void TestWeightMatrix_Backward() {
double epsilon = 1e-3;
int n_outputs = 2;
int n_inputs = 3;
InputLayer input_layer(n_inputs);
OutputLayer output_layer(n_outputs);
WeightMatrix weights(input_layer, output_layer);
weights.set(0, 0, 0.5);
weights.set(1, 0, -2.0);
weights.set(2, 0, 1.5);
weights.set(0, 1, 1.0);
weights.set(1, 1, 0.7);
weights.set(2, 1, -1.0);
weights.setBias(0, 0.8);
weights.setBias(1, -0.3);
std::vector<double> inputs;
inputs.push_back(-2.0);
inputs.push_back(1.0);
inputs.push_back(3.0);
input_layer.receiveInput(inputs);
std::vector<double> transition = weights.fire(input_layer);
output_layer.receiveInput(transition);
assert(output_layer.getInput(0) == 2.3);
assert(output_layer.getInput(1) == -4.6);
// backpropagation step
std::vector<double> actual_outputs;
actual_outputs.push_back(1.0);
actual_outputs.push_back(1.0);
output_layer.computeGradient(actual_outputs);
weights.computeGradient(input_layer, output_layer);
assert(weights.getPartialDerivative(0, 0) > -1.3 - epsilon &&
weights.getPartialDerivative(0, 0) < -1.3 + epsilon);
assert(weights.getPartialDerivative(1, 0) > 0.65 - epsilon &&
weights.getPartialDerivative(1, 0) < 0.65 + epsilon);
assert(weights.getPartialDerivative(2, 0) > 1.95 - epsilon &&
weights.getPartialDerivative(2, 0) < 1.95 + epsilon);
assert(weights.getPartialDerivative(0, 1) > 5.6 - epsilon &&
weights.getPartialDerivative(0, 1) < 5.6 + epsilon);
assert(weights.getPartialDerivative(1, 1) > -2.8 - epsilon &&
weights.getPartialDerivative(1, 1) < -2.8 + epsilon);
assert(weights.getPartialDerivative(2, 1) > -8.4 - epsilon &&
weights.getPartialDerivative(2, 1) < -8.4 + epsilon);
assert(weights.getBiasPartialDerivative(0) < 0.65 + epsilon &&
weights.getBiasPartialDerivative(0) > 0.65 - epsilon);
assert(weights.getBiasPartialDerivative(1) < -2.8 + epsilon &&
weights.getBiasPartialDerivative(1) > -2.8 - epsilon);
printPass("TestWeightMatrix_Backward()");
}
//------------------ANN construction------------------------------------------
void ANN (int N,float In, float * w_ji, float * w_kj, float b, float * y_pj,float & y_pk) {
float x_pi;
input_layer(In,x_pi);
hidden_layer(N,x_pi, w_ji, y_pj);
output_layer(N,y_pj,w_kj,b,y_pk);
}
void TestWeightMatrix_Forward() {
int n_outputs = 2;
InputLayer input_layer(3);
OutputLayer output_layer(n_outputs);
WeightMatrix weights(input_layer, output_layer);
weights.set(0, 0, 0.5);
weights.set(1, 0, -2.0);
weights.set(2, 0, 1.5);
weights.set(0, 1, 1.0);
weights.set(1, 1, 0.7);
weights.set(2, 1, -1.0);
weights.setBias(0, 0.8);
weights.setBias(1, -0.3);
std::vector<double> inputs;
inputs.push_back(-2.0);
inputs.push_back(1.0);
inputs.push_back(3.0);
input_layer.receiveInput(inputs);
std::vector<double> transition = weights.fire(input_layer);
assert(transition.size() == 2);
assert(transition[0] == 2.3);
assert(transition[1] == -4.6);
output_layer.receiveInput(transition);
assert(output_layer.getInput(0) == 2.3);
assert(output_layer.getInput(1) == -4.6);
assert(output_layer.getOutput(0) == 2.3);
assert(output_layer.getOutput(1) == -4.6);
printPass("TestWeightMatrix_Forward()");
}
int main (int argc, char* argv[]) {
// Initialize CN24
Conv::System::Init();
// Capture command line arguments
std::string net_config_fname;
if(argc > 1) {
net_config_fname = std::string(argv[1]);
LOGDEBUG << "Using user specified net: " << net_config_fname;
}
unsigned int CLASSES = 10;
unsigned int INPUTMAPS = 3;
