mirrors
/
PaddleClas
mirror of https://github.com/PaddlePaddle/PaddleClas.git
1
0
Fork 0
Code Issues Projects Releases Wiki Activity

code format for lite_shitu

pull/2146/head
dongshuilong 2022-07-12 11:01:03 +08:00
parent fa87707d2f
commit c839a87cff
15 changed files with 149 additions and 168 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

8
deploy/lite_shitu/include/config_parser.h
View File

@ -29,16 +29,16 @@
namespace PPShiTu {
void load_jsonf(std::string jsonfile, Json::Value& jsondata);
void load_jsonf(std::string jsonfile, Json::Value &jsondata);
// Inference model configuration parser
class ConfigPaser {
public:
public:
ConfigPaser() {}
~ConfigPaser() {}
bool load_config(const Json::Value& config) {
bool load_config(const Json::Value &config) {
// Get model arch : YOLO, SSD, RetinaNet, RCNN, Face
if (config["Global"].isMember("det_arch")) {
@ -89,4 +89,4 @@ class ConfigPaser {
std::vector<int> fpn_stride_;
};
} // namespace PPShiTu
} // namespace PPShiTu

9
deploy/lite_shitu/include/feature_extractor.h
View File

@ -18,13 +18,13 @@
#include <arm_neon.h>
#include <chrono>
#include <fstream>
#include <include/preprocess_op.h>
#include <iostream>
#include <math.h>
#include <opencv2/opencv.hpp>
#include <stdlib.h>
#include <sys/time.h>
#include <vector>
#include <include/preprocess_op.h>
using namespace paddle::lite_api; // NOLINT
using namespace std;
@ -72,13 +72,14 @@ public:
}
}
void RunRecModel(const cv::Mat &img, double &cost_time, std::vector<float> &feature);
//void PostProcess(std::vector<float> &feature);
void RunRecModel(const cv::Mat &img, double &cost_time,
std::vector<float> &feature);
// void PostProcess(std::vector<float> &feature);
void FeatureNorm(std::vector<float> &featuer);
private:
std::shared_ptr<PaddlePredictor> predictor;
//std::vector<std::string> label_list;
// std::vector<std::string> label_list;
std::vector<float> mean = {0.485f, 0.456f, 0.406f};
std::vector<float> std = {0.229f, 0.224f, 0.225f};
double scale = 0.00392157;

