Merge pull request #3745 from MissPenguin/dygraph
add cpp_infer for cice
This commit is contained in:
MissPenguin
GitHub
commit
c16b6ccb73
|
|
@ -206,6 +206,10 @@ endif()
|
|||
|
||||
set(DEPS ${DEPS} ${OpenCV_LIBS})
|
||||
|
||||
include(ExternalProject)
|
||||
include(external-cmake/auto-log.cmake)
|
||||
include_directories(${CMAKE_CURRENT_BINARY_DIR}/autolog/src/extern_Autolog/auto_log)
|
||||
|
||||
AUX_SOURCE_DIRECTORY(./src SRCS)
|
||||
add_executable(${DEMO_NAME} ${SRCS})
|
||||
|
||||
|
|
|
|||
|
|
@ -0,0 +1,14 @@
|
|||
find_package(Git REQUIRED)
|
||||
message("${CMAKE_BUILD_TYPE}")
|
||||
|
||||
set(AUTOLOG_REPOSITORY https://github.com/LDOUBLEV/AutoLog.git)
|
||||
SET(AUTOLOG_INSTALL_DIR ${CMAKE_CURRENT_BINARY_DIR}/install/Autolog)
|
||||
|
||||
ExternalProject_Add(
|
||||
extern_Autolog
|
||||
PREFIX autolog
|
||||
GIT_REPOSITORY ${AUTOLOG_REPOSITORY}
|
||||
GIT_TAG main
|
||||
DOWNLOAD_NO_EXTRACT True
|
||||
INSTALL_COMMAND cmake -E echo "Skipping install step."
|
||||
)
|
||||
|
|
@ -39,8 +39,8 @@
|
|||
DEFINE_bool(use_gpu, false, "Infering with GPU or CPU.");
|
||||
DEFINE_int32(gpu_id, 0, "Device id of GPU to execute.");
|
||||
DEFINE_int32(gpu_mem, 4000, "GPU id when infering with GPU.");
|
||||
DEFINE_int32(cpu_math_library_num_threads, 10, "Num of threads with CPU.");
|
||||
DEFINE_bool(use_mkldnn, false, "Whether use mkldnn with CPU.");
|
||||
DEFINE_int32(cpu_threads, 10, "Num of threads with CPU.");
|
||||
DEFINE_bool(enable_mkldnn, false, "Whether use mkldnn with CPU.");
|
||||
DEFINE_bool(use_tensorrt, false, "Whether use tensorrt.");
|
||||
DEFINE_string(precision, "fp32", "Precision be one of fp32/fp16/int8");
|
||||
DEFINE_bool(benchmark, true, "Whether use benchmark.");
|
||||
|
|
@ -60,6 +60,7 @@ DEFINE_string(cls_model_dir, "", "Path of cls inference model.");
|
|||
DEFINE_double(cls_thresh, 0.9, "Threshold of cls_thresh.");
|
||||
// recognition related
|
||||
DEFINE_string(rec_model_dir, "", "Path of rec inference model.");
|
||||
DEFINE_int32(rec_batch_num, 1, "rec_batch_num.");
|
||||
DEFINE_string(char_list_file, "../../ppocr/utils/ppocr_keys_v1.txt", "Path of dictionary.");
|
||||
|
||||
|
||||
|
|
@ -68,34 +69,6 @@ using namespace cv;
|
|||
using namespace PaddleOCR;
|
||||
|
||||
|
||||
void PrintBenchmarkLog(std::string model_name,
|
||||
int batch_size,
|
||||
std::string input_shape,
|
||||
std::vector<double> time_info,
|
||||
int img_num){
|
||||
LOG(INFO) << "----------------------- Config info -----------------------";
|
||||
LOG(INFO) << "runtime_device: " << (FLAGS_use_gpu ? "gpu" : "cpu");
|
||||
LOG(INFO) << "ir_optim: " << "True";
|
||||
LOG(INFO) << "enable_memory_optim: " << "True";
|
||||
LOG(INFO) << "enable_tensorrt: " << FLAGS_use_tensorrt;
|
||||
LOG(INFO) << "enable_mkldnn: " << (FLAGS_use_mkldnn ? "True" : "False");
