mmdeploy/csrc/core/graph.cpp

30 lines
695 B
C++
Raw Normal View History

Merge sdk (#251) * check in cmake * move backend_ops to csrc/backend_ops * check in preprocess, model, some codebase and their c-apis * check in CMakeLists.txt * check in parts of test_csrc * commit everything else * add readme * update core's BUILD_INTERFACE directory * skip codespell on third_party * update trt_net and ort_net's CMakeLists * ignore clion's build directory * check in pybind11 * add onnx.proto. Remove MMDeploy's dependency on ncnn's source code * export MMDeployTargets only when MMDEPLOY_BUILD_SDK is ON * remove useless message * target include directory is wrong * change target name from mmdeploy_ppl_net to mmdeploy_pplnn_net * skip install directory * update project's cmake * remove useless code * set CMAKE_BUILD_TYPE to Release by force if it isn't set by user * update custom ops CMakeLists * pass object target's source lists * fix lint end-of-file * fix lint: trailing whitespace * fix codespell hook * remove bicubic_interpolate to csrc/backend_ops/ * set MMDEPLOY_BUILD_SDK OFF * change custom ops build command * add spdlog installation command * update docs on how to checkout pybind11 * move bicubic_interpolate to backend_ops/tensorrt directory * remove useless code * correct cmake * fix typo * fix typo * fix install directory * correct sdk's readme * set cub dir when cuda version < 11.0 * change directory where clang-format will apply to * fix build command * add .clang-format * change clang-format style from google to file * reformat csrc/backend_ops * format sdk's code * turn off clang-format for some files * add -Xcompiler=-fno-gnu-unique * fix trt topk initialize * check in config for sdk demo * update cmake script and csrc's readme * correct config's path * add cuda include directory, otherwise compile failed in case of tensorrt8.2 * clang-format onnx2ncnn.cpp Co-authored-by: zhangli <lzhang329@gmail.com> Co-authored-by: grimoire <yaoqian@sensetime.com>
2021-12-07 10:57:55 +08:00
// Copyright (c) OpenMMLab. All rights reserved.
#include "core/graph.h"
#include "archive/value_archive.h"
Support Windows (#106) * minor changes * support windows * fix GCC build * fix lint * reformat * fix Windows build * fix GCC build * search backend ops for onnxruntime * fix lint * fix lint * code clean-up * code clean-up * fix clang build * fix trt support * fix cmake for ncnn * fix cmake for openvino * fix SDK Python API * handle ops for other backends (ncnn, trt) * handle SDK Python API library location * robustify linkage * fix cuda * minor fix for openvino & ncnn * use CMAKE_CUDA_ARCHITECTURES if set * fix cuda preprocessor * fix misc * fix pplnn & pplcv, drop support for pplcv<0.6.0 * robustify cmake * update build.md (#2) * build dynamic modules as module library & fix demo (partially) * fix candidate path for mmdeploy_python * move "enable CUDA" to cmake config for demo * refine demo cmake * add comment * fix ubuntu build * revert docs/en/build.md * fix C API * fix lint * Windows build doc (#3) * check in docs related to mmdeploy build on windows * update build guide on windows platform * update build guide on windows platform * make path of thirdparty libraries consistent * make path consistency * correct build command for custom ops * correct build command for sdk * update sdk build instructions * update doc * correct build command * fix lint * correct build command and fix lint Co-authored-by: lvhan <lvhan@pjlab.org> * trailing whitespace (#4) * minor fix * fix sr sdk model * fix type deduction * fix cudaFree after driver shutting down * update ppl.cv installation warning (#5) * fix device allocator threshold & fix lint * update doc (#6) * update ppl.cv installation warning * missing 'git clone' Co-authored-by: chenxin <chenxin2@sensetime.com> Co-authored-by: zhangli <zhangli@sensetime.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: lvhan <lvhan@pjlab.org>
2022-02-24 20:08:44 +08:00
#include "core/registry.h"
