lvhan028 36124f6205
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

53 lines
1.4 KiB
C++

// Copyright (c) OpenMMLab. All rights reserved.
#include "transform.h"
#include "core/registry.h"
namespace mmdeploy {
TransformImpl::TransformImpl(const Value &args) {
Device device{"cpu"};
if (args.contains("context")) {
device_ = args["context"].value("device", device);
stream_ = args["context"].value("stream", Stream::GetDefault(device_));
} else {
device_ = device;
stream_ = Stream::GetDefault(device_);
}
}
std::vector<std::string> TransformImpl::GetImageFields(const Value &input) {
if (input.contains("img_fields")) {
if (input["img_fields"].is_string()) {
return {input["img_fields"].get<std::string>()};
} else if (input["img_fields"].is_array()) {
std::vector<std::string> img_fields;
for (auto &v : input["img_fields"]) {
img_fields.push_back(v.get<std::string>());
}
return img_fields;
}
} else {
return {"img"};
}
throw_exception(eInvalidArgument);
}
Transform::Transform(const Value &args) {
Device device{"cpu"};
if (args.contains("context")) {
device = args["context"].value("device", device);
}
Platform platform(device.platform_id());
specified_platform_ = platform.GetPlatformName();
if (!(specified_platform_ == "cpu")) {
// add cpu platform, so that a transform op can fall back to its cpu
// version if it hasn't implementation on the specific platform
candidate_platforms_.push_back("cpu");
}
}
} // namespace mmdeploy