private static void test_writing(string cfgfile, string weightfile, string filename)
{
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(net, 1);
Utils.Rand = new Random(2222222);
var sw = new Stopwatch();
string input = "";
while (true)
{
if (!string.IsNullOrEmpty(filename))
{
input = filename;
}
else
{
Console.Write($"Enter Image Path: ");
input = Console.ReadLine();
if (string.IsNullOrEmpty(input))
{
return;
}
input = input.TrimEnd();
}
Image im = LoadArgs.load_image_color(input, 0, 0);
Network.resize_network(net, im.W, im.H);
Console.Write($"%d %d %d\n", im.H, im.W, im.C);
float[] x = im.Data;
sw.Reset();
sw.Start();
Network.network_predict(net, x);
sw.Stop();
Console.Write($"%s: Predicted ini %f seconds.\n", input, sw.Elapsed.Seconds);
Image pred = Network.get_network_image(net);
Image upsampled = LoadArgs.resize_image(pred, im.W, im.H);
Image thresh = LoadArgs.threshold_image(upsampled, .5f);
pred = thresh;
LoadArgs.show_image(pred, "prediction");
LoadArgs.show_image(im, "orig");
CvInvoke.WaitKey();
CvInvoke.DestroyAllWindows();
if (!string.IsNullOrEmpty(filename))
{
break;
}
}
}
private static void demo_art(string cfgfile, string weightfile, int camIndex)
{
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(net, 1);
Utils.Rand = new Random(2222222);
using (VideoCapture cap = new VideoCapture(camIndex))
{
string window = "ArtJudgementBot9000!!!";
if (cap != null)
{
Utils.Error("Couldn't connect to webcam.\n");
}
int i;
int[] idx = { 37, 401, 434 };
int n = idx.Length;
while (true)
{
Image ini = LoadArgs.get_image_from_stream(cap);
Image inS = LoadArgs.resize_image(ini, net.W, net.H);
LoadArgs.show_image(ini, window);
float[] p = Network.network_predict(net, inS.Data);
Console.Write($"\033[2J");
Console.Write($"\033[1;1H");
float score = 0;
for (i = 0; i < n; ++i)
{
float s = p[idx[i]];
if (s > score)
{
score = s;
}
}
Console.Write($"I APPRECIATE THIS ARTWORK: %10.7f%%\n", score * 100);
Console.Write($"[");
int upper = 30;
for (i = 0; i < upper; ++i)
{
Console.Write($"%c", ((i + .5) < score * upper) ? 219 : ' ');
}
Console.Write($"]\n");
CvInvoke.WaitKey(1);
}
}
}
private static void fetch_in_thread()
{
inputImage = LoadArgs.get_image_from_stream(vidCap);
if (inputImage.Data.Length == 0)
{
Utils.Error("Stream closed.");
}
inS = LoadArgs.resize_image(inputImage, net.W, net.H);
}
private static FloatPair get_rnn_vid_data(Network net, string[] files, int n, int batch, int steps)
{
int b;
Image outIm = Network.get_network_image(net);
int outputSize = outIm.W * outIm.H * outIm.C;
Console.Write($"%d %d %d\n", outIm.W, outIm.H, outIm.C);
float[] feats = new float[net.Batch * batch * outputSize];
for (b = 0; b < batch; ++b)
{
int inputSize = net.W * net.H * net.C;
float[] input = new float[inputSize * net.Batch];
string filename = files[Utils.Rand.Next() % n];
using (VideoCapture cap = new VideoCapture(filename))
{
int frames = (int)cap.GetCaptureProperty(CapProp.FrameCount);
int index = Utils.Rand.Next() % (frames - steps - 2);
if (frames < (steps + 4))
{
--b;
continue;
}
