,9 +294,9 @@ class NewInterpolate(torch.autograd.Function): align_corners=False) ``` -在具体介绍这个算子的实现前，让我们先理清一下思路。我们希望新的插值算子有两个输入，一个是被用于操作的图像，一个是图像的放缩比例。前面讲到，为了对接 ONNX 中 Resize 算子的 scales 参数，这个放缩比例是一个 \[1, 1, x, x\] 的张量，其中 x 为放大倍数。在之前放大3倍的模型中，这个参数被固定成了\[1, 1, 3, 3\]。因此，在插值算子中，我们希望模型的第二个输入是一个 \[1, 1, w, h\] 的张量，其中 w 和 h 分别是图片宽和高的放大倍数。 +在具体介绍这个算子的实现前，让我们先理清一下思路。我们希望新的插值算子有两个输入，一个是被用于操作的图像，一个是图像的放缩比例。前面讲到，为了对接 ONNX 中 Resize 算子的 scales 参数，这个放缩比例是一个 [1, 1, x, x] 的张量，其中 x 为放大倍数。在之前放大3倍的模型中，这个参数被固定成了[1, 1, 3, 3]。因此，在插值算子中，我们希望模型的第二个输入是一个 [1, 1, w, h] 的张量，其中 w 和 h 分别是图片宽和高的放大倍数。 -搞清楚了插值算子的输入，再看一看算子的具体实现。算子的推理行为由算子的 forward 方法决定。该方法的第一个参数必须为 ctx，后面的参数为算子的自定义输入，我们设置两个输入，分别为被操作的图像和放缩比例。为保证推理正确，需要把 \[1, 1, w, h\] 格式的输入对接到原来的 interpolate 函数上。我们的做法是截取输入张量的后两个元素，把这两个元素以 list 的格式传入 interpolate 的 scale_factor 参数。 +搞清楚了插值算子的输入，再看一看算子的具体实现。算子的推理行为由算子的 forward 方法决定。该方法的第一个参数必须为 ctx，后面的参数为算子的自定义输入，我们设置两个输入，分别为被操作的图像和放缩比例。为保证推理正确，需要把 [1, 1, w, h] 格式的输入对接到原来的 interpolate 函数上。我们的做法是截取输入张量的后两个元素，把这两个元素以 list 的格式传入 interpolate 的 scale_factor 参数。 接下来，我们要决定新算子映射到 ONNX 算子的方法。映射到 ONNX 的方法由一个算子的 symbolic 方法决定。symbolic 方法第一个参数必须是g，之后的参数是算子的自定义输入，和 forward 函数一样。ONNX 算子的具体定义由 g.op 实现。g.op 的每个参数都可以映射到 ONNX 中的算子属性： diff --git a/docs/zh_cn/tutorial/03_pytorch2onnx.md b/docs/zh_cn/tutorial/03_pytorch2onnx.md index 5839c0afb4..1a30c9c9b1 100644 --- a/docs/zh_cn/tutorial/03_pytorch2onnx.md +++ b/docs/zh_cn/tutorial/03_pytorch2onnx.md @@ -228,7 +228,7 @@ class Model(torch.nn.Module): return x ``` -这里，我们仅在模型导出时把输出张量的数值限制在\[0, 1\]之间。使用 `is_in_onnx_export` 确实能让我们方便地在代码中添加和模型部署相关的逻辑。但是，这些代码对只关心模型训练的开发者和用户来说很不友好，突兀的部署逻辑会降低代码整体的可读性。同时，`is_in_onnx_export` 只能在每个需要添加部署逻辑的地方都“打补丁”，难以进行统一的管理。我们之后会介绍如何使用 MMDeploy 的重写机制来规避这些问题。 +这里，我们仅在模型导出时把输出张量的数值限制在[0, 1]之间。使用 `is_in_onnx_export` 确实能让我们方便地在代码中添加和模型部署相关的逻辑。但是，这些代码对只关心模型训练的开发者和用户来说很不友好，突兀的部署逻辑会降低代码整体的可读性。同时，`is_in_onnx_export` 只能在每个需要添加部署逻辑的地方都“打补丁”，难以进行统一的管理。我们之后会介绍如何使用 MMDeploy 的重写机制来规避这些问题。 #### 利用中断张量跟踪的操作 diff --git a/docs/zh_cn/tutorial/06_introduction_to_tensorrt.md b/docs/zh_cn/tutorial/06_introduction_to_tensorrt.md index dca251f127..755f230db4 100644 --- a/docs/zh_cn/tutorial/06_introduction_to_tensorrt.md +++ b/docs/zh_cn/tutorial/06_introduction_to_tensorrt.md @@ -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/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。 +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/main/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 diff --git a/mmdeploy/version.py b/mmdeploy/version.py index b9b90e63ca..d5c458e274 100644 --- a/mmdeploy/version.py +++ b/mmdeploy/version.py @@ -1,7 +1,7 @@ # Copyright (c) OpenMMLab. All rights reserved. from typing import Tuple -__version__ = '1.0.0rc3' +__version__ = '1.0.0' short_version = __version__ diff --git a/requirements.txt b/requirements.txt index 5f50cbdc09..b5b5d97a6e 100644 --- a/requirements.txt +++ b/requirements.txt @@ -1,3 +1,4 @@ -r requirements/build.txt -r requirements/runtime.txt -r requirements/tests.txt +-r requirements/optional.txt diff --git a/requirements/backends.txt b/requirements/backends.txt index 6143ebd459..306b2c1528 100644 --- a/requirements/backends.txt +++ b/requirements/backends.txt @@ -1,2 +1,2 @@ onnxruntime>=1.8.0 -openvino-dev +openvino-dev>=2022.3.0 diff --git a/requirements/codebases.txt b/requirements/codebases.txt index 027c7bb346..2d1a8db3cf 100644 --- a/requirements/codebases.txt +++ b/requirements/codebases.txt @@ -5,4 +5,4 @@ mmedit>=1.0.0rc2 mmocr>=1.0.0rc4 mmpose>=1.0.0rc0 mmrotate>=1.0.0rc0 -mmsegmentation>=1.0.0rc0 +mmsegmentation @ git+https://github.com/open-mmlab/mmsegmentation.git@dev-1.x diff --git a/requirements/optional.txt b/requirements/optional.txt index 9c445a2534..bd3e5c6e86 100644 --- a/requirements/optional.txt +++ b/requirements/optional.txt @@ -1,4 +1,2 @@ --r requirements/codebases.txt --r requirements/backends.txt h5py tqdm diff --git a/tools/package_tools/packaging/mmdeploy_runtime/version.py b/tools/package_tools/packaging/mmdeploy_runtime/version.py index 5ad5d727cf..8b33ac0e6c 100644 --- a/tools/package_tools/packaging/mmdeploy_runtime/version.py +++ b/tools/package_tools/packaging/mmdeploy_runtime/version.py @@ -1,2 +1,2 @@ # Copyright (c) OpenMMLab. All rights reserved. -__version__ = '1.0.0rc3' +__version__ = '1.0.0' diff --git a/tools/package_tools/test/test_sdk.sh b/tools/package_tools/test/test_sdk.sh index 57e27de752..472a8d5b4c 100755 --- a/tools/package_tools/test/test_sdk.sh +++ b/tools/package_tools/test/test_sdk.sh @@ -18,7 +18,7 @@ cp -r $test_pkg $work_dir pushd $work_dir # opencv -if [[ ! -d $OpenCV_DIR ]]; then +if [ ! -d "$OpenCV_DIR" ]; then ./install_opencv.sh fi diff --git a/tools/scripts/ubuntu_utils.py b/tools/scripts/ubuntu_utils.py index 742e069629..31cea14037 100644 --- a/tools/scripts/ubuntu_utils.py +++ b/tools/scripts/ubuntu_utils.py @@ -29,8 +29,6 @@ def get_job(argv) -> int: nproc = cmd_result('nproc') if nproc is not None and len(nproc) > 0: job = max(int(nproc) - 2, 1) - else: - job = 1 else: job = int(argv[1]) return job