|
||||
LOG(INFO) << "cpu_math_library_num_threads: " << FLAGS_cpu_math_library_num_threads;
|
||||
LOG(INFO) << "----------------------- Data info -----------------------";
|
||||
LOG(INFO) << "batch_size: " << batch_size;
|
||||
LOG(INFO) << "input_shape: " << input_shape;
|
||||
LOG(INFO) << "data_num: " << img_num;
|
||||
LOG(INFO) << "----------------------- Model info -----------------------";
|
||||
LOG(INFO) << "model_name: " << model_name;
|
||||
LOG(INFO) << "precision: " << FLAGS_precision;
|
||||
LOG(INFO) << "----------------------- Perf info ------------------------";
|
||||
LOG(INFO) << "Total time spent(ms): "
|
||||
<< std::accumulate(time_info.begin(), time_info.end(), 0);
|
||||
LOG(INFO) << "preprocess_time(ms): " << time_info[0] / img_num
|
||||
<< ", inference_time(ms): " << time_info[1] / img_num
|
||||
<< ", postprocess_time(ms): " << time_info[2] / img_num;
|
||||
}
|
||||
|
||||
|
||||
static bool PathExists(const std::string& path){
|
||||
#ifdef _WIN32
|
||||
struct _stat buffer;
|
||||
|
|
@ -110,8 +83,8 @@ static bool PathExists(const std::string& path){
|
|||
int main_det(std::vector<cv::String> cv_all_img_names) {
|
||||
std::vector<double> time_info = {0, 0, 0};
|
||||
DBDetector det(FLAGS_det_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
|
||||
FLAGS_use_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_threads,
|
||||
FLAGS_enable_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
|
||||
FLAGS_det_db_box_thresh, FLAGS_det_db_unclip_ratio,
|
||||
FLAGS_use_polygon_score, FLAGS_visualize,
|
||||
FLAGS_use_tensorrt, FLAGS_precision);
|
||||
|
|
@ -135,7 +108,17 @@ int main_det(std::vector<cv::String> cv_all_img_names) {
|
|||
}
|
||||
|
||||
if (FLAGS_benchmark) {
|
||||
PrintBenchmarkLog("det", 1, "dynamic", time_info, cv_all_img_names.size());
|
||||
AutoLogger autolog("ocr_det",
|
||||
FLAGS_use_gpu,
|
||||
FLAGS_use_tensorrt,
|
||||
FLAGS_enable_mkldnn,
|
||||
FLAGS_cpu_threads,
|
||||
1,
|
||||
"dynamic",
|
||||
FLAGS_precision,
|
||||
time_info,
|
||||
cv_all_img_names.size());
|
||||
autolog.report();
|
||||
}
|
||||
return 0;
|
||||
}
|
||||
|
|
@ -144,8 +127,8 @@ int main_det(std::vector<cv::String> cv_all_img_names) {
|
|||
int main_rec(std::vector<cv::String> cv_all_img_names) {
|
||||
std::vector<double> time_info = {0, 0, 0};
|
||||
CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
|
||||
FLAGS_use_mkldnn, FLAGS_char_list_file,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_threads,
|
||||
FLAGS_enable_mkldnn, FLAGS_char_list_file,
|
||||
FLAGS_use_tensorrt, FLAGS_precision);
|
||||
|
||||
for (int i = 0; i < cv_all_img_names.size(); ++i) {
|
||||
|
|
@ -165,18 +148,14 @@ int main_rec(std::vector<cv::String> cv_all_img_names) {
|
|||
time_info[2] += rec_times[2];