61
deploy/lite_shitu/include/object_detector.h
View File

@ -16,24 +16,24 @@
#include <ctime>
#include <memory>
#include <stdlib.h>
#include <string>
#include <utility>
#include <vector>
#include <stdlib.h>
#include "json/json.h"
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include "json/json.h"
#include "paddle_api.h" // NOLINT
#include "paddle_api.h" // NOLINT
#include "include/config_parser.h"
#include "include/picodet_postprocess.h"
#include "include/preprocess_op.h"
#include "include/utils.h"
#include "include/picodet_postprocess.h"
using namespace paddle::lite_api; // NOLINT
using namespace paddle::lite_api; // NOLINT
namespace PPShiTu {
@ -41,53 +41,51 @@ namespace PPShiTu {
std::vector<int> GenerateColorMap(int num_class);
// Visualiztion Detection Result
cv::Mat VisualizeResult(const cv::Mat& img,
const std::vector<PPShiTu::ObjectResult>& results,
const std::vector<std::string>& lables,
const std::vector<int>& colormap,
const bool is_rbox);
cv::Mat VisualizeResult(const cv::Mat &img,
const std::vector<PPShiTu::ObjectResult> &results,
const std::vector<std::string> &lables,
const std::vector<int> &colormap, const bool is_rbox);
class ObjectDetector {
public:
explicit ObjectDetector(const Json::Value& config,
const std::string& model_dir,
int cpu_threads = 1,
public:
explicit ObjectDetector(const Json::Value &config,
const std::string &model_dir, int cpu_threads = 1,
const int batch_size = 1) {
config_.load_config(config);
printf("config created\n");
preprocessor_.Init(config_.preprocess_info_);
printf("before object detector\n");
if(config["Global"]["det_model_path"].as<std::string>().empty()){
std::cout << "Please set [det_model_path] in config file" << std::endl;
exit(-1);
if (config["Global"]["det_model_path"].as<std::string>().empty()) {
std::cout << "Please set [det_model_path] in config file" << std::endl;
exit(-1);
}
LoadModel(config["Global"]["det_model_path"].as<std::string>(), cpu_threads);
printf("create object detector\n"); }
LoadModel(config["Global"]["det_model_path"].as<std::string>(),
cpu_threads);
printf("create object detector\n");
}
// Load Paddle inference model
void LoadModel(std::string model_file, int num_theads);
// Run predictor
void Predict(const std::vector<cv::Mat>& imgs,
const int warmup = 0,
void Predict(const std::vector<cv::Mat> &imgs, const int warmup = 0,
const int repeats = 1,
std::vector<PPShiTu::ObjectResult>* result = nullptr,
std::vector<int>* bbox_num = nullptr,
std::vector<double>* times = nullptr);
std::vector<PPShiTu::ObjectResult> *result = nullptr,
std::vector<int> *bbox_num = nullptr,
std::vector<double> *times = nullptr);
// Get Model Label list
const std::vector<std::string>& GetLabelList() const {
const std::vector<std::string> &GetLabelList() const {
return config_.label_list_;
}
private:
private:
// Preprocess image and copy data to input buffer
void Preprocess(const cv::Mat& image_mat);
void Preprocess(const cv::Mat &image_mat);
// Postprocess result
void Postprocess(const std::vector<cv::Mat> mats,
std::vector<PPShiTu::ObjectResult>* result,
std::vector<int> bbox_num,
bool is_rbox);
std::vector<PPShiTu::ObjectResult> *result,
std::vector<int> bbox_num, bool is_rbox);
std::shared_ptr<PaddlePredictor> predictor_;
Preprocessor preprocessor_;
@ -96,7 +94,6 @@ class ObjectDetector {
std::vector<int> out_bbox_num_data_;
float threshold_;
ConfigPaser config_;
};
} // namespace PPShiTu
} // namespace PPShiTu

26
deploy/lite_shitu/include/picodet_postprocess.h
View File

@ -14,25 +14,23 @@
#pragma once
#include <string>
#include <vector>
#include <memory>
#include <utility>
#include <ctime>
#include <memory>
#include <numeric>
#include <string>
#include <utility>
#include <vector>
#include "include/utils.h"
namespace PPShiTu {
void PicoDetPostProcess(std::vector<PPShiTu::ObjectResult>* results,
std::vector<const float *> outs,
std::vector<int> fpn_stride,
std::vector<float> im_shape,
std::vector<float> scale_factor,
float score_threshold = 0.3,
float nms_threshold = 0.5,
int num_class = 80,
int reg_max = 7);
void PicoDetPostProcess(std::vector<PPShiTu::ObjectResult> *results,
std::vector<const float *> outs,
std::vector<int> fpn_stride,
std::vector<float> im_shape,
std::vector<float> scale_factor,
float score_threshold = 0.3, float nms_threshold = 0.5,
int num_class = 80, int reg_max = 7);
} // namespace PPShiTu
} // namespace PPShiTu