Console.Write($"frames: %d, index: %d\n", frames, index);
cap.SetCaptureProperty(CapProp.PosFrames, index);
int i;
for (i = 0; i < net.Batch; ++i)
{
using (Mat src = cap.QueryFrame())
{
Image im = new Image(src);
LoadArgs.rgbgr_image(im);
Image re = LoadArgs.resize_image(im, net.W, net.H);
Array.Copy(re.Data, 0, input, i * inputSize, inputSize);
}
}
float[] output = Network.network_predict(net, input);
for (i = 0; i < net.Batch; ++i)
{
Array.Copy(output, i * outputSize, feats, (b + i * batch) * outputSize, outputSize);
}
}
}
FloatPair p = new FloatPair();
p.X = feats;
p.Y = new float[feats.Length - outputSize * batch];
Array.Copy(feats, outputSize * batch, p.Y, 0, p.Y.Length);
return(p);
}
private static void optimize_picture(Network net, Image orig, int maxLayer, float scale, float rate, float thresh, bool norm)
{
net.N = maxLayer + 1;
int dx = Utils.Rand.Next() % 16 - 8;
int dy = Utils.Rand.Next() % 16 - 8;
bool flip = Utils.Rand.Next() % 2 != 0;
Image crop = LoadArgs.crop_image(orig, dx, dy, orig.W, orig.H);
Image im = LoadArgs.resize_image(crop, (int)(orig.W * scale), (int)(orig.H * scale));
if (flip)
{
LoadArgs.flip_image(im);
}
Network.resize_network(net, im.W, im.H);
Layer last = net.Layers[net.N - 1];
Image delta = new Image(im.W, im.H, im.C);
NetworkState state = new NetworkState();
state.Input = (float[])im.Data.Clone();
state.Delta = (float[])im.Data.Clone();
Network.forward_network_gpu(net, state);
Blas.copy_ongpu(last.Outputs, last.OutputGpu, last.DeltaGpu);
Array.Copy(last.DeltaGpu, last.Delta, last.Outputs);
calculate_loss(last.Delta, last.Delta, last.Outputs, thresh);
Array.Copy(last.Delta, last.DeltaGpu, last.Outputs);
Network.backward_network_gpu(net, state);
Array.Copy(state.Delta, delta.Data, im.W * im.H * im.C);
if (flip)
{
LoadArgs.flip_image(delta);
}
Image resized = LoadArgs.resize_image(delta, orig.W, orig.H);
Image outi = LoadArgs.crop_image(resized, -dx, -dy, orig.W, orig.H);
if (norm)
{
Utils.normalize_array(outi.Data, outi.W * outi.H * outi.C);
}
Blas.Axpy_cpu(orig.W * orig.H * orig.C, rate, outi.Data, orig.Data);
LoadArgs.constrain_image(orig);
}
private static void test_coco(string cfgfile, string weightfile, string filename, float thresh)
{
Image[][] alphabet = LoadArgs.load_alphabet();
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Layer l = net.Layers[net.N - 1];
Network.set_batch_network(net, 1);
Utils.Rand = new Random(2222222);
float nms = .4f;
var sw = new Stopwatch();
int j;
Box[] boxes = new Box[l.Side * l.Side * l.N];
float[][] probs = new float[l.Side * l.Side * l.N][];
for (j = 0; j < l.Side * l.Side * l.N; ++j) probs[j] = new float[l.Classes];
while (true)
{
string input;
if (!string.IsNullOrEmpty(filename))
{
input = filename;
}
else
{
Console.Write($"Enter Image Path: ");
input = Console.ReadLine();
if (string.IsNullOrEmpty(input)) return;
input = input.TrimEnd();
}
Image im = LoadArgs.load_image_color(input, 0, 0);
Image sized = LoadArgs.resize_image(im, net.W, net.H);
float[] x = sized.Data;
sw.Reset();
sw.Start();
Network.network_predict(net, x);
sw.Stop();
