From 393dc8eb6f3a9dd92ec665200444186c1addc5d2 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 9 Sep 2015 12:48:40 -0700
Subject: [PATCH] stable
---
Makefile | 2 +-
cfg/darknet.cfg | 14 +-
cfg/yolo.cfg | 7 +-
src/darknet.c | 3 +
src/detection_layer.c | 17 ++-
src/network.c | 13 +-
src/network.h | 6 +-
src/parser.c | 37 ++++-
src/yolo.c | 18 +--
src/yoloplus.c | 334 ++++++++++++++++++++++++++++++++++++++++++
10 files changed, 415 insertions(+), 36 deletions(-)
create mode 100644 src/yoloplus.c
diff --git a/Makefile b/Makefile
index 65264de..581b6d7 100644
--- a/Makefile
+++ b/Makefile
@@ -34,7 +34,7 @@ CFLAGS+= -DGPU
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif
-OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o imagenet.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o region_layer.o layer.o compare.o
+OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o imagenet.o captcha.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o dice.o yolo.o region_layer.o layer.o compare.o yoloplus.o
ifeq ($(GPU), 1)
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o softmax_layer_kernels.o network_kernels.o avgpool_layer_kernels.o
endif
diff --git a/cfg/darknet.cfg b/cfg/darknet.cfg
index f52ff3f..eb1310a 100644
--- a/cfg/darknet.cfg
+++ b/cfg/darknet.cfg
@@ -27,7 +27,7 @@ pad=1
activation=leaky
[maxpool]
-size=3
+size=2
stride=2
[convolutional]
@@ -38,7 +38,7 @@ pad=1
activation=leaky
[maxpool]
-size=3
+size=2
stride=2
[convolutional]
@@ -49,7 +49,7 @@ pad=1
activation=leaky
[maxpool]
-size=3
+size=2
stride=2
[convolutional]
@@ -60,7 +60,7 @@ pad=1
activation=leaky
[maxpool]
-size=3
+size=2
stride=2
[convolutional]
@@ -71,7 +71,7 @@ pad=1
activation=leaky
[maxpool]
-size=3
+size=2
stride=2
[convolutional]
@@ -82,7 +82,7 @@ pad=1
activation=leaky
[maxpool]
-size=3
+size=2
stride=2
[convolutional]
@@ -99,7 +99,7 @@ probability=.5
[connected]
output=1000
-activation=linear
+activation=leaky
[softmax]
diff --git a/cfg/yolo.cfg b/cfg/yolo.cfg
index eef0b69..88176a6 100644
--- a/cfg/yolo.cfg
+++ b/cfg/yolo.cfg
@@ -4,10 +4,15 @@ subdivisions=64
height=448
width=448
channels=3
-learning_rate=0.01
+learning_rate=0.001
momentum=0.9
decay=0.0005
+policy=steps
+steps=50, 5000
+scales=10, .1
+max_batches = 8000
+
[crop]
crop_width=448
crop_height=448
diff --git a/src/darknet.c b/src/darknet.c
index 3709ed1..833f89e 100644
--- a/src/darknet.c
+++ b/src/darknet.c
@@ -13,6 +13,7 @@
extern void run_imagenet(int argc, char **argv);
extern void run_yolo(int argc, char **argv);
+extern void run_yoloplus(int argc, char **argv);
extern void run_coco(int argc, char **argv);
extern void run_writing(int argc, char **argv);
extern void run_captcha(int argc, char **argv);
@@ -178,6 +179,8 @@ int main(int argc, char **argv)
average(argc, argv);
} else if (0 == strcmp(argv[1], "yolo")){
run_yolo(argc, argv);
+ } else if (0 == strcmp(argv[1], "yoloplus")){
+ run_yoloplus(argc, argv);
} else if (0 == strcmp(argv[1], "coco")){
run_coco(argc, argv);
} else if (0 == strcmp(argv[1], "compare")){
diff --git a/src/detection_layer.c b/src/detection_layer.c
index 80b606b..daeee04 100644
--- a/src/detection_layer.c
+++ b/src/detection_layer.c
@@ -85,11 +85,12 @@ void forward_detection_layer(const detection_layer l, network_state state)
int size = get_detection_layer_output_size(l) * l.batch;
memset(l.delta, 0, size * sizeof(float));
for (i = 0; i < l.batch*locations; ++i) {
- int classes = l.objectness+l.classes;