84
deploy/lite_shitu/include/preprocess_op.h
View File

@ -21,16 +21,16 @@
#include <utility>
#include <vector>
#include "json/json.h"
#include <opencv2/core/core.hpp>
#include <opencv2/highgui/highgui.hpp>
#include <opencv2/imgproc/imgproc.hpp>
#include "json/json.h"
namespace PPShiTu {
// Object for storing all preprocessed data
class ImageBlob {
public:
public:
// image width and height
std::vector<float> im_shape_;
// Buffer for image data after preprocessing
@ -45,20 +45,20 @@ class ImageBlob {
// Abstraction of preprocessing opration class
class PreprocessOp {
public:
virtual void Init(const Json::Value& item) = 0;
virtual void Run(cv::Mat* im, ImageBlob* data) = 0;
public:
virtual void Init(const Json::Value &item) = 0;
virtual void Run(cv::Mat *im, ImageBlob *data) = 0;
};
class InitInfo : public PreprocessOp {
public:
virtual void Init(const Json::Value& item) {}
virtual void Run(cv::Mat* im, ImageBlob* data);
public:
virtual void Init(const Json::Value &item) {}
virtual void Run(cv::Mat *im, ImageBlob *data);
};
class NormalizeImage : public PreprocessOp {
public:
virtual void Init(const Json::Value& item) {
public:
virtual void Init(const Json::Value &item) {
mean_.clear();
scale_.clear();
for (auto tmp : item["mean"]) {
@ -70,11 +70,11 @@ class NormalizeImage : public PreprocessOp {
is_scale_ = item["is_scale"].as<bool>();
}
virtual void Run(cv::Mat* im, ImageBlob* data);
virtual void Run(cv::Mat *im, ImageBlob *data);
void Run_feature(cv::Mat *im, const std::vector<float> &mean,
const std::vector<float> &std, float scale);
const std::vector<float> &std, float scale);
private:
private:
// CHW or HWC
std::vector<float> mean_;
std::vector<float> scale_;
@ -82,15 +82,15 @@ class NormalizeImage : public PreprocessOp {
};
class Permute : public PreprocessOp {
public:
virtual void Init(const Json::Value& item) {}
virtual void Run(cv::Mat* im, ImageBlob* data);
public:
virtual void Init(const Json::Value &item) {}
virtual void Run(cv::Mat *im, ImageBlob *data);
void Run_feature(const cv::Mat *im, float *data);
};
class Resize : public PreprocessOp {
public:
virtual void Init(const Json::Value& item) {
public:
virtual void Init(const Json::Value &item) {
interp_ = item["interp"].as<int>();
// max_size_ = item["target_size"].as<int>();
keep_ratio_ = item["keep_ratio"].as<bool>();
@ -101,12 +101,13 @@ class Resize : public PreprocessOp {
}
// Compute best resize scale for x-dimension, y-dimension
std::pair<float, float> GenerateScale(const cv::Mat& im);
std::pair<float, float> GenerateScale(const cv::Mat &im);
virtual void Run(cv::Mat* im, ImageBlob* data);
void Run_feature(const cv::Mat &img, cv::Mat &resize_img, int max_size_len, int size=0);
virtual void Run(cv::Mat *im, ImageBlob *data);
void Run_feature(const cv::Mat &img, cv::Mat &resize_img, int max_size_len,
int size = 0);
private:
private:
int interp_;
bool keep_ratio_;
std::vector<int> target_size_;
@ -115,46 +116,43 @@ class Resize : public PreprocessOp {
// Models with FPN need input shape % stride == 0
class PadStride : public PreprocessOp {
public:
virtual void Init(const Json::Value& item) {
public:
virtual void Init(const Json::Value &item) {
stride_ = item["stride"].as<int>();
}
virtual void Run(cv::Mat* im, ImageBlob* data);
virtual void Run(cv::Mat *im, ImageBlob *data);
private:
private:
int stride_;
};
class TopDownEvalAffine : public PreprocessOp {
public:
virtual void Init(const Json::Value& item) {
public:
virtual void Init(const Json::Value &item) {
trainsize_.clear();
for (auto tmp : item["trainsize"]) {
trainsize_.emplace_back(tmp.as<int>());
}
}
virtual void Run(cv::Mat* im, ImageBlob* data);
virtual void Run(cv::Mat *im, ImageBlob *data);
private:
private:
int interp_ = 1;
std::vector<int> trainsize_;
};
void CropImg(cv::Mat& img,
cv::Mat& crop_img,
std::vector<int>& area,
std::vector<float>& center,
std::vector<float>& scale,
void CropImg(cv::Mat &img, cv::Mat &crop_img, std::vector<int> &area,
std::vector<float> &center, std::vector<float> &scale,
float expandratio = 0.15);
class Preprocessor {
public:
void Init(const Json::Value& config_node) {
public:
void Init(const Json::Value &config_node) {
// initialize image info at first
ops_["InitInfo"] = std::make_shared<InitInfo>();
for (const auto& item : config_node) {
for (const auto &item : config_node) {
auto op_name = item["type"].as<std::string>();
ops_[op_name] = CreateOp(op_name);
@ -162,7 +160,7 @@ class Preprocessor {
}
}
std::shared_ptr<PreprocessOp> CreateOp(const std::string& name) {
std::shared_ptr<PreprocessOp> CreateOp(const std::string &name) {
if (name == "DetResize") {
return std::make_shared<Resize>();
} else if (name == "DetPermute") {
@ -180,13 +178,13 @@ class Preprocessor {
return nullptr;
}
void Run(cv::Mat* im, ImageBlob* data);
void Run(cv::Mat *im, ImageBlob *data);
public:
public:
static const std::vector<std::string> RUN_ORDER;
private:
private:
std::unordered_map<std::string, std::shared_ptr<PreprocessOp>> ops_;
};
} // namespace PPShiTu
} // namespace PPShiTu