Console.Write($"%s: Predicted ini %f seconds.\n", input, sw.Elapsed.Seconds);
l.get_detection_boxes( 1, 1, thresh, probs, boxes, false);
if (nms != 0) Box.do_nms_sort(boxes, probs, l.Side * l.Side * l.N, l.Classes, nms);
LoadArgs.draw_detections(im, l.Side * l.Side * l.N, thresh, boxes, probs, CocoClasses, alphabet, 80);
LoadArgs.save_image(im, "prediction");
LoadArgs.show_image(im, "predictions");
CvInvoke.WaitKey();
CvInvoke.DestroyAllWindows();
if (!string.IsNullOrEmpty(filename)) break;
}
}
private static void generate_vid_rnn(string cfgfile, string weightfile)
{
Network extractor = Parser.parse_network_cfg("cfg/extractor.recon.cfg");
Parser.load_weights(extractor, "/home/pjreddie/trained/yolo-coco.conv");
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(extractor, 1);
Network.set_batch_network(net, 1);
int i;
VideoCapture cap = new VideoCapture("/extra/vid/ILSVRC2015/Data.Data/VID/snippets/val/ILSVRC2015_val_00007030.mp4");
float[] feat;
float[] next;
next = null;
Image last = null;
for (i = 0; i < 25; ++i)
{
Image im = LoadArgs.get_image_from_stream(cap);
Image re = LoadArgs.resize_image(im, extractor.W, extractor.H);
feat = Network.network_predict(extractor, re.Data);
if (i > 0)
{
Console.Write($"%f %f\n", Utils.mean_array(feat, 14 * 14 * 512), Utils.variance_array(feat, 14 * 14 * 512));
Console.Write($"%f %f\n", Utils.mean_array(next, 14 * 14 * 512), Utils.variance_array(next, 14 * 14 * 512));
Console.Write($"%f\n", Utils.mse_array(feat, 14 * 14 * 512));
Blas.Axpy_cpu(14 * 14 * 512, -1, feat, next);
Console.Write($"%f\n", Utils.mse_array(next, 14 * 14 * 512));
}
next = Network.network_predict(net, feat);
if (i == 24)
{
last = new Image(re);
}
}
for (i = 0; i < 30; ++i)
{
next = Network.network_predict(net, next);
Image newi = save_reconstruction(extractor, last, next, "new", i);
last = newi;
}
}
private static void gun_classifier(string datacfg, string cfgfile, string weightfile, int camIndex, string filename)
{
int[] badCats = { 218, 539, 540, 1213, 1501, 1742, 1911, 2415, 4348, 19223, 368, 369, 370, 1133, 1200, 1306, 2122, 2301, 2537, 2823, 3179, 3596, 3639, 4489, 5107, 5140, 5289, 6240, 6631, 6762, 7048, 7171, 7969, 7984, 7989, 8824, 8927, 9915, 10270, 10448, 13401, 15205, 18358, 18894, 18895, 19249, 19697 };
Console.Write($"Classifier Demo\n");
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(net, 1);
var options = OptionList.read_data_cfg(datacfg);
Utils.Rand = new Random(2222222);
using (VideoCapture cap = !string.IsNullOrEmpty(filename)
? new VideoCapture(filename)
: new VideoCapture(camIndex))
{
int top = OptionList.option_find_int(options, "top", 1);
string nameList = OptionList.option_find_str(options, "names", "");
string[] names = Data.Data.get_labels(nameList);
int[] indexes = new int[top];
if (cap.IsOpened)
{
Utils.Error("Couldn't connect to webcam.\n");
}
float fps = 0;
int i;
while (true)
{
var sw = new Stopwatch();
sw.Start();
Image ini = LoadArgs.get_image_from_stream(cap);
Image inS = LoadArgs.resize_image(ini, net.W, net.H);
LoadArgs.show_image(ini, "Threat Detection");