Merge sdk (#251) * check in cmake * move backend_ops to csrc/backend_ops * check in preprocess, model, some codebase and their c-apis * check in CMakeLists.txt * check in parts of test_csrc * commit everything else * add readme * update core's BUILD_INTERFACE directory * skip codespell on third_party * update trt_net and ort_net's CMakeLists * ignore clion's build directory * check in pybind11 * add onnx.proto. Remove MMDeploy's dependency on ncnn's source code * export MMDeployTargets only when MMDEPLOY_BUILD_SDK is ON * remove useless message * target include directory is wrong * change target name from mmdeploy_ppl_net to mmdeploy_pplnn_net * skip install directory * update project's cmake * remove useless code * set CMAKE_BUILD_TYPE to Release by force if it isn't set by user * update custom ops CMakeLists * pass object target's source lists * fix lint end-of-file * fix lint: trailing whitespace * fix codespell hook * remove bicubic_interpolate to csrc/backend_ops/ * set MMDEPLOY_BUILD_SDK OFF * change custom ops build command * add spdlog installation command * update docs on how to checkout pybind11 * move bicubic_interpolate to backend_ops/tensorrt directory * remove useless code * correct cmake * fix typo * fix typo * fix install directory * correct sdk's readme * set cub dir when cuda version < 11.0 * change directory where clang-format will apply to * fix build command * add .clang-format * change clang-format style from google to file * reformat csrc/backend_ops * format sdk's code * turn off clang-format for some files * add -Xcompiler=-fno-gnu-unique * fix trt topk initialize * check in config for sdk demo * update cmake script and csrc's readme * correct config's path * add cuda include directory, otherwise compile failed in case of tensorrt8.2 * clang-format onnx2ncnn.cpp Co-authored-by: zhangli <lzhang329@gmail.com> Co-authored-by: grimoire <yaoqian@sensetime.com>
2021-12-07 10:57:55 +08:00
Support Windows (#106) * minor changes * support windows * fix GCC build * fix lint * reformat * fix Windows build * fix GCC build * search backend ops for onnxruntime * fix lint * fix lint * code clean-up * code clean-up * fix clang build * fix trt support * fix cmake for ncnn * fix cmake for openvino * fix SDK Python API * handle ops for other backends (ncnn, trt) * handle SDK Python API library location * robustify linkage * fix cuda * minor fix for openvino & ncnn * use CMAKE_CUDA_ARCHITECTURES if set * fix cuda preprocessor * fix misc * fix pplnn & pplcv, drop support for pplcv<0.6.0 * robustify cmake * update build.md (#2) * build dynamic modules as module library & fix demo (partially) * fix candidate path for mmdeploy_python * move "enable CUDA" to cmake config for demo * refine demo cmake * add comment * fix ubuntu build * revert docs/en/build.md * fix C API * fix lint * Windows build doc (#3) * check in docs related to mmdeploy build on windows * update build guide on windows platform * update build guide on windows platform * make path of thirdparty libraries consistent * make path consistency * correct build command for custom ops * correct build command for sdk * update sdk build instructions * update doc * correct build command * fix lint * correct build command and fix lint Co-authored-by: lvhan <lvhan@pjlab.org> * trailing whitespace (#4) * minor fix * fix sr sdk model * fix type deduction * fix cudaFree after driver shutting down * update ppl.cv installation warning (#5) * fix device allocator threshold & fix lint * update doc (#6) * update ppl.cv installation warning * missing 'git clone' Co-authored-by: chenxin <chenxin2@sensetime.com> Co-authored-by: zhangli <zhangli@sensetime.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: lvhan <lvhan@pjlab.org>
2022-02-24 20:08:44 +08:00
namespace mmdeploy {
namespace graph {
Merge sdk (#251) * check in cmake * move backend_ops to csrc/backend_ops * check in preprocess, model, some codebase and their c-apis * check in CMakeLists.txt * check in parts of test_csrc * commit everything else * add readme * update core's BUILD_INTERFACE directory * skip codespell on third_party * update trt_net and ort_net's CMakeLists * ignore clion's build directory * check in pybind11 * add onnx.proto. Remove MMDeploy's dependency on ncnn's source code * export MMDeployTargets only when MMDEPLOY_BUILD_SDK is ON * remove useless message * target include directory is wrong * change target name from mmdeploy_ppl_net to mmdeploy_pplnn_net * skip install directory * update project's cmake * remove useless code * set CMAKE_BUILD_TYPE to