5
deploy/lite_shitu/include/utils.h
View File

@ -43,12 +43,11 @@ void nms(std::vector<ObjectResult> &input_boxes, float nms_threshold,
template <typename T>
static inline bool SortScorePairDescend(const std::pair<float, T> &pair1,
const std::pair<float, T> &pair2){
const std::pair<float, T> &pair2) {
return pair1.first > pair2.first;
}
float RectOverlap(const ObjectResult &a,
const ObjectResult &b);
float RectOverlap(const ObjectResult &a, const ObjectResult &b);
inline void
GetMaxScoreIndex(const std::vector<ObjectResult> &det_result,

2
deploy/lite_shitu/include/vector_search.h
View File

@ -70,4 +70,4 @@ private:
std::vector<faiss::Index::idx_t> I;
SearchResult sr;
};
}
} // namespace PPShiTu

2
deploy/lite_shitu/src/config_parser.cc
View File

@ -29,4 +29,4 @@ void load_jsonf(std::string jsonfile, Json::Value &jsondata) {
}
}
} // namespace PPShiTu
} // namespace PPShiTu

23
deploy/lite_shitu/src/feature_extractor.cc
View File

@ -17,8 +17,7 @@
#include <numeric>
namespace PPShiTu {
void FeatureExtract::RunRecModel(const cv::Mat &img,
double &cost_time,
void FeatureExtract::RunRecModel(const cv::Mat &img, double &cost_time,
std::vector<float> &feature) {
// Read img
cv::Mat img_fp;
@ -34,7 +33,7 @@ void FeatureExtract::RunRecModel(const cv::Mat &img,
// const float *dimg = reinterpret_cast<const float *>(img_fp.data);
// NeonMeanScale(dimg, data0, img_fp.rows * img_fp.cols);
for(int i=0; i < input.size(); ++i){
for (int i = 0; i < input.size(); ++i) {
data0[i] = input[i];
}
@ -44,7 +43,7 @@ void FeatureExtract::RunRecModel(const cv::Mat &img,
// Get output and post process
std::unique_ptr<const Tensor> output_tensor(
std::move(this->predictor->GetOutput(0))); //only one output
std::move(this->predictor->GetOutput(0))); // only one output
auto end = std::chrono::system_clock::now();
auto duration =
std::chrono::duration_cast<std::chrono::microseconds>(end - start);
@ -52,7 +51,7 @@ void FeatureExtract::RunRecModel(const cv::Mat &img,
std::chrono::microseconds::period::num /
std::chrono::microseconds::period::den;
//do postprocess
// do postprocess
int output_size = 1;
for (auto dim : output_tensor->shape()) {
output_size *= dim;
@ -60,15 +59,15 @@ void FeatureExtract::RunRecModel(const cv::Mat &img,
feature.resize(output_size);
output_tensor->CopyToCpu(feature.data());
//postprocess include sqrt or binarize.
// postprocess include sqrt or binarize.
FeatureNorm(feature);
return;
}
void FeatureExtract::FeatureNorm(std::vector<float> &feature){
float feature_sqrt = std::sqrt(std::inner_product(
feature.begin(), feature.end(), feature.begin(), 0.0f));
for (int i = 0; i < feature.size(); ++i)
feature[i] /= feature_sqrt;
}
void FeatureExtract::FeatureNorm(std::vector<float> &feature) {
float feature_sqrt = std::sqrt(std::inner_product(
feature.begin(), feature.end(), feature.begin(), 0.0f));
for (int i = 0; i < feature.size(); ++i)
feature[i] /= feature_sqrt;
}
} // namespace PPShiTu