float[] predictions = Network.network_predict(net, inS.Data);
Network.top_predictions(net, top, indexes);
Console.Write($"\033[2J");
Console.Write($"\033[1;1H");
bool threat = false;
for (i = 0; i < badCats.Length; ++i)
{
int index = badCats[i];
if (predictions[index] > .01)
{
Console.Write($"Threat Detected!\n");
threat = true;
break;
}
}
if (threat)
{
Console.Write($"Scanning...\n");
}
for (i = 0; i < badCats.Length; ++i)
{
int index = badCats[i];
if (predictions[index] > .01)
{
Console.Write($"%s\n", names[index]);
}
}
CvInvoke.WaitKey(10);
sw.Stop();
float curr = 1000.0f / sw.ElapsedMilliseconds;
fps = .9f * fps + .1f * curr;
}
}
}
private static void threat_classifier(string datacfg, string cfgfile, string weightfile, int camIndex, string filename)
{
float threat = 0;
float roll = .2f;
Console.Write($"Classifier Demo\n");
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(net, 1);
var options = OptionList.read_data_cfg(datacfg);
Utils.Rand = new Random(2222222);
using (VideoCapture cap = !string.IsNullOrEmpty(filename)
? new VideoCapture(filename)
: new VideoCapture(camIndex))
{
int top = OptionList.option_find_int(options, "top", 1);
string nameList = OptionList.option_find_str(options, "names", "");
string[] names = Data.Data.get_labels(nameList);
int[] indexes = new int[top];
if (!cap.IsOpened)
{
Utils.Error("Couldn't connect to webcam.\n");
}
float fps = 0;
int i;
int count = 0;
while (true)
{
++count;
var sw = new Stopwatch();
sw.Start();
Image ini = LoadArgs.get_image_from_stream(cap);
if (ini.Data.Length == 0)
{
break;
}
Image inS = LoadArgs.resize_image(ini, net.W, net.H);
Image outo = ini;
int x1 = outo.W / 20;
int y1 = outo.H / 20;
int x2 = 2 * x1;
int y2 = outo.H - outo.H / 20;
int border = (int)(.01f * outo.H);
int h = y2 - y1 - 2 * border;
int w = x2 - x1 - 2 * border;
float[] predictions = Network.network_predict(net, inS.Data);
float currThreat = 0;
currThreat = predictions[0] * 0f +
predictions[1] * .6f +
predictions[2];
threat = roll * currThreat + (1 - roll) * threat;
LoadArgs.draw_box_width(outo, x2 + border, (int)(y1 + .02 * h), (int)(x2 + .5 * w), (int)(y1 + .02 * h + border), border, 0, 0,
0);
if (threat > .97)
{
LoadArgs.draw_box_width(outo, (int)(x2 + .5 * w + border),
(int)(y1 + .02 * h - 2 * border),
(int)(x2 + .5 * w + 6 * border),
(int)(y1 + .02 * h + 3 * border), 3 * border, 1, 0, 0);
}
LoadArgs.draw_box_width(outo, (int)(x2 + .5 * w + border),
(int)(y1 + .02 * h - 2 * border),
(int)(x2 + .5 * w + 6 * border),
(int)(y1 + .02 * h + 3 * border), (int)(.5 * border), 0, 0, 0);
LoadArgs.draw_box_width(outo, x2 + border, (int)(y1 + .42 * h), (int)(x2 + .5 * w), (int)(y1 + .42 * h + border), border, 0, 0,
0);
if (threat > .57)
{
LoadArgs.draw_box_width(outo, (int)(x2 + .5 * w + border),
(int)(y1 + .42 * h - 2 * border),
(int)(x2 + .5 * w + 6 * border),
(int)(y1 + .42 * h + 3 * border), 3 * border, 1, 1, 0);
}
LoadArgs.draw_box_width(outo, (int)(x2 + .5 * w + border),
(int)(y1 + .42 * h - 2 * border),
(int)(x2 + .5 * w + 6 * border),
(int)(y1 + .42 * h + 3 * border), (int)(.5 * border), 0, 0, 0);
