mirror of
https://github.com/pjreddie/darknet.git
synced 2023-08-10 21:13:14 +03:00
more detection stuff
This commit is contained in:
Joseph Redmon
parent
c521f87c9e
commit
28d5a4a913
@ -527,11 +527,11 @@ pthread_t load_data_detection_thread(int n, char **paths, int m, int classes, in
|
||||
data load_data_writing(char **paths, int n, int m, int w, int h)
|
||||
{
|
||||
if(m) paths = get_random_paths(paths, n, m);
|
||||
char **replace_paths = find_replace_paths(paths, n, ".png", "label.png");
|
||||
char **replace_paths = find_replace_paths(paths, n, ".png", "-label.png");
|
||||
data d;
|
||||
d.shallow = 0;
|
||||
d.X = load_image_paths(paths, n, w, h);
|
||||
d.y = load_image_paths_gray(replace_paths, n, w/4, h/4);
|
||||
d.y = load_image_paths_gray(replace_paths, n, w/8, h/8);
|
||||
if(m) free(paths);
|
||||
int i;
|
||||
for(i = 0; i < n; ++i) free(replace_paths[i]);
|
||||
|
||||
@ -21,7 +21,7 @@ void draw_detection(image im, float *box, int side, char *label)
|
||||
//printf("%d\n", j);
|
||||
//printf("Prob: %f\n", box[j]);
|
||||
int class = max_index(box+j, classes);
|
||||
if(box[j+class] > .4){
|
||||
if(box[j+class] > .05){
|
||||
//int z;
|
||||
//for(z = 0; z < classes; ++z) printf("%f %s\n", box[j+z], class_names[z]);
|
||||
printf("%f %s\n", box[j+class], class_names[class]);
|
||||
@ -257,8 +257,8 @@ void train_detection(char *cfgfile, char *weightfile)
|
||||
if (imgnet){
|
||||
plist = get_paths("/home/pjreddie/data/imagenet/det.train.list");
|
||||
}else{
|
||||
plist = get_paths("/home/pjreddie/data/voc/no_2012_val.txt");
|
||||
//plist = get_paths("/home/pjreddie/data/voc/no_2007_test.txt");
|
||||
//plist = get_paths("/home/pjreddie/data/voc/no_2012_val.txt");
|
||||
plist = get_paths("/home/pjreddie/data/voc/no_2007_test.txt");
|
||||
//plist = get_paths("/home/pjreddie/data/coco/trainval.txt");
|
||||
//plist = get_paths("/home/pjreddie/data/voc/all2007-2012.txt");
|
||||
}
|
||||
@ -289,7 +289,7 @@ void train_detection(char *cfgfile, char *weightfile)
|
||||
if(i == 100){
|
||||
net.learning_rate *= 10;
|
||||
}
|
||||
if(i%100==0){
|
||||
if(i%1000==0){
|
||||
char buff[256];
|
||||
sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
|
||||
save_weights(net, buff);
|
||||
@ -336,8 +336,8 @@ void validate_detection(char *cfgfile, char *weightfile)
|
||||
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
|
||||
srand(time(0));
|
||||
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/test_2007.txt");
|
||||
list *plist = get_paths("/home/pjreddie/data/voc/val_2012.txt");
|
||||
list *plist = get_paths("/home/pjreddie/data/voc/test_2007.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/val_2012.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/test.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/val.expanded.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
|
||||
@ -388,6 +388,89 @@ void validate_detection(char *cfgfile, char *weightfile)
|
||||
}
|
||||
}
|
||||
|
||||
void do_mask(network net, data d, int offset, int classes, int nuisance, int background, int num_boxes, int per_box)
|
||||
{
|
||||
matrix pred = network_predict_data(net, d);
|
||||
int j, k, class;
|
||||
for(j = 0; j < pred.rows; ++j){
|
||||
printf("%d ", offset + j);
|
||||
for(k = 0; k < pred.cols; k += per_box){
|
||||
float scale = 1.;
|
||||
if (nuisance) scale = 1.-pred.vals[j][k];
|
||||
float max_prob = 0;
|
||||
for (class = 0; class < classes; ++class){
|
||||
float prob = scale*pred.vals[j][k+class+background+nuisance];
|
||||
if(prob > max_prob) max_prob = prob;
|
||||
}
|
||||