10
deploy/lite_shitu/src/main.cc
View File

@ -27,8 +27,8 @@
#include "include/feature_extractor.h"
#include "include/object_detector.h"
#include "include/preprocess_op.h"
#include "include/vector_search.h"
#include "include/utils.h"
#include "include/vector_search.h"
#include "json/json.h"
Json::Value RT_Config;
@ -216,7 +216,7 @@ int main(int argc, char **argv) {
// add the whole image for recognition to improve recall
PPShiTu::ObjectResult result_whole_img = {
{0, 0, srcimg.cols, srcimg.rows}, 0, 1.0};
{0, 0, srcimg.cols, srcimg.rows}, 0, 1.0};
det_result.push_back(result_whole_img);
// get rec result
@ -233,9 +233,10 @@ int main(int argc, char **argv) {
// do vectore search
search_result = searcher.Search(features.data(), det_result.size());
for (int i = 0; i < det_result.size(); ++i) {
det_result[i].confidence = search_result.D[search_result.return_k * i];
det_result[i].confidence = search_result.D[search_result.return_k * i];
}
NMSBoxes(det_result, searcher.GetThreshold(), rec_nms_threshold, indeices);
NMSBoxes(det_result, searcher.GetThreshold(), rec_nms_threshold,
indeices);
PrintResult(img_path, det_result, searcher, search_result);
batch_imgs.clear();
@ -243,7 +244,6 @@ int main(int argc, char **argv) {
features.clear();
feature.clear();
indeices.clear();
}
}
return 0;