LoadArgs.draw_box_width(outo, x1, y1, x2, y2, border, 0, 0, 0);
for (i = 0; i < threat * h; ++i)
{
float ratio = (float)i / h;
float r = (ratio < .5f) ? (2 * (ratio)) : 1;
float g = (ratio < .5f) ? 1 : 1 - 2 * (ratio - .5f);
LoadArgs.draw_box_width(outo, x1 + border, y2 - border - i, x2 - border, y2 - border - i, 1, r, g, 0);
}
Network.top_predictions(net, top, indexes);
string buff = $"/home/pjreddie/tmp/threat_{count:06}";
Console.Write($"\033[2J");
Console.Write($"\033[1;1H");
Console.Write($"\nFPS:%.0f\n", fps);
for (i = 0; i < top; ++i)
{
int index = indexes[i];
Console.Write($"%.1f%%: %s\n", predictions[index] * 100, names[index]);
}
LoadArgs.show_image(outo, "Threat");
CvInvoke.WaitKey(10);
sw.Stop();
float curr = 1000.0f / sw.ElapsedMilliseconds;
fps = .9f * fps + .1f * curr;
}
}
}
private static void demo_classifier(string datacfg, string cfgfile, string weightfile, int camIndex, string filename)
{
Console.Write($"Classifier Demo\n");
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(net, 1);
var options = OptionList.read_data_cfg(datacfg);
Utils.Rand = new Random(2222222);
using (VideoCapture cap = !string.IsNullOrEmpty(filename)
? new VideoCapture(filename)
: new VideoCapture(camIndex))
{
int top = OptionList.option_find_int(options, "top", 1);
string nameList = OptionList.option_find_str(options, "names", "");
string[] names = Data.Data.get_labels(nameList);
int[] indexes = new int[top];
if (cap != null)
{
Utils.Error("Couldn't connect to webcam.\n");
}
float fps = 0;
int i;
while (true)
{
var sw = new Stopwatch();
sw.Start();
Image ini = LoadArgs.get_image_from_stream(cap);
Image inS = LoadArgs.resize_image(ini, net.W, net.H);
LoadArgs.show_image(ini, "Classifier");
float[] predictions = Network.network_predict(net, inS.Data);
if (net.Hierarchy != null)
{
net.Hierarchy.Hierarchy_predictions(predictions, 0, net.Outputs, true);
}
Network.top_predictions(net, top, indexes);
Console.Write($"\033[2J");
Console.Write($"\033[1;1H");
Console.Write($"\nFPS:%.0f\n", fps);
for (i = 0; i < top; ++i)
{
int index = indexes[i];
Console.Write($"%.1f%%: %s\n", predictions[index] * 100, names[index]);
}
CvInvoke.WaitKey(10);
sw.Stop();
float curr = 1000.0f / sw.ElapsedMilliseconds;
fps = .9f * fps + .1f * curr;
}
}
}
public static void run_nightmare(List <string> args)
{
if (args.Count < 4)
{
Console.Error.Write($"usage: %s %s [cfg] [weights] [Image] [Layer] [options! (optional)]\n", args[0], args[1]);
return;
}
string cfg = args[2];
string weights = args[3];
string input = args[4];
int maxLayer = int.Parse(args[5]);
int range = Utils.find_int_arg(args, "-range", 1);
bool norm = Utils.find_int_arg(args, "-norm", 1) != 0;
int rounds = Utils.find_int_arg(args, "-rounds", 1);
int iters = Utils.find_int_arg(args, "-iters", 10);
int octaves = Utils.find_int_arg(args, "-octaves", 4);
float zoom = Utils.find_int_arg(args, "-zoom", 1);
float rate = Utils.find_int_arg(args, "-rate", .04f);
float thresh = Utils.find_int_arg(args, "-thresh", 1);
float rotate = Utils.find_int_arg(args, "-rotate", 0);