printf("%f ", max_prob);
|
||||
}
|
||||
printf("\n");
|
||||
}
|
||||
free_matrix(pred);
|
||||
}
|
||||
|
||||
void mask_detection(char *cfgfile, char *weightfile)
|
||||
{
|
||||
network net = parse_network_cfg(cfgfile);
|
||||
if(weightfile){
|
||||
load_weights(&net, weightfile);
|
||||
}
|
||||
detection_layer layer = get_network_detection_layer(net);
|
||||
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
|
||||
srand(time(0));
|
||||
|
||||
list *plist = get_paths("/home/pjreddie/data/voc/test_2007.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/val_2012.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/test.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/val.expanded.txt");
|
||||
//list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
|
||||
char **paths = (char **)list_to_array(plist);
|
||||
|
||||
int classes = layer.classes;
|
||||
int nuisance = layer.nuisance;
|
||||
int background = (layer.background && !nuisance);
|
||||
int num_boxes = sqrt(get_detection_layer_locations(layer));
|
||||
|
||||
int per_box = 4+classes+background+nuisance;
|
||||
int num_output = num_boxes*num_boxes*per_box;
|
||||
|
||||
int m = plist->size;
|
||||
int i = 0;
|
||||
int splits = 100;
|
||||
|
||||
int nthreads = 4;
|
||||
int t;
|
||||
data *val = calloc(nthreads, sizeof(data));
|
||||
data *buf = calloc(nthreads, sizeof(data));
|
||||
pthread_t *thr = calloc(nthreads, sizeof(data));
|
||||
for(t = 0; t < nthreads; ++t){
|
||||
int num = (i+1+t)*m/splits - (i+t)*m/splits;
|
||||
char **part = paths+((i+t)*m/splits);
|
||||
thr[t] = load_data_thread(part, num, 0, 0, num_output, net.w, net.h, &(buf[t]));
|
||||
}
|
||||
|
||||
clock_t time;
|
||||
for(i = nthreads; i <= splits; i += nthreads){
|
||||
time=clock();
|
||||
for(t = 0; t < nthreads; ++t){
|
||||
pthread_join(thr[t], 0);
|
||||
val[t] = buf[t];
|
||||
}
|
||||
for(t = 0; t < nthreads && i < splits; ++t){
|
||||
int num = (i+1+t)*m/splits - (i+t)*m/splits;
|
||||
char **part = paths+((i+t)*m/splits);
|
||||
thr[t] = load_data_thread(part, num, 0, 0, num_output, net.w, net.h, &(buf[t]));
|
||||
}
|
||||
|
||||
fprintf(stderr, "%d: Loaded: %lf seconds\n", i, sec(clock()-time));
|
||||
for(t = 0; t < nthreads; ++t){
|
||||
do_mask(net, val[t], (i-nthreads+t)*m/splits, classes, nuisance, background, num_boxes, per_box);
|
||||
free_data(val[t]);
|
||||
}
|
||||
time=clock();
|
||||
}
|
||||
}
|
||||
|
||||
void validate_detection_post(char *cfgfile, char *weightfile)
|
||||
{
|
||||
network net = parse_network_cfg(cfgfile);
|
||||
@ -534,6 +617,7 @@ void test_detection(char *cfgfile, char *weightfile)
|
||||
printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
|
||||
draw_detection(im, predictions, 7, "detections");
|
||||
free_image(im);
|
||||
cvWaitKey(0);
|
||||
}
|
||||
}
|
||||
|
||||
@ -551,5 +635,6 @@ void run_detection(int argc, char **argv)
|
||||
else if(0==strcmp(argv[2], "teststuff")) train_detection_teststuff(cfg, weights);
|
||||
else if(0==strcmp(argv[2], "trainloc")) train_localization(cfg, weights);
|
||||
else if(0==strcmp(argv[2], "valid")) validate_detection(cfg, weights);
|
||||
else if(0==strcmp(argv[2], "mask")) mask_detection(cfg, weights);
|
||||
else if(0==strcmp(argv[2], "validpost")) validate_detection_post(cfg, weights);
|
||||
}
|
||||
|
||||
@ -372,15 +372,12 @@ void forward_detection_layer(const detection_layer l, network_state state)
|
||||
l.delta[j+1] = 4 * (state.truth[j+1] - l.output[j+1]);
|
||||
l.delta[j+2] = 4 * (state.truth[j+2] - l.output[j+2]);
|
||||
l.delta[j+3] = 4 * (state.truth[j+3] - l.output[j+3]);
