Add input as array of images (#168)

Co-authored-by: AndreySorokin7 <andrey_sorokin_nn@mail,ru>

Author: Semyon1104

README.md

@@ -117,10 +117,14 @@ To start the testing process locally, you need to go to the directory
 # **Some files used to create the library**
 ### *neural network models*
 You need to download [Alexnet-model.h5](https://github.com/moizahmed97/Convolutional-Neural-Net-Designer/blob/master/AlexNet-model.h5) to the folder *docs*
-# **How do I get a file with the weights of the model to launch the inference?**
-You need to run the script *parcer.py* that is located in *app/AlexNet* to read weights from a model *Alexnet-model.h5* and the json file with the weights will be stored in the *docs* folder.
+
+# **How do I launch the inference?**
+* You need to run the script *parcer.py* that is located in app/AlexNet to read weights from a model *Alexnet-model.h5* and the json file with the weights will be stored in the *docs* folder.
+* Then put the test images in png format in the folder *docs/input*
+
 # **Accuracy validation**
 To run accuracy validation you need to use the MNIST dataset, which you can download [here](https://github.com/DeepTrackAI/MNIST_dataset/tree/main/mnist/test) and put it in a folder *docs/mnist/mnist/test*
 Now you can run accuracy check - *build\bin\ACC_MNIST.exe*
+
 # **Structure of our library**
 ![Class diagram](./docs/class_diagram.svg)

app/Graph/CMakeLists.txt

@@ -46,12 +46,13 @@ add_custom_command(TARGET ACC_MNIST POST_BUILD
 endif()
 
 file(DOWNLOAD
-    "https://raw.githubusercontent.com/opencv/opencv/4.x/samples/data/lena.jpg"
-    "${CMAKE_CURRENT_BINARY_DIR}/image.jpg"
+    "https://raw.githubusercontent.com/DeepTrackAI/MNIST_dataset/main/mnist/test/1_000008.png"
+    "${CMAKE_SOURCE_DIR}/docs/input/test1.png"
     SHOW_PROGRESS
     STATUS status_code
     LOG log_file
 )
-add_definitions(-DIMAGE1_PATH="${CMAKE_CURRENT_BINARY_DIR}/image.jpg")
+
+add_definitions(-DIMAGE1_PATH="${CMAKE_SOURCE_DIR}/docs/input/")
 add_definitions(-DMODEL_PATH="${CMAKE_SOURCE_DIR}/docs/model_data_alexnet_1.json")
 add_definitions(-DMNIST_PATH="${CMAKE_SOURCE_DIR}/docs/mnist/mnist/test")

app/Graph/build.hpp

@@ -1,3 +1,4 @@
+#include <filesystem>
 #include <iostream>
 #include <opencv2/opencv.hpp>
 #include <stdexcept>

app/Graph/graph_build.cpp

@@ -1,46 +1,56 @@
 #include "build.cpp"
 #include "build.hpp"
 
+namespace fs = std::filesystem;
 using namespace itlab_2023;
 
 int main() {
-  std::string image_path = IMAGE1_PATH;
-  cv::Mat image = cv::imread(image_path);
-  if (image.empty()) {
-    throw std::runtime_error("Failed to load image");
+  std::string image_folder = IMAGE1_PATH;
+  std::vector<std::string> image_paths;
+
+  for (const auto& entry : fs::directory_iterator(image_folder)) {
+    if (entry.path().extension() == ".png") {
+      image_paths.push_back(entry.path().string());
+    }
   }
-  cv::cvtColor(image, image, cv::COLOR_BGR2GRAY);
-  std::vector<cv::Mat> channels;
 
-  cv::split(image, channels);
+  if (image_paths.empty()) {
+    throw std::runtime_error("No PNG images found in the folder");
+  }
+
+  for (const auto& image_path : image_paths) {
+    cv::Mat image = cv::imread(image_path);
+    if (image.empty()) {
+      std::cerr << "Failed to load image: " << image_path << std::endl;
+      continue;
+    }
 
-  int count_pic = 1;
-  std::vector<float> res(count_pic * 28 * 28);
+    cv::cvtColor(image, image, cv::COLOR_BGR2GRAY);
+    std::vector<cv::Mat> channels;
+    cv::split(image, channels);
 
-  for (int i = 0; i < 28; ++i) {
-    for (int j = 0; j < 28; ++j) {
-      res[i * 28 + j] = channels[0].at<uchar>(j, i);
+    std::vector<float> res(28 * 28);
+    for (int i = 0; i < 28; ++i) {
+      for (int j = 0; j < 28; ++j) {
+        res[i * 28 + j] = channels[0].at<uchar>(j, i);
+      }
     }
-  }
-  Shape sh({static_cast<size_t>(count_pic), 1, 28, 28});
-  // move to reshape layer
-  Tensor t = make_tensor<float>(res, sh);
-  Tensor input = t;
-
-  Shape sh1({1, 5, 5, 3});
-  std::vector<float> vec;
-  vec.reserve(75);
-  for (int i = 0; i < 75; ++i) {
-    vec.push_back(3);
-  }
-  Tensor output = make_tensor(vec, sh1);
 
-  build_graph(input, output, true);
+    Shape sh({1, 1, 28, 28});
+    Tensor input = make_tensor<float>(res, sh);
+
+    Shape sh1({1, 5, 5, 3});
+    std::vector<float> vec(75, 3);
+    Tensor output = make_tensor(vec, sh1);
+
+    build_graph(input, output, true);
 
-  std::vector<float> tmp_output = softmax<float>(*output.as<float>());
-  for (size_t i = 0; i < tmp_output.size(); i++) {
-    if (tmp_output[i] >= 1e-6) {
-      std::cout << i << std::endl;
+    std::vector<float> tmp_output = softmax<float>(*output.as<float>());
+    for (size_t i = 0; i < tmp_output.size(); i++) {
+      if (tmp_output[i] >= 1e-6) {
+        std::cout << "Image: " << image_path << " -> Class: " << i << std::endl;
+      }
     }
   }
+  return 0;
 }