+ int classes = (l.objectness || l.background)+l.classes;
int offset = i*(classes+l.coords);
for (j = offset; j < offset+classes; ++j) {
*(l.cost) += pow(state.truth[j] - l.output[j], 2);
l.delta[j] = state.truth[j] - l.output[j];
+ if(l.background && j == offset) l.delta[j] *= .1;
}
box truth;
@@ -115,9 +116,15 @@ void forward_detection_layer(const detection_layer l, network_state state)
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(l.rescore){
- for (j = offset; j < offset+classes; ++j) {
- if(state.truth[j]) state.truth[j] = iou;
- l.delta[j] = state.truth[j] - l.output[j];
+ if(l.objectness){
+ state.truth[offset] = iou;
+ l.delta[offset] = state.truth[offset] - l.output[offset];
+ }
+ else{
+ for (j = offset; j < offset+classes; ++j) {
+ if(state.truth[j]) state.truth[j] = iou;
+ l.delta[j] = state.truth[j] - l.output[j];
+ }
}
}
}
@@ -145,7 +152,7 @@ void backward_detection_layer(const detection_layer l, network_state state)
if (l.objectness) {
}else if (l.background) gradient_array(l.output + out_i, l.coords, LOGISTIC, l.delta + out_i);
- for(j = 0; j < l.coords; ++j){
+ for (j = 0; j < l.coords; ++j){
state.delta[in_i++] += l.delta[out_i++];
}
if(l.joint) state.delta[in_i-l.coords-l.classes-l.joint] += latent_delta;
diff --git a/src/network.c b/src/network.c
index d823c15..af4861a 100644
--- a/src/network.c
+++ b/src/network.c
@@ -29,15 +29,26 @@ int get_current_batch(network net)
float get_current_rate(network net)
{
int batch_num = get_current_batch(net);
+ int i;
+ float rate;
switch (net.policy) {
case CONSTANT:
return net.learning_rate;
case STEP:
- return net.learning_rate * pow(net.gamma, batch_num/net.step);
+ return net.learning_rate * pow(net.scale, batch_num/net.step);
+ case STEPS:
+ rate = net.learning_rate;
+ for(i = 0; i < net.num_steps; ++i){
+ if(net.steps[i] > batch_num) return rate;
+ rate *= net.scales[i];
+ }
+ return rate;
case EXP:
return net.learning_rate * pow(net.gamma, batch_num);
case POLY:
return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power);
+ case SIG:
+ return net.learning_rate * (1/(1+exp(net.gamma*(batch_num - net.step))));
default:
fprintf(stderr, "Policy is weird!\n");
return net.learning_rate;
diff --git a/src/network.h b/src/network.h
index 85e5dbc..5a39f08 100644
--- a/src/network.h
+++ b/src/network.h
@@ -8,7 +8,7 @@
#include "data.h"
typedef enum {
- CONSTANT, STEP, EXP, POLY
+ CONSTANT, STEP, EXP, POLY, STEPS, SIG
} learning_rate_policy;
typedef struct {
@@ -25,9 +25,13 @@ typedef struct {
float learning_rate;
float gamma;
+ float scale;
float power;
int step;
int max_batches;
+ float *scales;
+ int *steps;
+ int num_steps;
int inputs;
int h, w, c;
diff --git a/src/parser.c b/src/parser.c
index b9f6cb6..94dc0fa 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -169,7 +169,7 @@ detection_layer parse_detection(list *options, size_params params)
int rescore = option_find_int(options, "rescore", 0);
int joint = option_find_int(options, "joint", 0);
int objectness = option_find_int(options, "objectness", 0);
- int background = 0;
+ int background = option_find_int(options, "background", 0);
detection_layer layer = make_detection_layer(params.batch, params.inputs, classes, coords, joint, rescore, background, objectness);
return layer;
}
@@ -312,6 +312,8 @@ learning_rate_policy get_policy(char *s)
if (strcmp(s, "constant")==0) return CONSTANT;
if (strcmp(s, "step")==0) return STEP;
if (strcmp(s, "exp")==0) return EXP;