Release by force if it isn't set by user * update custom ops CMakeLists * pass object target's source lists * fix lint end-of-file * fix lint: trailing whitespace * fix codespell hook * remove bicubic_interpolate to csrc/backend_ops/ * set MMDEPLOY_BUILD_SDK OFF * change custom ops build command * add spdlog installation command * update docs on how to checkout pybind11 * move bicubic_interpolate to backend_ops/tensorrt directory * remove useless code * correct cmake * fix typo * fix typo * fix install directory * correct sdk's readme * set cub dir when cuda version < 11.0 * change directory where clang-format will apply to * fix build command * add .clang-format * change clang-format style from google to file * reformat csrc/backend_ops * format sdk's code * turn off clang-format for some files * add -Xcompiler=-fno-gnu-unique * fix trt topk initialize * check in config for sdk demo * update cmake script and csrc's readme * correct config's path * add cuda include directory, otherwise compile failed in case of tensorrt8.2 * clang-format onnx2ncnn.cpp Co-authored-by: zhangli <lzhang329@gmail.com> Co-authored-by: grimoire <yaoqian@sensetime.com>
2021-12-07 10:57:55 +08:00
[Feature] New pipeline & executor for SDK (#497) * executor prototype * add split/when_all * fix GCC build * WIP let_value * fix let_value * WIP ensure_started * ensure_started & start_detached * fix let_value + when_all combo on MSVC 142 * fix static thread pool * generic just, then, let_value, sync_wait * minor * generic split and when_all * fully generic sender adapters * when_all: workaround for GCC7 * support legacy spdlog * fix memleak * bulk * static detector * fix bulk & first pipeline * bulk for static thread pools * fix on MSVC * WIP async batch submission * WIP collation * async batch * fix detector * fix async detector * fix * fix * debug * fix cuda allocator * WIP type erased executor * better type erasure * simplify C API impl * Expand & type erase TC * deduction guide for type erased senders * fix GCC build * when_all for arrays of Value senders * WIP pipeline v2 * WIP pipeline parser * WIP timed batch operation * add registry * experiment * fix pipeline * naming * fix mem-leak * fix deferred batch operation * WIP * WIP configurable scheduler * WIP configurable scheduler * add comment * parse scheduler config * force link schedulers * WIP pipeable sender * WIP CPO * ADL isolation and dismantle headers * type erase single thread context * fix MSVC build * CPO * replace decay_t with remove_cvref_t * structure adjustment * structure adjustment * apply CPOs & C API rework * refine C API * detector async C API * adjust detector async C API * # Conflicts: # csrc/apis/c/detector.cpp * fix when_all for type erased senders * support void return for Then * async detector * fix some CPOs * minor * WIP rework capture mechanism for type erased types * minor fix * fix MSVC build * move expand.h to execution * make `Expand` pipeable * fix type erased * un-templatize `_TypeErasedOperation` * re-work C API * remove async_detector C API * fix pipeline * add flatten & unflatten * fix flatten & unflatten * add aync OCR demo * config executor for nodes & better executor API * working async OCR example * minor * dynamic batch via scheduler * dynamic batch on `Value` * fix MSVC build * type erase dynamic batch scheduler * sender as Python Awaitable * naming * naming * add docs * minor * merge tmp branch * unify C APIs * fix ocr * unify APIs * fix typo * update async OCR demo * add v3 API text recognizer * fix v3 API * fix lint * add license info & reformat * add demo async_ocr_v2 * revert files * revert files * resolve link issues * fix scheduler linkage for shared libs * fix license header * add docs for `mmdeploy_executor_split` * add missing `mmdeploy_executor_transfer_just` and `mmdeploy_executor_execute` * make `TimedSingleThreadContext` header only * fix lint * simplify type-erased sender
2022-06-01 14:10:43 +08:00
Result<void> NodeParser::Parse(const Value& config, Node& node) {
try {
from_value(config["input"], node.inputs_);
from_value(config["output"], node.outputs_);
node.name_ = config.value<std::string>("name", "");
return success();
} catch (const Exception& e) {
MMDEPLOY_ERROR("error parsing config: {}", config);