unsigned int BENCHMARK_PASSES_FWD = 30;
unsigned int BENCHMARK_PASSES_BWD = 15;
std::istream* net_config_stream;
if(argc > 1) {
// Open network and dataset configuration files
std::ifstream* net_config_file = new std::ifstream(net_config_fname,std::ios::in);
if(!net_config_file->good()) {
FATAL("Cannot open net configuration file!");
}
net_config_stream = net_config_file;
} else {
LOGINFO << "Using hardcoded net.";
std::stringstream* ss = new std::stringstream(hardcoded_net);
net_config_stream = ss;
}
// Parse network configuration file
Conv::ConfigurableFactory* factory = new Conv::ConfigurableFactory(*net_config_stream, 238238, false);
// Set image dimensions
unsigned int width = 512;
unsigned int height = 512;
Conv::Tensor data_tensor(factory->optimal_settings().pbatchsize, width, height, INPUTMAPS);
data_tensor.Clear();
// Assemble net
Conv::NetGraph graph;
Conv::InputLayer input_layer(data_tensor);
Conv::NetGraphNode input_node(&input_layer);
input_node.is_input = true;
graph.AddNode(&input_node);
bool complete = factory->AddLayers(graph, Conv::NetGraphConnection(&input_node), CLASSES);
if (!complete)
FATAL("Failed completeness check, inspect model!");
factory->InitOptimalSettings();
LOGINFO << "Initializing net, this may take a while..." << std::flush;
graph.Initialize();
graph.SetIsTesting(true);
graph.FeedForward();
graph.BackPropagate();
LOGINFO << "Benchmark information";
LOGINFO << "=====================";
LOGINFO << "Input width : " << width;
LOGINFO << "Input height : " << height;
LOGINFO << "Parallel inputs: " << factory->optimal_settings().pbatchsize;
LOGINFO << "=====================";
LOGINFO << "Running forward benchmark...\n" << std::flush;
{
auto t_begin = std::chrono::system_clock::now();
for(unsigned int p = 0; p < BENCHMARK_PASSES_FWD; p++) {
graph.FeedForward();
std::cout << "." << std::flush;
}
std::cout << "\n";
auto t_end = std::chrono::system_clock::now();
std::chrono::duration<double> t_diff = t_end - t_begin;
double total_pixels = (double)width * (double)height
* (double)(factory->optimal_settings().pbatchsize) * (double)BENCHMARK_PASSES_FWD;
double total_frames = (double)BENCHMARK_PASSES_FWD * (double)(factory->optimal_settings().pbatchsize);
double pixels_per_second = total_pixels / t_diff.count();
double frames_per_second = total_frames / t_diff.count();
LOGINFO << "Forward speed: " << pixels_per_second << " pixel/s";
LOGINFO << "Forward speed: " << frames_per_second << " fps";
LOGINFO << "=====================";
}
graph.SetIsTesting(false);
LOGINFO << "Running forward+backward benchmark...\n" << std::flush;
{
auto t_begin = std::chrono::system_clock::now();
for(unsigned int p = 0; p < BENCHMARK_PASSES_BWD; p++) {
graph.FeedForward();
graph.BackPropagate();
std::cout << "." << std::flush;
}
std::cout << "\n";
auto t_end = std::chrono::system_clock::now();
std::chrono::duration<double> t_diff = t_end - t_begin;
double total_pixels = (double)width * (double)height
* (double)(factory->optimal_settings().pbatchsize) * (double)BENCHMARK_PASSES_BWD;
double total_frames = (double)BENCHMARK_PASSES_BWD * (double)(factory->optimal_settings().pbatchsize);
double pixels_per_second = total_pixels / t_diff.count();
double frames_per_second = total_frames / t_diff.count();
LOGINFO << "F+B speed : " << pixels_per_second << " pixel/s";
LOGINFO << "F+B speed : " << frames_per_second << " fps";
LOGINFO << "=====================";
}