69
deploy/lite_shitu/src/object_detector.cc
View File

@ -13,9 +13,9 @@
// limitations under the License.
#include <sstream>
// for setprecision
#include "include/object_detector.h"
#include <chrono>
#include <iomanip>
#include "include/object_detector.h"
namespace PPShiTu {
@ -30,10 +30,10 @@ void ObjectDetector::LoadModel(std::string model_file, int num_theads) {
}
// Visualiztion MaskDetector results
cv::Mat VisualizeResult(const cv::Mat& img,
const std::vector<PPShiTu::ObjectResult>& results,
const std::vector<std::string>& lables,
const std::vector<int>& colormap,
cv::Mat VisualizeResult(const cv::Mat &img,
const std::vector<PPShiTu::ObjectResult> &results,
const std::vector<std::string> &lables,
const std::vector<int> &colormap,
const bool is_rbox = false) {
cv::Mat vis_img = img.clone();
for (int i = 0; i < results.size(); ++i) {
@ -75,24 +75,18 @@ cv::Mat VisualizeResult(const cv::Mat& img,
origin.y = results[i].rect[1];
// Configure text background
cv::Rect text_back = cv::Rect(results[i].rect[0],
results[i].rect[1] - text_size.height,
text_size.width,
text_size.height);
cv::Rect text_back =
cv::Rect(results[i].rect[0], results[i].rect[1] - text_size.height,
text_size.width, text_size.height);
// Draw text, and background
cv::rectangle(vis_img, text_back, roi_color, -1);
cv::putText(vis_img,
text,
origin,
font_face,
font_scale,
cv::Scalar(255, 255, 255),
thickness);
cv::putText(vis_img, text, origin, font_face, font_scale,
cv::Scalar(255, 255, 255), thickness);
}
return vis_img;
}
void ObjectDetector::Preprocess(const cv::Mat& ori_im) {
void ObjectDetector::Preprocess(const cv::Mat &ori_im) {
// Clone the image : keep the original mat for postprocess
cv::Mat im = ori_im.clone();
// cv::cvtColor(im, im, cv::COLOR_BGR2RGB);
@ -100,7 +94,7 @@ void ObjectDetector::Preprocess(const cv::Mat& ori_im) {
}
void ObjectDetector::Postprocess(const std::vector<cv::Mat> mats,
std::vector<PPShiTu::ObjectResult>* result,
std::vector<PPShiTu::ObjectResult> *result,
std::vector<int> bbox_num,
bool is_rbox = false) {
result->clear();
@ -156,12 +150,11 @@ void ObjectDetector::Postprocess(const std::vector<cv::Mat> mats,
}
}
void ObjectDetector::Predict(const std::vector<cv::Mat>& imgs,
const int warmup,
void ObjectDetector::Predict(const std::vector<cv::Mat> &imgs, const int warmup,
const int repeats,
std::vector<PPShiTu::ObjectResult>* result,
std::vector<int>* bbox_num,
std::vector<double>* times) {
std::vector<PPShiTu::ObjectResult> *result,
std::vector<int> *bbox_num,
std::vector<double> *times) {
auto preprocess_start = std::chrono::steady_clock::now();
int batch_size = imgs.size();
@ -180,29 +173,29 @@ void ObjectDetector::Predict(const std::vector<cv::Mat>& imgs,
scale_factor_all[bs_idx * 2 + 1] = inputs_.scale_factor_[1];
// TODO: reduce cost time
in_data_all.insert(
in_data_all.end(), inputs_.im_data_.begin(), inputs_.im_data_.end());
in_data_all.insert(in_data_all.end(), inputs_.im_data_.begin(),
inputs_.im_data_.end());
}
auto preprocess_end = std::chrono::steady_clock::now();
std::vector<const float *> output_data_list_;
// Prepare input tensor
auto input_names = predictor_->GetInputNames();
for (const auto& tensor_name : input_names) {
for (const auto &tensor_name : input_names) {
auto in_tensor = predictor_->GetInputByName(tensor_name);
if (tensor_name == "image") {
int rh = inputs_.in_net_shape_[0];
int rw = inputs_.in_net_shape_[1];
in_tensor->Resize({batch_size, 3, rh, rw});
auto* inptr = in_tensor->mutable_data<float>();
auto *inptr = in_tensor->mutable_data<float>();
std::copy_n(in_data_all.data(), in_data_all.size(), inptr);
} else if (tensor_name == "im_shape") {
in_tensor->Resize({batch_size, 2});
auto* inptr = in_tensor->mutable_data<float>();
auto *inptr = in_tensor->mutable_data<float>();
std::copy_n(im_shape_all.data(), im_shape_all.size(), inptr);
} else if (tensor_name == "scale_factor") {
in_tensor->Resize({batch_size, 2});
auto* inptr = in_tensor->mutable_data<float>();
auto *inptr = in_tensor->mutable_data<float>();
std::copy_n(scale_factor_all.data(), scale_factor_all.size(), inptr);
}
}
@ -216,7 +209,7 @@ void ObjectDetector::Predict(const std::vector<cv::Mat>& imgs,
if (config_.arch_ == "PicoDet") {
for (int j = 0; j < output_names.size(); j++) {
auto output_tensor = predictor_->GetTensor(output_names[j]);
const float* outptr = output_tensor->data<float>();
const float *outptr = output_tensor->data<float>();
std::vector<int64_t> output_shape = output_tensor->shape();
output_data_list_.push_back(outptr);
}
@ -242,7 +235,7 @@ void ObjectDetector::Predict(const std::vector<cv::Mat>& imgs,
if (config_.arch_ == "PicoDet") {
for (int i = 0; i < output_names.size(); i++) {
auto output_tensor = predictor_->GetTensor(output_names[i]);
const float* outptr = output_tensor->data<float>();
const float *outptr = output_tensor->data<float>();
std::vector<int64_t> output_shape = output_tensor->shape();
if (i == 0) {
num_class = output_shape[2];
@ -268,16 +261,15 @@ void ObjectDetector::Predict(const std::vector<cv::Mat>& imgs,
std::cerr << "[WARNING] No object detected." << std::endl;
}
output_data_.resize(output_size);
std::copy_n(
output_tensor->mutable_data<float>(), output_size, output_data_.data());
std::copy_n(output_tensor->mutable_data<float>(), output_size,
output_data_.data());
int out_bbox_num_size = 1;
for (int j = 0; j < out_bbox_num_shape.size(); ++j) {
out_bbox_num_size *= out_bbox_num_shape[j];
}
out_bbox_num_data_.resize(out_bbox_num_size);
std::copy_n(out_bbox_num->mutable_data<int>(),
out_bbox_num_size,
std::copy_n(out_bbox_num->mutable_data<int>(), out_bbox_num_size,
out_bbox_num_data_.data());
}
// Postprocessing result
@ -285,9 +277,8 @@ void ObjectDetector::Predict(const std::vector<cv::Mat>& imgs,
result->clear();
if (config_.arch_ == "PicoDet") {
PPShiTu::PicoDetPostProcess(
result, output_data_list_, config_.fpn_stride_,
inputs_.im_shape_, inputs_.scale_factor_,
config_.nms_info_["score_threshold"].as<float>(),
result, output_data_list_, config_.fpn_stride_, inputs_.im_shape_,
inputs_.scale_factor_, config_.nms_info_["score_threshold"].as<float>(),
config_.nms_info_["nms_threshold"].as<float>(), num_class, reg_max);
bbox_num->push_back(result->size());
} else {
@ -326,4 +317,4 @@ std::vector<int> GenerateColorMap(int num_class) {
return colormap;
}
} // namespace PPShiTu
} // namespace PPShiTu