float momentum = Utils.find_int_arg(args, "-momentum", .9f);
float lambda = Utils.find_int_arg(args, "-lambda", .01f);
string prefix = Utils.find_int_arg(args, "-prefix", "");
bool reconstruct = Utils.find_arg(args, "-reconstruct");
int smoothSize = Utils.find_int_arg(args, "-smooth", 1);
Network net = Parser.parse_network_cfg(cfg);
Parser.load_weights(net, weights);
string cfgbase = Utils.Basecfg(cfg);
string imbase = Utils.Basecfg(input);
Network.set_batch_network(net, 1);
Image im = LoadArgs.load_image_color(input, 0, 0);
float[] features = new float[0];
Image update = null;
if (reconstruct)
{
Network.resize_network(net, im.W, im.H);
int zz = 0;
Network.network_predict(net, im.Data);
Image outIm = Network.get_network_image(net);
Image crop = LoadArgs.crop_image(outIm, zz, zz, outIm.W - 2 * zz, outIm.H - 2 * zz);
Image fIm = LoadArgs.resize_image(crop, outIm.W, outIm.H);
Console.Write($"%d features\n", outIm.W * outIm.H * outIm.C);
im = LoadArgs.resize_image(im, im.W, im.H);
fIm = LoadArgs.resize_image(fIm, fIm.W, fIm.H);
features = fIm.Data;
int i;
for (i = 0; i < 14 * 14 * 512; ++i)
{
features[i] += Utils.rand_uniform(-.19f, .19f);
}
im = LoadArgs.make_random_image(im.W, im.H, im.C);
update = new Image(im.W, im.H, im.C);
}
int e;
int n;
for (e = 0; e < rounds; ++e)
{
Console.Error.Write($"Iteration: ");
for (n = 0; n < iters; ++n)
{
Console.Error.Write($"%d, ", n);
if (reconstruct)
{
reconstruct_picture(net, features, im, update, rate, momentum, lambda, smoothSize, 1);
//if ((n+1)%30 == 0) rate *= .5;
LoadArgs.show_image(im, "reconstruction");
CvInvoke.WaitKey(10);
}
else
{
int layer = maxLayer + Utils.Rand.Next() % range - range / 2;
int octave = Utils.Rand.Next() % octaves;
optimize_picture(net, im, layer, 1 / (float)Math.Pow(1.33333333, octave), rate, thresh, norm);
}
}
Console.Error.Write($"done\n");
string buff;
if (!string.IsNullOrEmpty(prefix))
{
buff = $"{prefix}_{imbase}_{cfgbase}_{maxLayer}_{e:06}%s/%s_%s_%d_%06d";
}
else
{
buff = $"{imbase}_{cfgbase}_{maxLayer}_{e:06}";
}
Console.Write($"%d %s\n", e, buff);
LoadArgs.save_image(im, buff);
//LoadArgs.show_image(im, buff);
//CvInvoke.WaitKey();
if (rotate != 0)
{
Image rot = LoadArgs.rotate_image(im, rotate);
im = rot;
}
Image crop = LoadArgs.crop_image(im, (int)(im.W * (1f - zoom) / 2f), (int)(im.H * (1f - zoom) / 2f), (int)(im.W * zoom), (int)(im.H * zoom));
Image resized = LoadArgs.resize_image(crop, im.W, im.H);
im = resized;
}
}
private static void validate_yolo_recall(string cfgfile, string weightfile)
{
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(net, 1);
Console.Error.Write($"Learning Rate: %g, Momentum: %g, Decay: %g\n", net.LearningRate, net.Momentum, net.Decay);
string[] paths = Data.Data.GetPaths("Data.Data/voc.2007.test");
Layer l = net.Layers[net.N - 1];
int classes = l.Classes;
int side = l.Side;
int j, k;
Box[] boxes = new Box[side * side * l.N];
float[][] probs = new float[side * side * l.N][];
for (j = 0; j < side * side * l.N; ++j)
{
probs[j] = new float[classes];
}
int m = paths.Length;
int i = 0;