return failure(e.code());
Merge sdk (#251) * check in cmake * move backend_ops to csrc/backend_ops * check in preprocess, model, some codebase and their c-apis * check in CMakeLists.txt * check in parts of test_csrc * commit everything else * add readme * update core's BUILD_INTERFACE directory * skip codespell on third_party * update trt_net and ort_net's CMakeLists * ignore clion's build directory * check in pybind11 * add onnx.proto. Remove MMDeploy's dependency on ncnn's source code * export MMDeployTargets only when MMDEPLOY_BUILD_SDK is ON * remove useless message * target include directory is wrong * change target name from mmdeploy_ppl_net to mmdeploy_pplnn_net * skip install directory * update project's cmake * remove useless code * set CMAKE_BUILD_TYPE to Release by force if it isn't set by user * update custom ops CMakeLists * pass object target's source lists * fix lint end-of-file * fix lint: trailing whitespace * fix codespell hook * remove bicubic_interpolate to csrc/backend_ops/ * set MMDEPLOY_BUILD_SDK OFF * change custom ops build command * add spdlog installation command * update docs on how to checkout pybind11 * move bicubic_interpolate to backend_ops/tensorrt directory * remove useless code * correct cmake * fix typo * fix typo * fix install directory * correct sdk's readme * set cub dir when cuda version < 11.0 * change directory where clang-format will apply to * fix build command * add .clang-format * change clang-format style from google to file * reformat csrc/backend_ops * format sdk's code * turn off clang-format for some files * add -Xcompiler=-fno-gnu-unique * fix trt topk initialize * check in config for sdk demo * update cmake script and csrc's readme * correct config's path * add cuda include directory, otherwise compile failed in case of tensorrt8.2 * clang-format onnx2ncnn.cpp Co-authored-by: zhangli <lzhang329@gmail.com> Co-authored-by: grimoire <yaoqian@sensetime.com>
2021-12-07 10:57:55 +08:00
}
}
Support Windows (#106) * minor changes * support windows * fix GCC build * fix lint * reformat * fix Windows build * fix GCC build * search backend ops for onnxruntime * fix lint * fix lint * code clean-up * code clean-up * fix clang build * fix trt support * fix cmake for ncnn * fix cmake for openvino * fix SDK Python API * handle ops for other backends (ncnn, trt) * handle SDK Python API library location * robustify linkage * fix cuda * minor fix for openvino & ncnn * use CMAKE_CUDA_ARCHITECTURES if set * fix cuda preprocessor * fix misc * fix pplnn & pplcv, drop support for pplcv<0.6.0 * robustify cmake * update build.md (#2) * build dynamic modules as module library & fix demo (partially) * fix candidate path for mmdeploy_python * move "enable CUDA" to cmake config for demo * refine demo cmake * add comment * fix ubuntu build * revert docs/en/build.md * fix C API * fix lint * Windows build doc (#3) * check in docs related to mmdeploy build on windows * update build guide on windows platform * update build guide on windows platform * make path of thirdparty libraries consistent * make path consistency * correct build command for custom ops * correct build command for sdk * update sdk build instructions * update doc * correct build command * fix lint * correct build command and fix lint Co-authored-by: lvhan <lvhan@pjlab.org> * trailing whitespace (#4) * minor fix * fix sr sdk model * fix type deduction * fix cudaFree after driver shutting down * update ppl.cv installation warning (#5) * fix device allocator threshold & fix lint * update doc (#6) * update ppl.cv installation warning * missing 'git clone' Co-authored-by: chenxin <chenxin2@sensetime.com> Co-authored-by: zhangli <zhangli@sensetime.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: lvhan <lvhan@pjlab.org>
2022-02-24 20:08:44 +08:00
} // namespace graph
MMDEPLOY_DEFINE_REGISTRY(graph::Node);