+ if (strcmp(s, "sigmoid")==0) return SIG;
+ if (strcmp(s, "steps")==0) return STEPS;
fprintf(stderr, "Couldn't find policy %s, going with constant\n", s);
return CONSTANT;
}
@@ -337,9 +339,36 @@ void parse_net_options(list *options, network *net)
net->policy = get_policy(policy_s);
if(net->policy == STEP){
net->step = option_find_int(options, "step", 1);
- net->gamma = option_find_float(options, "gamma", 1);
+ net->scale = option_find_float(options, "scale", 1);
+ } else if (net->policy == STEPS){
+ char *l = option_find(options, "steps");
+ char *p = option_find(options, "scales");
+ if(!l || !p) error("STEPS policy must have steps and scales in cfg file");
+
+ int len = strlen(l);
+ int n = 1;
+ int i;
+ for(i = 0; i < len; ++i){
+ if (l[i] == ',') ++n;
+ }
+ int *steps = calloc(n, sizeof(int));
+ float *scales = calloc(n, sizeof(float));
+ for(i = 0; i < n; ++i){
+ int step = atoi(l);
+ float scale = atof(p);
+ l = strchr(l, ',')+1;
+ p = strchr(p, ',')+1;
+ steps[i] = step;
+ scales[i] = scale;
+ }
+ net->scales = scales;
+ net->steps = steps;
+ net->num_steps = n;
} else if (net->policy == EXP){
net->gamma = option_find_float(options, "gamma", 1);
+ } else if (net->policy == SIG){
+ net->gamma = option_find_float(options, "gamma", 1);
+ net->step = option_find_int(options, "step", 1);
} else if (net->policy == POLY){
net->power = option_find_float(options, "power", 1);
}
@@ -401,10 +430,10 @@ network parse_network_cfg(char *filename)
l = parse_dropout(options, params);
l.output = net.layers[count-1].output;
l.delta = net.layers[count-1].delta;
- #ifdef GPU
+#ifdef GPU
l.output_gpu = net.layers[count-1].output_gpu;
l.delta_gpu = net.layers[count-1].delta_gpu;
- #endif
+#endif
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
diff --git a/src/yolo.c b/src/yolo.c
index 61a5344..9b229e2 100644
--- a/src/yolo.c
+++ b/src/yolo.c
@@ -66,7 +66,6 @@ void train_yolo(char *cfgfile, char *weightfile)
load_weights(&net, weightfile);
}
detection_layer layer = get_network_detection_layer(net);
- printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
int imgs = 128;
int i = *net.seen/imgs;
@@ -75,10 +74,6 @@ void train_yolo(char *cfgfile, char *weightfile)
int N = plist->size;
paths = (char **)list_to_array(plist);
- if(i*imgs > N*80){
- net.layers[net.n-1].joint = 1;
- net.layers[net.n-1].objectness = 0;
- }
if(i*imgs > N*120){
net.layers[net.n-1].rescore = 1;
}
@@ -102,7 +97,7 @@ void train_yolo(char *cfgfile, char *weightfile)
pthread_t load_thread = load_data_in_thread(args);
clock_t time;
- while(i*imgs < N*130){
+ while(get_current_batch(net) < net.max_batches){
i += 1;
time=clock();
pthread_join(load_thread, 0);
@@ -115,19 +110,10 @@ void train_yolo(char *cfgfile, char *weightfile)
if (avg_loss < 0) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
- printf("%d: %f, %f avg, %lf seconds, %d images, epoch: %f\n", i, loss, avg_loss, sec(clock()-time), i*imgs, ((float)i)*imgs/N);
-
- if((i-1)*imgs <= N && i*imgs > N){
- fprintf(stderr, "First stage done\n");
- net.learning_rate *= 10;
- char buff[256];
- sprintf(buff, "%s/%s_first_stage.weights", backup_directory, base);
- save_weights(net, buff);
- }
+ printf("%d: %f, %f avg, %lf seconds, %f rate, %d images, epoch: %f\n", get_current_batch(net), loss, avg_loss, sec(clock()-time), get_current_rate(net), *net.seen, (float)*net.seen/N);
if((i-1)*imgs <= 80*N && i*imgs > N*80){
fprintf(stderr, "Second stage done.\n");