|
||||
}
|
||||
|
||||
if (FLAGS_benchmark) {
|
||||
PrintBenchmarkLog("rec", 1, "dynamic", time_info, cv_all_img_names.size());
|
||||
}
|
||||
|
||||
return 0;
|
||||
}
|
||||
|
||||
|
||||
int main_system(std::vector<cv::String> cv_all_img_names) {
|
||||
DBDetector det(FLAGS_det_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
|
||||
FLAGS_use_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_threads,
|
||||
FLAGS_enable_mkldnn, FLAGS_max_side_len, FLAGS_det_db_thresh,
|
||||
FLAGS_det_db_box_thresh, FLAGS_det_db_unclip_ratio,
|
||||
FLAGS_use_polygon_score, FLAGS_visualize,
|
||||
FLAGS_use_tensorrt, FLAGS_precision);
|
||||
|
|
@ -184,14 +163,14 @@ int main_system(std::vector<cv::String> cv_all_img_names) {
|
|||
Classifier *cls = nullptr;
|
||||
if (FLAGS_use_angle_cls) {
|
||||
cls = new Classifier(FLAGS_cls_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
|
||||
FLAGS_use_mkldnn, FLAGS_cls_thresh,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_threads,
|
||||
FLAGS_enable_mkldnn, FLAGS_cls_thresh,
|
||||
FLAGS_use_tensorrt, FLAGS_precision);
|
||||
}
|
||||
|
||||
CRNNRecognizer rec(FLAGS_rec_model_dir, FLAGS_use_gpu, FLAGS_gpu_id,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_math_library_num_threads,
|
||||
FLAGS_use_mkldnn, FLAGS_char_list_file,
|
||||
FLAGS_gpu_mem, FLAGS_cpu_threads,
|
||||
FLAGS_enable_mkldnn, FLAGS_char_list_file,
|
||||
FLAGS_use_tensorrt, FLAGS_precision);
|
||||
|
||||
auto start = std::chrono::system_clock::now();
|
||||
|
|
|
|||
|
|
@ -49,4 +49,19 @@ inference:tools/infer/predict_det.py
|
|||
--save_log_path:null
|
||||
--benchmark:True
|
||||
null:null
|
||||
===========================cpp_infer_params===========================
|
||||
use_opencv:True
|
||||
infer_model:./inference/ch_ppocr_mobile_v2.0_det_infer/
|
||||
infer_quant:False
|
||||
inference:./deploy/cpp_infer/build/ppocr det
|
||||
--use_gpu:True|False
|
||||
--enable_mkldnn:True|False
|
||||
--cpu_threads:1|6
|
||||
--rec_batch_num:1
|
||||
--use_tensorrt:False|True
|
||||
--precision:fp32|fp16
|
||||
--det_model_dir:
|
||||
--image_dir:./inference/ch_det_data_50/all-sum-510/
|
||||
--save_log_path:null
|
||||
--benchmark:True
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
#!/bin/bash
|
||||
FILENAME=$1
|
||||
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
|
||||
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer', 'cpp_infer']
|
||||
MODE=$2
|
||||
|
||||
dataline=$(cat ${FILENAME})
|
||||
|
|
@ -58,7 +58,7 @@ elif [ ${MODE} = "whole_infer" ];then
|
|||
cd ./train_data/ && tar xf icdar2015_infer.tar && tar xf ic15_data.tar
|
||||
ln -s ./icdar2015_infer ./icdar2015
|
||||
cd ../
|
||||
else
|
||||
elif [ ${MODE} = "infer" ] || [ ${MODE} = "cpp_infer" ];then
|
||||
if [ ${model_name} = "ocr_det" ]; then