[Feature] New pipeline & executor for SDK (#497) * executor prototype * add split/when_all * fix GCC build * WIP let_value * fix let_value * WIP ensure_started * ensure_started & start_detached * fix let_value + when_all combo on MSVC 142 * fix static thread pool * generic just, then, let_value, sync_wait * minor * generic split and when_all * fully generic sender adapters * when_all: workaround for GCC7 * support legacy spdlog * fix memleak * bulk * static detector * fix bulk & first pipeline * bulk for static thread pools * fix on MSVC * WIP async batch submission * WIP collation * async batch * fix detector * fix async detector * fix * fix * debug * fix cuda allocator * WIP type erased executor * better type erasure * simplify C API impl * Expand & type erase TC * deduction guide for type erased senders * fix GCC build * when_all for arrays of Value senders * WIP pipeline v2 * WIP pipeline parser * WIP timed batch operation * add registry * experiment * fix pipeline * naming * fix mem-leak * fix deferred batch operation * WIP * WIP configurable scheduler * WIP configurable scheduler * add comment * parse scheduler config * force link schedulers * WIP pipeable sender * WIP CPO * ADL isolation and dismantle headers * type erase single thread context * fix MSVC build * CPO * replace decay_t with remove_cvref_t * structure adjustment * structure adjustment * apply CPOs & C API rework * refine C API * detector async C API * adjust detector async C API * # Conflicts: # csrc/apis/c/detector.cpp * fix when_all for type erased senders * support void return for Then * async detector * fix some CPOs * minor * WIP rework capture mechanism for type erased types * minor fix * fix MSVC build * move expand.h to execution * make `Expand` pipeable * fix type erased * un-templatize `_TypeErasedOperation` * re-work C API * remove async_detector C API * fix pipeline * add flatten & unflatten * fix flatten & unflatten * add aync OCR demo * config executor for nodes & better executor API * working async OCR example * minor * dynamic batch via scheduler * dynamic batch on `Value` * fix MSVC build * type erase dynamic batch scheduler * sender as Python Awaitable * naming * naming * add docs * minor * merge tmp branch * unify C APIs * fix ocr * unify APIs * fix typo * update async OCR demo * add v3 API text recognizer * fix v3 API * fix lint * add license info & reformat * add demo async_ocr_v2 * revert files * revert files * resolve link issues * fix scheduler linkage for shared libs * fix license header * add docs for `mmdeploy_executor_split` * add missing `mmdeploy_executor_transfer_just` and `mmdeploy_executor_execute` * make `TimedSingleThreadContext` header only * fix lint * simplify type-erased sender
2022-06-01 14:10:43 +08:00
MMDEPLOY_DEFINE_REGISTRY(TypeErasedScheduler<Value>);
Support Windows (#106) * minor changes * support windows * fix GCC build * fix lint * reformat * fix Windows build * fix GCC build * search backend ops for onnxruntime * fix lint * fix lint * code clean-up * code clean-up * fix clang build * fix trt support * fix cmake for ncnn * fix cmake for openvino * fix SDK Python API * handle ops for other backends (ncnn, trt) * handle SDK Python API library location * robustify linkage * fix cuda * minor fix for openvino & ncnn * use CMAKE_CUDA_ARCHITECTURES if set * fix cuda preprocessor * fix misc * fix pplnn & pplcv, drop support for pplcv<0.6.0 * robustify cmake * update build.md (#2) * build dynamic modules as module library & fix demo (partially) * fix candidate path for mmdeploy_python * move "enable CUDA" to cmake config for demo * refine demo cmake * add comment * fix ubuntu build * revert docs/en/build.md * fix C API * fix lint * Windows build doc (#3) * check in docs related to mmdeploy build on windows * update build guide on windows platform * update build guide on windows platform * make path of thirdparty libraries consistent * make path consistency * correct build command for custom ops * correct build command for sdk * update sdk build instructions * update doc * correct build command * fix lint * correct build command and fix lint Co-authored-by: lvhan <lvhan@pjlab.org> * trailing whitespace (#4) * minor fix * fix sr sdk model * fix type deduction * fix cudaFree after driver shutting down * update ppl.cv installation warning (#5) * fix device allocator threshold & fix lint * update doc (#6) * update ppl.cv installation warning * missing 'git clone' Co-authored-by: chenxin <chenxin2@sensetime.com> Co-authored-by: zhangli <zhangli@sensetime.com> Co-authored-by: lvhan028 <lvhan_028@163.com> Co-authored-by: lvhan <lvhan@pjlab.org>
2022-02-24 20:08:44 +08:00
} // namespace mmdeploy