- net.learning_rate *= .1;
char buff[256];
sprintf(buff, "%s/%s_second_stage.weights", backup_directory, base);
save_weights(net, buff);
diff --git a/src/yoloplus.c b/src/yoloplus.c
new file mode 100644
index 0000000..dcae7bc
--- /dev/null
+++ b/src/yoloplus.c
@@ -0,0 +1,334 @@
+#include "network.h"
+#include "detection_layer.h"
+#include "cost_layer.h"
+#include "utils.h"
+#include "parser.h"
+#include "box.h"
+
+#ifdef OPENCV
+#include "opencv2/highgui/highgui_c.h"
+#endif
+
+char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
+
+void draw_yoloplus(image im, float *box, int side, int objectness, char *label, float thresh)
+{
+ int classes = 20;
+ int elems = 4+classes+objectness;
+ int j;
+ int r, c;
+
+ for(r = 0; r < side; ++r){
+ for(c = 0; c < side; ++c){
+ j = (r*side + c) * elems;
+ float scale = 1;
+ if(objectness) scale = 1 - box[j++];
+ int class = max_index(box+j, classes);
+ if(scale * box[j+class] > thresh){
+ int width = sqrt(scale*box[j+class])*5 + 1;
+ printf("%f %s\n", scale * box[j+class], voc_names[class]);
+ float red = get_color(0,class,classes);
+ float green = get_color(1,class,classes);
+ float blue = get_color(2,class,classes);
+
+ j += classes;
+ float x = box[j+0];
+ float y = box[j+1];
+ x = (x+c)/side;
+ y = (y+r)/side;
+ float w = box[j+2]; //*maxwidth;
+ float h = box[j+3]; //*maxheight;
+ h = h*h;
+ w = w*w;
+
+ int left = (x-w/2)*im.w;
+ int right = (x+w/2)*im.w;
+ int top = (y-h/2)*im.h;
+ int bot = (y+h/2)*im.h;
+ draw_box_width(im, left, top, right, bot, width, red, green, blue);
+ }
+ }
+ }
+ show_image(im, label);
+}
+
+void train_yoloplus(char *cfgfile, char *weightfile)
+{
+ char *train_images = "/home/pjreddie/data/voc/test/train.txt";
+ char *backup_directory = "/home/pjreddie/backup/";
+ srand(time(0));
+ data_seed = time(0);
+ char *base = basecfg(cfgfile);
+ printf("%s\n", base);
+ float avg_loss = -1;
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ detection_layer layer = get_network_detection_layer(net);
+ int imgs = 128;
+ int i = *net.seen/imgs;
+
+ char **paths;
+ list *plist = get_paths(train_images);
+ int N = plist->size;
+ paths = (char **)list_to_array(plist);
+
+ if(i*imgs > N*120){
+ net.layers[net.n-1].rescore = 1;
+ }
+ data train, buffer;
+
+ int classes = layer.classes;
+ int background = layer.objectness;
+ int side = sqrt(get_detection_layer_locations(layer));
+
+ load_args args = {0};
+ args.w = net.w;
+ args.h = net.h;
+ args.paths = paths;
+ args.n = imgs;
+ args.m = plist->size;
+ args.classes = classes;
+ args.num_boxes = side;
+ args.background = background;
+ args.d = &buffer;
+ args.type = DETECTION_DATA;
+
+ pthread_t load_thread = load_data_in_thread(args);
+ clock_t time;
+ while(get_current_batch(net) < net.max_batches){
+ i += 1;
+ time=clock();
+ pthread_join(load_thread, 0);
+ train = buffer;
+ load_thread = load_data_in_thread(args);
+
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+ time=clock();
+ float loss = train_network(net, train);
+ if (avg_loss < 0) avg_loss = loss;
+ avg_loss = avg_loss*.9 + loss*.1;
+
+ printf("%d: %f, %f avg, %lf seconds, %f rate, %d images, epoch: %f\n", get_current_batch(net), loss, avg_loss, sec(clock()-time), get_current_rate(net), *net.seen, (float)*net.seen/N);
+
+ if((i-1)*imgs <= 80*N && i*imgs > N*80){
+ fprintf(stderr, "Second stage done.\n");
+ char buff[256];
+ sprintf(buff, "%s/%s_second_stage.weights", backup_directory, base);