|
||||
eval_model_name="ch_ppocr_mobile_v2.0_det_infer"
|
||||
rm -rf ./train_data/icdar2015
|
||||
|
|
@ -74,3 +74,72 @@ else
|
|||
fi
|
||||
fi
|
||||
|
||||
if [ ${MODE} = "cpp_infer" ];then
|
||||
cd deploy/cpp_infer
|
||||
use_opencv=$(func_parser_value "${lines[52]}")
|
||||
if [ ${use_opencv} = "True" ]; then
|
||||
echo "################### build opencv ###################"
|
||||
rm -rf 3.4.7.tar.gz opencv-3.4.7/
|
||||
wget https://github.com/opencv/opencv/archive/3.4.7.tar.gz
|
||||
tar -xf 3.4.7.tar.gz
|
||||
|
||||
cd opencv-3.4.7/
|
||||
install_path=$(pwd)/opencv-3.4.7/opencv3
|
||||
|
||||
rm -rf build
|
||||
mkdir build
|
||||
cd build
|
||||
|
||||
cmake .. \
|
||||
-DCMAKE_INSTALL_PREFIX=${install_path} \
|
||||
-DCMAKE_BUILD_TYPE=Release \
|
||||
-DBUILD_SHARED_LIBS=OFF \
|
||||
-DWITH_IPP=OFF \
|
||||
-DBUILD_IPP_IW=OFF \
|
||||
-DWITH_LAPACK=OFF \
|
||||
-DWITH_EIGEN=OFF \
|
||||
-DCMAKE_INSTALL_LIBDIR=lib64 \
|
||||
-DWITH_ZLIB=ON \
|
||||
-DBUILD_ZLIB=ON \
|
||||
-DWITH_JPEG=ON \
|
||||
-DBUILD_JPEG=ON \
|
||||
-DWITH_PNG=ON \
|
||||
-DBUILD_PNG=ON \
|
||||
-DWITH_TIFF=ON \
|
||||
-DBUILD_TIFF=ON
|
||||
|
||||
make -j
|
||||
make install
|
||||
cd ../
|
||||
echo "################### build opencv finished ###################"
|
||||
fi
|
||||
|
||||
|
||||
echo "################### build PaddleOCR demo ####################"
|
||||
if [ ${use_opencv} = "True" ]; then
|
||||
OPENCV_DIR=$(pwd)/opencv-3.4.7/opencv3/
|
||||
else
|
||||
OPENCV_DIR=''
|
||||
fi
|
||||
LIB_DIR=$(pwd)/Paddle/build/paddle_inference_install_dir/
|
||||
CUDA_LIB_DIR=$(dirname `find /usr -name libcudart.so`)
|
||||
CUDNN_LIB_DIR=$(dirname `find /usr -name libcudnn.so`)
|
||||
|
||||
BUILD_DIR=build
|
||||
rm -rf ${BUILD_DIR}
|
||||
mkdir ${BUILD_DIR}
|
||||
cd ${BUILD_DIR}
|
||||
cmake .. \
|
||||
-DPADDLE_LIB=${LIB_DIR} \
|
||||
-DWITH_MKL=ON \
|
||||
-DWITH_GPU=OFF \
|
||||
-DWITH_STATIC_LIB=OFF \
|
||||
-DWITH_TENSORRT=OFF \
|
||||
-DOPENCV_DIR=${OPENCV_DIR} \
|
||||
-DCUDNN_LIB=${CUDNN_LIB_DIR} \
|
||||
-DCUDA_LIB=${CUDA_LIB_DIR} \
|
||||
-DTENSORRT_DIR=${TENSORRT_DIR} \
|
||||
|
||||
make -j
|
||||
echo "################### build PaddleOCR demo finished ###################"
|
||||
fi
|
||||
113
tests/test.sh
113
tests/test.sh
|
|
@ -1,6 +1,6 @@
|
|||
#!/bin/bash
|
||||
FILENAME=$1
|
||||
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer']
|
||||
# MODE be one of ['lite_train_infer' 'whole_infer' 'whole_train_infer', 'infer', 'cpp_infer']
|
||||
MODE=$2
|
||||
|
||||
dataline=$(cat ${FILENAME})
|
||||
|
|
@ -145,6 +145,33 @@ benchmark_value=$(func_parser_value "${lines[49]}")
|
|||
infer_key1=$(func_parser_key "${lines[50]}")
|
||||
infer_value1=$(func_parser_value "${lines[50]}")
|
||||
|
||||
if [ ${MODE} = "cpp_infer" ]; then
|
||||
