I created small application with OpenVINO which takes 3-channel image and apply to it neural net. NN was trained for segmentation and must find ellipses. But in output blob I see white ellipse and many noise pixels. Could anybody help me find an error?
In applied archive there are:
- TestOpVnn.cpp - main program (one file in MSVS project) - this file attached singly
- Neural net in IR format (zf_unet_224)
- Basic neural net in Keras format (h5+json)
- Input image (input.png)
- Expected output image (output.png)
- Output image which gave us OpenVINO program (output_image.bmp)
Images:
Input:
Expected output:
Real output:
My application code:
#include "pch.h"
#include <iostream>
#include <string>
#include <vector>
// Without next pragmas there are many warnings, how correctly fix them?
#pragma warning(push)
#pragma warning(disable:4251)
#pragma warning(disable:4275)
#include <inference_engine.hpp>
#pragma warning(pop)
#include <opencv2/opencv.hpp>
template<class T>
std::ostream & operator << (std::ostream &out, const std::vector<T> &vec)
{
out << "{ ";
for (size_t i = 0; i + 1 < vec.size(); ++i)
{
out << vec << ", ";
}
if (!vec.empty())
{
out << vec.back();
}
out << " }";
return out;
}
namespace io_info
{
template<class T>
void i_print_info(const T & i_info)
{
std::cout << " io_info->getPrecision() = " << i_info->getPrecision() << std::endl;
std::cout << " io_info->getLayout () = " << i_info->getLayout() << std::endl;
std::cout << " io_info->name () = " << i_info->name() << std::endl;
std::cout << " io_info->dims = " << i_info->getTensorDesc().getDims() << std::endl;
std::cout << std::endl;
}
}
namespace OV_helper
{
/**
* @brief Sets image data stored in cv::Mat object to a given Blob object.
* @param orig_image - given cv::Mat object with an image data.
* @param blob - Blob object which to be filled by an image data.
* @param batchIndex - batch index of an image inside of the blob.
*/
template <typename T>
void matU8ToBlob(const cv::Mat& orig_image, InferenceEngine::Blob::Ptr& blob, int batchIndex = 0) {
InferenceEngine::SizeVector blobSize = blob->getTensorDesc().getDims();
const size_t width = blobSize[3];
const size_t height = blobSize[2];
const size_t channels = blobSize[1];
T* blob_data = blob->buffer().as<T*>();
cv::Mat resized_image(orig_image);
if (static_cast<int>(width) != orig_image.size().width ||
static_cast<int>(height) != orig_image.size().height) {
cv::resize(orig_image, resized_image, cv::Size(width, height));
}
int batchOffset = batchIndex * width * height * channels;
for (size_t c = 0; c < channels; c++) {
for (size_t h = 0; h < height; h++) {
for (size_t w = 0; w < width; w++) {
blob_data[batchOffset + c * width * height + h * width + w] =
resized_image.at<cv::Vec3b>(h, w);
}
}
}
}
// Extracts 1-channel image from the FP32 blob
cv::Mat blobFP32_to_img1ch(const InferenceEngine::Blob::Ptr &blob, int batchIndex = 0)
{
InferenceEngine::SizeVector blobSize = blob->getTensorDesc().getDims();
std::cout << " blobSize = " << blobSize << std::endl;
const size_t width = blobSize[3];
const size_t height = blobSize[2];
const size_t channels = blobSize[1];
std::cout << " width = " << width << std::endl;
std::cout << " height = " << height << std::endl;
std::cout << " channels = " << channels << std::endl;
if (channels != 1)
{
throw std::runtime_error("OV_helper::blobFP32_to_img1ch() : Invalid numbers of channels.");
}
cv::Mat img(height, width, CV_8UC1);
float* blob_data = blob->buffer().as<float*>();
if ( static_cast<int>(width ) != img.size().width
|| static_cast<int>(height) != img.size().height)
{
throw std::runtime_error("OV_helper::blobFP32_to_img1ch() : Invalid img sizes.");
}
int batchOffset = batchIndex * width * height * channels;
for (size_t c = 0; c < channels; c++) {
for (size_t h = 0; h < height; h++) {
for (size_t w = 0; w < width; w++) {
img.at<uchar>(h, w) = 255 * blob_data[batchOffset + c * width * height + h * width + w];
}
}
}
return img;
}
} // namespace OV_helper
int main()
{
try
{
// Read model name
std::string model_name;
std::cin >> model_name;
std::string model_xml = model_name + ".xml";
std::string model_bin = model_name + ".bin";
std::cout << std::endl << " net source = " << "[ " + model_xml + ", " + model_bin + " ]" << std::endl;
// Read image name
std::string image_name;
std::cin >> image_name;
cv::Mat1f frame = cv::imread(image_name, cv::IMREAD_GRAYSCALE);
std::cout << " image source = " << image_name << std::endl << std::endl;
// 1 - Read neural net
// Without next 5 strings net didn't load. How load the net correctly?