6
deploy/lite_shitu/src/picodet_postprocess.cc
View File

@ -47,9 +47,9 @@ int activation_function_softmax(const _Tp *src, _Tp *dst, int length) {
}
// PicoDet decode
PPShiTu::ObjectResult
disPred2Bbox(const float *&dfl_det, int label, float score, int x, int y,
int stride, std::vector<float> im_shape, int reg_max) {
PPShiTu::ObjectResult disPred2Bbox(const float *&dfl_det, int label,
float score, int x, int y, int stride,
std::vector<float> im_shape, int reg_max) {
float ct_x = (x + 0.5) * stride;
float ct_y = (y + 0.5) * stride;
std::vector<float> dis_pred;

6
deploy/lite_shitu/src/preprocess_op.cc
View File

@ -47,7 +47,7 @@ void NormalizeImage::Run(cv::Mat *im, ImageBlob *data) {
}
void NormalizeImage::Run_feature(cv::Mat *im, const std::vector<float> &mean,
const std::vector<float> &std, float scale) {
const std::vector<float> &std, float scale) {
(*im).convertTo(*im, CV_32FC3, scale);
for (int h = 0; h < im->rows; h++) {
for (int w = 0; w < im->cols; w++) {
@ -127,8 +127,8 @@ std::pair<float, float> Resize::GenerateScale(const cv::Mat &im) {
return resize_scale;
}
void Resize::Run_feature(const cv::Mat &img, cv::Mat &resize_img, int resize_short_size,
int size) {
void Resize::Run_feature(const cv::Mat &img, cv::Mat &resize_img,
int resize_short_size, int size) {
int resize_h = 0;
int resize_w = 0;
if (size > 0) {

4
deploy/lite_shitu/src/utils.cc
View File

@ -54,9 +54,7 @@ void nms(std::vector<ObjectResult> &input_boxes, float nms_threshold,
}
}
float RectOverlap(const ObjectResult &a,
const ObjectResult &b) {
float RectOverlap(const ObjectResult &a, const ObjectResult &b) {
float Aa = (a.rect[2] - a.rect[0] + 1) * (a.rect[3] - a.rect[1] + 1);
float Ab = (b.rect[2] - b.rect[0] + 1) * (b.rect[3] - b.rect[1] + 1);

2
deploy/lite_shitu/src/vector_search.cc
View File

@ -64,4 +64,4 @@ const SearchResult &VectorSearch::Search(float *feature, int query_number) {
const std::string &VectorSearch::GetLabel(faiss::Index::idx_t ind) {
return this->id_map.at(ind);
}
}
} // namespace PPShiTu