Conv::Tensor* net_output_tensor = &graph.GetDefaultOutputNode()->output_buffers[0].combined_tensor->data;
Conv::Tensor image_output_tensor(1, net_output_tensor->width(), net_output_tensor->height(), 3);
//LOGINFO << "Colorizing..." << std::flush;
//dataset->Colorize(*net_output_tensor, image_output_tensor);
LOGINFO << "DONE!";
LOGEND;
return 0;
}
int main (int argc, char* argv[]) {
if (argc < 6) {
LOGERROR << "USAGE: " << argv[0] << " <dataset config file> <net config file> <net parameter tensor> <input image file> <output image file>";
LOGEND;
return -1;
}
// Capture command line arguments
std::string output_image_fname (argv[5]);
std::string input_image_fname (argv[4]);
std::string param_tensor_fname (argv[3]);
std::string net_config_fname (argv[2]);
std::string dataset_config_fname (argv[1]);
// Initialize CN24
Conv::System::Init();
// Open network and dataset configuration files
std::ifstream param_tensor_file(param_tensor_fname,std::ios::in | std::ios::binary);
std::ifstream net_config_file(net_config_fname,std::ios::in);
std::ifstream dataset_config_file(dataset_config_fname,std::ios::in);
if(!param_tensor_file.good()) {
FATAL("Cannot open param tensor file!");
}
if(!net_config_file.good()) {
FATAL("Cannot open net configuration file!");
}
if(!dataset_config_file.good()) {
FATAL("Cannot open dataset configuration file!");
}
// Parse network configuration file
Conv::ConfigurableFactory* factory = new Conv::ConfigurableFactory(net_config_file, 238238, false);
// Parse dataset configuration file
Conv::TensorStreamDataset* dataset = Conv::TensorStreamDataset::CreateFromConfiguration(dataset_config_file, true);
unsigned int CLASSES = dataset->GetClasses();
// Load image
Conv::Tensor original_data_tensor(input_image_fname);
// Rescale image
unsigned int width = original_data_tensor.width();
unsigned int height = original_data_tensor.height();
if(width & 1)
width++;
if(height & 1)
height++;
if(width & 2)
width+=2;
if(height & 2)
height+=2;
if(width & 4)
width+=4;
if(height & 4)
height+=4;
Conv::Tensor data_tensor(1, width, height, original_data_tensor.maps());
data_tensor.Clear();
Conv::Tensor::CopySample(original_data_tensor, 0, data_tensor, 0);
// Assemble net
Conv::NetGraph graph;
Conv::InputLayer input_layer(data_tensor);
Conv::NetGraphNode input_node(&input_layer);
input_node.is_input = true;
graph.AddNode(&input_node);
bool complete = factory->AddLayers(graph, Conv::NetGraphConnection(&input_node), CLASSES);
if (!complete)
FATAL("Failed completeness check, inspect model!");
graph.Initialize();
// Load network parameters
graph.DeserializeParameters(param_tensor_file);
graph.SetIsTesting(true);
LOGINFO << "Classifying..." << std::flush;
graph.FeedForward();
Conv::Tensor* net_output_tensor = &graph.GetDefaultOutputNode()->output_buffers[0].combined_tensor->data; // &net.buffer(output_layer_id)->data;
Conv::Tensor image_output_tensor(1, net_output_tensor->width(), net_output_tensor->height(), 3);
LOGINFO << "Colorizing..." << std::flush;
dataset->Colorize(*net_output_tensor, image_output_tensor);
// Recrop image down
Conv::Tensor small(1, original_data_tensor.width(), original_data_tensor.height(), 3);
for(unsigned int m = 0; m < 3; m++)
for(unsigned int y = 0; y < small.height(); y++)
for(unsigned int x = 0; x < small.width(); x++)
*small.data_ptr(x,y,m,0) = *image_output_tensor.data_ptr_const(x,y,m,0);
small.WriteToFile(output_image_fname);
LOGINFO << "DONE!";
LOGEND;
return 0;
}