mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-10-04 16:22:57 +08:00
721e6efb81
* add GPL lisence * add GPL-3.0 lisence * add GPL-3.0 lisence * add GPL-3.0 lisence * support yolov8 * add pybind for yolov8 * add yolov8 readme * add cpp benchmark * add cpu and gpu mem * public part split * add runtime mode * fixed bugs * add cpu_thread_nums * deal with comments * deal with comments * deal with comments * rm useless code * add FASTDEPLOY_DECL * add FASTDEPLOY_DECL * fixed for windows * mv rss to pss * mv rss to pss * Update utils.cc * use thread to collect mem * Add ResourceUsageMonitor * rm useless code * fixed bug * fixed typo * update ResourceUsageMonitor * fixed bug * fixed bug * add note for ResourceUsageMonitor * deal with comments * add macros * deal with comments * deal with comments * deal with comments * re-lint * rm pmap and use mem api * rm pmap and use mem api * add mem api * Add PrintBenchmarkInfo func * Add PrintBenchmarkInfo func * Add PrintBenchmarkInfo func * deal with comments * fixed enable_paddle_to_trt * add log for paddle_trt * support ppcls benchmark * use new trt option api * update benchmark info * simplify benchmark.cc * simplify benchmark.cc * deal with comments * Add ppseg && ppocr benchmark * add OCR rec img * add ocr benchmark * fixed trt shape * add trt shape * resolve conflict * add ENABLE_BENCHMARK define * Add ClassifyDiff * Add Resize for ClassifyResult * deal with comments --------- Co-authored-by: DefTruth <31974251+DefTruth@users.noreply.github.com>
98 lines
3.7 KiB
C++
Executable File
98 lines
3.7 KiB
C++
Executable File
// Copyright (c) 2023 PaddlePaddle Authors. All Rights Reserved.
|
|
//
|
|
// Licensed under the Apache License, Version 2.0 (the "License");
|
|
// you may not use this file except in compliance with the License.
|
|
// You may obtain a copy of the License at
|
|
//
|
|
// http://www.apache.org/licenses/LICENSE-2.0
|
|
//
|
|
// Unless required by applicable law or agreed to in writing, software
|
|
// distributed under the License is distributed on an "AS IS" BASIS,
|
|
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
// See the License for the specific language governing permissions and
|
|
// limitations under the License.
|
|
|
|
#pragma once
|
|
|
|
#include "gflags/gflags.h"
|
|
#include "fastdeploy/benchmark/utils.h"
|
|
|
|
#ifdef WIN32
|
|
static const char sep = '\\';
|
|
#else
|
|
static const char sep = '/';
|
|
#endif
|
|
|
|
DEFINE_string(model, "", "Directory of the inference model.");
|
|
DEFINE_string(image, "", "Path of the image file.");
|
|
DEFINE_string(device, "cpu",
|
|
"Type of inference device, support 'cpu/gpu/xpu'.");
|
|
DEFINE_int32(device_id, 0, "device(gpu/xpu/...) id.");
|
|
DEFINE_int32(warmup, 200, "Number of warmup for profiling.");
|
|
DEFINE_int32(repeat, 1000, "Number of repeats for profiling.");
|
|
DEFINE_string(profile_mode, "runtime", "runtime or end2end.");
|
|
DEFINE_string(backend, "default",
|
|
"The inference runtime backend, support: ['default', 'ort', "
|
|
"'paddle', 'ov', 'trt', 'paddle_trt', 'lite']");
|
|
DEFINE_int32(cpu_thread_nums, 8, "Set numbers of cpu thread.");
|
|
DEFINE_bool(
|
|
include_h2d_d2h, false, "Whether run profiling with h2d and d2h.");
|
|
DEFINE_bool(
|
|
use_fp16, false,
|
|
"Whether to use FP16 mode, only support 'trt', 'paddle_trt' "
|
|
"and 'lite' backend");
|
|
DEFINE_bool(
|
|
collect_memory_info, false, "Whether to collect memory info");
|
|
DEFINE_int32(sampling_interval, 50, "How often to collect memory info(ms).");
|
|
|
|
static void PrintUsage() {
|
|
std::cout << "Usage: infer_demo --model model_path --image img_path --device "
|
|
"[cpu|gpu|xpu] --backend "
|
|
"[default|ort|paddle|ov|trt|paddle_trt|lite] "
|
|
"--use_fp16 false"
|
|
<< std::endl;
|
|
std::cout << "Default value of device: cpu" << std::endl;
|
|
std::cout << "Default value of backend: default" << std::endl;
|
|
std::cout << "Default value of use_fp16: false" << std::endl;
|
|
}
|
|
|
|
static void PrintBenchmarkInfo() {
|
|
#if defined(ENABLE_BENCHMARK) && defined(ENABLE_VISION)
|
|
// Get model name
|
|
std::vector<std::string> model_names;
|
|
fastdeploy::benchmark::Split(FLAGS_model, model_names, sep);
|
|
if (model_names.empty()) {
|
|
std::cout << "Directory of the inference model is invalid!!!" << std::endl;
|
|
return;
|
|
}
|
|
// Save benchmark info
|
|
std::stringstream ss;
|
|
ss.precision(3);
|
|
ss << "\n======= Model Info =======\n";
|
|
ss << "model_name: " << model_names[model_names.size() - 1] << std::endl;
|
|
ss << "profile_mode: " << FLAGS_profile_mode << std::endl;
|
|
if (FLAGS_profile_mode == "runtime") {
|
|
ss << "include_h2d_d2h: " << FLAGS_include_h2d_d2h << std::endl;
|
|
}
|
|
ss << "\n======= Backend Info =======\n";
|
|
ss << "warmup: " << FLAGS_warmup << std::endl;
|
|
ss << "repeats: " << FLAGS_repeat << std::endl;
|
|
ss << "device: " << FLAGS_device << std::endl;
|
|
if (FLAGS_device == "gpu") {
|
|
ss << "device_id: " << FLAGS_device_id << std::endl;
|
|
}
|
|
ss << "backend: " << FLAGS_backend << std::endl;
|
|
if (FLAGS_device == "cpu") {
|
|
ss << "cpu_thread_nums: " << FLAGS_cpu_thread_nums << std::endl;
|
|
}
|
|
ss << "use_fp16: " << FLAGS_use_fp16 << std::endl;
|
|
ss << "collect_memory_info: " << FLAGS_collect_memory_info << std::endl;
|
|
if (FLAGS_collect_memory_info) {
|
|
ss << "sampling_interval: " << std::to_string(FLAGS_sampling_interval)
|
|
<< "ms" << std::endl;
|
|
}
|
|
std::cout << ss.str() << std::endl;
|
|
#endif
|
|
return;
|
|
}
|