# parser cpp inference model
|
||||
cpp_infer_model_dir_list=$(func_parser_value "${lines[53]}")
|
||||
cpp_infer_is_quant=$(func_parser_value "${lines[54]}")
|
||||
# parser cpp inference
|
||||
inference_cmd=$(func_parser_value "${lines[55]}")
|
||||
cpp_use_gpu_key=$(func_parser_key "${lines[56]}")
|
||||
cpp_use_gpu_list=$(func_parser_value "${lines[56]}")
|
||||
cpp_use_mkldnn_key=$(func_parser_key "${lines[57]}")
|
||||
cpp_use_mkldnn_list=$(func_parser_value "${lines[57]}")
|
||||
cpp_cpu_threads_key=$(func_parser_key "${lines[58]}")
|
||||
cpp_cpu_threads_list=$(func_parser_value "${lines[58]}")
|
||||
cpp_batch_size_key=$(func_parser_key "${lines[59]}")
|
||||
cpp_batch_size_list=$(func_parser_value "${lines[59]}")
|
||||
cpp_use_trt_key=$(func_parser_key "${lines[60]}")
|
||||
cpp_use_trt_list=$(func_parser_value "${lines[60]}")
|
||||
cpp_precision_key=$(func_parser_key "${lines[61]}")
|
||||
cpp_precision_list=$(func_parser_value "${lines[61]}")
|
||||
cpp_infer_model_key=$(func_parser_key "${lines[62]}")
|
||||
cpp_image_dir_key=$(func_parser_key "${lines[63]}")
|
||||
cpp_infer_img_dir=$(func_parser_value "${lines[63]}")
|
||||
cpp_save_log_key=$(func_parser_key "${lines[64]}")
|
||||
cpp_benchmark_key=$(func_parser_key "${lines[65]}")
|
||||
cpp_benchmark_value=$(func_parser_value "${lines[65]}")
|
||||
fi
|
||||
|
||||
|
||||
LOG_PATH="./tests/output"
|
||||
mkdir -p ${LOG_PATH}
|
||||
status_log="${LOG_PATH}/results.log"
|
||||
|
|
@ -218,6 +245,71 @@ function func_inference(){
|
|||
done
|
||||
}
|
||||
|
||||
function func_cpp_inference(){
|
||||
IFS='|'
|
||||
_script=$1
|
||||
_model_dir=$2
|
||||
_log_path=$3
|
||||
_img_dir=$4
|
||||
_flag_quant=$5
|
||||
# inference
|
||||
for use_gpu in ${cpp_use_gpu_list[*]}; do
|
||||
if [ ${use_gpu} = "False" ] || [ ${use_gpu} = "cpu" ]; then
|
||||
for use_mkldnn in ${cpp_use_mkldnn_list[*]}; do
|
||||
if [ ${use_mkldnn} = "False" ] && [ ${_flag_quant} = "True" ]; then
|
||||
continue
|
||||
fi
|
||||
for threads in ${cpp_cpu_threads_list[*]}; do
|
||||
for batch_size in ${cpp_batch_size_list[*]}; do
|
||||
_save_log_path="${_log_path}/cpp_infer_cpu_usemkldnn_${use_mkldnn}_threads_${threads}_batchsize_${batch_size}.log"
|
||||
set_infer_data=$(func_set_params "${cpp_image_dir_key}" "${_img_dir}")
|
||||
set_benchmark=$(func_set_params "${cpp_benchmark_key}" "${cpp_benchmark_value}")
|
||||
set_batchsize=$(func_set_params "${cpp_batch_size_key}" "${batch_size}")
|
||||
set_cpu_threads=$(func_set_params "${cpp_cpu_threads_key}" "${threads}")
|
||||
set_model_dir=$(func_set_params "${cpp_infer_model_key}" "${_model_dir}")
|
||||
command="${_script} ${cpp_use_gpu_key}=${use_gpu} ${cpp_use_mkldnn_key}=${use_mkldnn} ${set_cpu_threads} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} > ${_save_log_path} 2>&1 "