float thresh = .001f;
float iouThresh = .5f;
int total = 0;
int correct = 0;
int proposals = 0;
float avgIou = 0;
for (i = 0; i < m; ++i)
{
string path = paths[i];
Image orig = LoadArgs.load_image_color(path, 0, 0);
Image sized = LoadArgs.resize_image(orig, net.W, net.H);
string id = Utils.Basecfg(path);
Network.network_predict(net, sized.Data);
l.get_detection_boxes(orig.W, orig.H, thresh, probs, boxes, true);
string labelpath;
Utils.find_replace(path, "images", "labels", out labelpath);
Utils.find_replace(labelpath, "JPEGImages", "labels", out labelpath);
Utils.find_replace(labelpath, ".jpg", ".txt", out labelpath);
Utils.find_replace(labelpath, ".JPEG", ".txt", out labelpath);
int numLabels = 0;
BoxLabel[] truth = Data.Data.read_boxes(labelpath, ref numLabels);
for (k = 0; k < side * side * l.N; ++k)
{
if (probs[k][0] > thresh)
{
++proposals;
}
}
for (j = 0; j < numLabels; ++j)
{
++total;
Box t = new Box(truth[j].X, truth[j].Y, truth[j].W, truth[j].H);
float bestIou = 0;
for (k = 0; k < side * side * l.N; ++k)
{
float iou = Box.box_iou(boxes[k], t);
if (probs[k][0] > thresh && iou > bestIou)
{
bestIou = iou;
}
}
avgIou += bestIou;
if (bestIou > iouThresh)
{
++correct;
}
}
Console.Error.Write($"%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals / (i + 1), avgIou * 100 / total, 100f * correct / total);
}
}
public static void test_detector(string datacfg, string cfgfile, string weightfile, string filename, float thresh)
{
var options = OptionList.read_data_cfg(datacfg);
string nameList = OptionList.option_find_str(options, "names", "Data.Data/names.list");
string[] names = Data.Data.get_labels(nameList);
Image[][] alphabet = LoadArgs.load_alphabet();
Network net = Parser.parse_network_cfg(cfgfile);
if (string.IsNullOrEmpty(weightfile))
{
Parser.load_weights(net, weightfile);
}
Network.set_batch_network(net, 1);
Utils.Rand = new Random(2222222);
var sw = new Stopwatch();
string input = "";
int j;
float nms = .4f;
while (true)
{
if (!string.IsNullOrEmpty(filename))
{
input = filename;
}
else
{
Console.Write($"Enter Image Path: ");
input = Console.ReadLine();
if (string.IsNullOrEmpty(input))
{
return;
}
input = input.TrimEnd();
}
Image im = LoadArgs.load_image_color(input, 0, 0);
Image sized = LoadArgs.resize_image(im, net.W, net.H);
Layer l = net.Layers[net.N - 1];
Box[] boxes = new Box[l.W * l.H * l.N];
float[][] probs = new float[l.W * l.H * l.N][];
for (j = 0; j < l.W * l.H * l.N; ++j)
{
probs[j] = new float[l.Classes];
}
float[] x = sized.Data;
sw.Start();
Network.network_predict(net, x);
sw.Stop();
Console.Write($"%s: Predicted ini %f seconds.\n", input, sw.Elapsed.Seconds);
Layer.get_region_boxes(l, 1, 1, thresh, probs, boxes, false, new int[0]);
if (nms != 0)
{
Box.do_nms_sort(boxes, probs, l.W * l.H * l.N, l.Classes, nms);
}
LoadArgs.draw_detections(im, l.W * l.H * l.N, thresh, boxes, probs, names, alphabet, l.Classes);
LoadArgs.save_image(im, "predictions");
LoadArgs.show_image(im, "predictions");
CvInvoke.WaitKey();
CvInvoke.DestroyAllWindows();
if (!string.IsNullOrEmpty(filename))
{
break;
}
}
}