|
||||
if(1){
|
||||
if(0){
|
||||
for (j = offset; j < offset+classes; ++j) {
|
||||
if(state.truth[j]) state.truth[j] = iou;
|
||||
l.delta[j] = state.truth[j] - l.output[j];
|
||||
}
|
||||
}
|
||||
|
||||
/*
|
||||
*/
|
||||
}
|
||||
printf("Avg IOU: %f\n", avg_iou/count);
|
||||
}
|
||||
|
||||
@ -133,20 +133,18 @@ float train_network_datum_gpu(network net, float *x, float *y)
|
||||
float *get_network_output_layer_gpu(network net, int i)
|
||||
{
|
||||
layer l = net.layers[i];
|
||||
cuda_pull_array(l.output_gpu, l.output, l.outputs*l.batch);
|
||||
if(l.type == CONVOLUTIONAL){
|
||||
return l.output;
|
||||
} else if(l.type == DECONVOLUTIONAL){
|
||||
return l.output;
|
||||
} else if(l.type == CONNECTED){
|
||||
cuda_pull_array(l.output_gpu, l.output, l.outputs*l.batch);
|
||||
return l.output;
|
||||
} else if(l.type == DETECTION){
|
||||
cuda_pull_array(l.output_gpu, l.output, l.outputs*l.batch);
|
||||
return l.output;
|
||||
} else if(l.type == MAXPOOL){
|
||||
return l.output;
|
||||
} else if(l.type == SOFTMAX){
|
||||
pull_softmax_layer_output(l);
|
||||
return l.output;
|
||||
}
|
||||
return 0;
|
||||
|
||||
73
src/writing.c
Normal file
73
src/writing.c
Normal file
@ -0,0 +1,73 @@
|
||||
#include "network.h"
|
||||
#include "utils.h"
|
||||
#include "parser.h"
|
||||
|
||||
void train_writing(char *cfgfile, char *weightfile)
|
||||
{
|
||||
data_seed = time(0);
|
||||
srand(time(0));
|
||||
float avg_loss = -1;
|
||||
char *base = basecfg(cfgfile);
|
||||
printf("%s\n", base);
|
||||
network net = parse_network_cfg(cfgfile);
|
||||
if(weightfile){
|
||||
load_weights(&net, weightfile);
|
||||
}
|
||||
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
|
||||
int imgs = 1024;
|
||||
int i = net.seen/imgs;
|
||||
list *plist = get_paths("figures.list");
|
||||
char **paths = (char **)list_to_array(plist);
|
||||
printf("%d\n", plist->size);
|
||||
clock_t time;
|
||||
while(1){
|
||||
++i;
|
||||
time=clock();
|
||||
data train = load_data_writing(paths, imgs, plist->size, 512, 512);
|
||||
float loss = train_network(net, train);
|
||||
#ifdef GPU
|
||||
float *out = get_network_output_gpu(net);
|
||||
#else
|
||||
float *out = get_network_output(net);
|
||||
#endif
|
||||
image pred = float_to_image(64, 64, 1, out);
|
||||
print_image(pred);
|
||||
|
||||
/*
|
||||
image im = float_to_image(256, 256, 3, train.X.vals[0]);
|
||||
image lab = float_to_image(64, 64, 1, train.y.vals[0]);
|
||||
image pred = float_to_image(64, 64, 1, out);
|
||||
show_image(im, "image");
|
||||
show_image(lab, "label");
|
||||
print_image(lab);
|
||||
show_image(pred, "pred");
|
||||
cvWaitKey(0);
|
||||
*/
|
||||
|
||||
net.seen += imgs;
|
||||
if(avg_loss == -1) avg_loss = loss;
|
||||
avg_loss = avg_loss*.9 + loss*.1;
|
||||
printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), net.seen);
|
||||
free_data(train);
|
||||
if((i % 20000) == 0) net.learning_rate *= .1;
|
||||
//if(i%100 == 0 && net.learning_rate > .00001) net.learning_rate *= .97;
|
||||
if(i%1000==0){
|
||||
char buff[256];
|
||||
sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
|
||||
save_weights(net, buff);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
void run_writing(int argc, char **argv)
|
||||
{
|
||||
if(argc < 4){
|
||||
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
|
||||
return;
|
||||
}
|
||||
|
||||
char *cfg = argv[3];
|
||||
char *weights = (argc > 4) ? argv[4] : 0;
|
||||
if(0==strcmp(argv[2], "train")) train_writing(cfg, weights);
|
||||
}
|
||||
|
||||
Loading…
Reference in New Issue
Block a user