|
||||
eval $command
|
||||
last_status=${PIPESTATUS[0]}
|
||||
eval "cat ${_save_log_path}"
|
||||
status_check $last_status "${command}" "${status_log}"
|
||||
done
|
||||
done
|
||||
done
|
||||
elif [ ${use_gpu} = "True" ] || [ ${use_gpu} = "gpu" ]; then
|
||||
for use_trt in ${cpp_use_trt_list[*]}; do
|
||||
for precision in ${cpp_precision_list[*]}; do
|
||||
if [[ ${_flag_quant} = "False" ]] && [[ ${precision} =~ "int8" ]]; then
|
||||
continue
|
||||
fi
|
||||
if [[ ${precision} =~ "fp16" || ${precision} =~ "int8" ]] && [ ${use_trt} = "False" ]; then
|
||||
continue
|
||||
fi
|
||||
if [[ ${use_trt} = "False" || ${precision} =~ "int8" ]] && [ ${_flag_quant} = "True" ]; then
|
||||
continue
|
||||
fi
|
||||
for batch_size in ${cpp_batch_size_list[*]}; do
|
||||
_save_log_path="${_log_path}/cpp_infer_gpu_usetrt_${use_trt}_precision_${precision}_batchsize_${batch_size}.log"
|
||||
set_infer_data=$(func_set_params "${cpp_image_dir_key}" "${_img_dir}")
|
||||
set_benchmark=$(func_set_params "${cpp_benchmark_key}" "${cpp_benchmark_value}")
|
||||
set_batchsize=$(func_set_params "${cpp_batch_size_key}" "${batch_size}")
|
||||
set_tensorrt=$(func_set_params "${cpp_use_trt_key}" "${use_trt}")
|
||||
set_precision=$(func_set_params "${cpp_precision_key}" "${precision}")
|
||||
set_model_dir=$(func_set_params "${cpp_infer_model_key}" "${_model_dir}")
|
||||
command="${_script} ${cpp_use_gpu_key}=${use_gpu} ${set_tensorrt} ${set_precision} ${set_model_dir} ${set_batchsize} ${set_infer_data} ${set_benchmark} > ${_save_log_path} 2>&1 "
|
||||
eval $command
|
||||
last_status=${PIPESTATUS[0]}
|
||||
eval "cat ${_save_log_path}"
|
||||
status_check $last_status "${command}" "${status_log}"
|
||||
|
||||
done
|
||||
done
|
||||
done
|
||||
else
|
||||
echo "Does not support hardware other than CPU and GPU Currently!"
|
||||
fi
|
||||
done
|
||||
}
|
||||
|
||||
if [ ${MODE} = "infer" ]; then
|
||||
GPUID=$3
|
||||
if [ ${#GPUID} -le 0 ];then
|
||||
|
|
@ -252,6 +344,25 @@ if [ ${MODE} = "infer" ]; then
|
|||
Count=$(($Count + 1))
|
||||
done
|
||||
|
||||
elif [ ${MODE} = "cpp_infer" ]; then
|
||||
GPUID=$3
|
||||
if [ ${#GPUID} -le 0 ];then
|
||||
env=" "
|
||||
else
|
||||
env="export CUDA_VISIBLE_DEVICES=${GPUID}"
|
||||
fi
|
||||
# set CUDA_VISIBLE_DEVICES
|
||||
eval $env
|
||||
export Count=0
|
||||
IFS="|"
|
||||
infer_quant_flag=(${cpp_infer_is_quant})
|
||||
for infer_model in ${cpp_infer_model_dir_list[*]}; do
|
||||
#run inference
|
||||
is_quant=${infer_quant_flag[Count]}
|
||||
func_cpp_inference "${inference_cmd}" "${infer_model}" "${LOG_PATH}" "${cpp_infer_img_dir}" ${is_quant}
|
||||
Count=$(($Count + 1))
|
||||
done
|
||||
|
||||
else
|
||||
IFS="|"
|
||||
export Count=0
|
||||
|
|
|
|||
Loading…
Reference in New Issue