#ifdef WIN32
auto extension_ptr = InferenceEngine::make_so_pointer<::InferenceEngine::IExtension>(L"cpu_extension_avx2.dll");
#else
auto extension_ptr = make_so_pointer<::InferenceEngine::IExtension>("libcpu_extension.so");
#endif
InferenceEngine::Core core;
InferenceEngine::CNNNetReader network_reader;
network_reader.ReadNetwork(model_xml);
network_reader.ReadWeights(model_bin);
// 2 - Get net from reader class
auto network = network_reader.getNetwork();
// 3 - Get i/o info
InferenceEngine::InputsDataMap input_info = network.getInputsInfo();
InferenceEngine::OutputsDataMap output_info = network.getOutputsInfo();
if (input_info.size() != 1)
{
throw std::runtime_error("item.size() != 1");
}
if (output_info.size() != 1)
{
throw std::runtime_error("item.size() != 1");
}
std::cout << " input_info.size() = " << input_info.size() << " output_info.size() = " << output_info.size() << std::endl << std::endl;
std::cout << "#input/output names: " << std::endl;
std::string input_name = input_info .begin()->first;
std::string output_name = output_info.begin()->first;
std::cout << " input_info.begin() = " << input_name << " output_info.begin() = " << output_name << std::endl << std::endl;
// 5 - Load net
core.AddExtension(extension_ptr,"CPU");
auto executable_network = core.LoadNetwork(network, "CPU");
// 6 - Create an inference request
auto infer_request = executable_network.CreateInferRequest();
// Print input parameters
std::cout << "#Input info: " << std::endl;
io_info::i_print_info(input_info.at(input_name));
// Print output parameters
InferenceEngine::DataPtr o_info = output_info.at(output_name);
std::cout << "#Output info: " << std::endl;
std::cout << " io_info->getPrecision() = " << o_info->getPrecision () << std::endl;
std::cout << " io_info->getLayout () = " << o_info->getLayout () << std::endl;
std::cout << " io_info->getName () = " << o_info->getName () << std::endl;
std::cout << " io_info->dims = " << o_info->getTensorDesc().getDims() << std::endl;
std::cout << std::endl;
auto input = infer_request.GetBlob(input_name);
// Normalizing of image to [-1/2 .. 1/2)
frame = frame / 256.f - 0.5f;
OV_helper::matU8ToBlob<float>(frame, input);
infer_request.SetBlob(input_name, input);
// 8 - Infer request
infer_request.Infer();
// 9 - Parse an answer
auto output = infer_request.GetBlob(output_name);
auto img = OV_helper::blobFP32_to_img1ch(output);
cv::imwrite("output_image.bmp", img);
}
catch (std::exception &e)
{
std::cout << "Exception raised: " << e.what() << std::endl;
}
std::cout << "Ok return.\n" << std::endl;
return 0;
}
Link Copied