+ save_weights(net, buff);
+ net.layers[net.n-1].joint = 1;
+ net.layers[net.n-1].objectness = 0;
+ background = 0;
+
+ pthread_join(load_thread, 0);
+ free_data(buffer);
+ args.background = background;
+ load_thread = load_data_in_thread(args);
+ }
+
+ if((i-1)*imgs <= 120*N && i*imgs > N*120){
+ fprintf(stderr, "Third stage done.\n");
+ char buff[256];
+ sprintf(buff, "%s/%s_final.weights", backup_directory, base);
+ net.layers[net.n-1].rescore = 1;
+ save_weights(net, buff);
+ }
+
+ if(i%1000==0){
+ char buff[256];
+ sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
+ save_weights(net, buff);
+ }
+ free_data(train);
+ }
+ char buff[256];
+ sprintf(buff, "%s/%s_rescore.weights", backup_directory, base);
+ save_weights(net, buff);
+}
+
+void convert_yoloplus_detections(float *predictions, int classes, int objectness, int background, int num_boxes, int w, int h, float thresh, float **probs, box *boxes)
+{
+ int i,j;
+ int per_box = 4+classes+(background || objectness);
+ for (i = 0; i < num_boxes*num_boxes; ++i){
+ float scale = 1;
+ if(objectness) scale = 1-predictions[i*per_box];
+ int offset = i*per_box+(background||objectness);
+ for(j = 0; j < classes; ++j){
+ float prob = scale*predictions[offset+j];
+ probs[i][j] = (prob > thresh) ? prob : 0;
+ }
+ int row = i / num_boxes;
+ int col = i % num_boxes;
+ offset += classes;
+ boxes[i].x = (predictions[offset + 0] + col) / num_boxes * w;
+ boxes[i].y = (predictions[offset + 1] + row) / num_boxes * h;
+ boxes[i].w = pow(predictions[offset + 2], 2) * w;
+ boxes[i].h = pow(predictions[offset + 3], 2) * h;
+ }
+}
+
+void print_yoloplus_detections(FILE **fps, char *id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
+{
+ int i, j;
+ for(i = 0; i < num_boxes*num_boxes; ++i){
+ float xmin = boxes[i].x - boxes[i].w/2.;
+ float xmax = boxes[i].x + boxes[i].w/2.;
+ float ymin = boxes[i].y - boxes[i].h/2.;
+ float ymax = boxes[i].y + boxes[i].h/2.;
+
+ if (xmin < 0) xmin = 0;
+ if (ymin < 0) ymin = 0;
+ if (xmax > w) xmax = w;
+ if (ymax > h) ymax = h;
+
+ for(j = 0; j < classes; ++j){
+ if (probs[i][j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, probs[i][j],
+ xmin, ymin, xmax, ymax);
+ }
+ }
+}
+
+void validate_yoloplus(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+ 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));
+
+ char *base = "results/comp4_det_test_";
+ list *plist = get_paths("/home/pjreddie/data/voc/test/2007_test.txt");
+ char **paths = (char **)list_to_array(plist);
+
+ int classes = layer.classes;
+ int objectness = layer.objectness;
+ int background = layer.background;
+ int num_boxes = sqrt(get_detection_layer_locations(layer));
+
+ int j;
+ FILE **fps = calloc(classes, sizeof(FILE *));
+ for(j = 0; j < classes; ++j){
+ char buff[1024];
+ snprintf(buff, 1024, "%s%s.txt", base, voc_names[j]);
+ fps[j] = fopen(buff, "w");
+ }
+ box *boxes = calloc(num_boxes*num_boxes, sizeof(box));
+ float **probs = calloc(num_boxes*num_boxes, sizeof(float *));
+ for(j = 0; j < num_boxes*num_boxes; ++j) probs[j] = calloc(classes, sizeof(float *));
+
+ int m = plist->size;
+ int i=0;
+ int t;
+
+ float thresh = .001;
+ int nms = 1;
+ float iou_thresh = .5;
+
+ int nthreads = 8;
+ image *val = calloc(nthreads, sizeof(image));
+ image *val_resized = calloc(nthreads, sizeof(image));
+ image *buf = calloc(nthreads, sizeof(image));
+ image *buf_resized = calloc(nthreads, sizeof(image));
+ pthread_t *thr = calloc(nthreads, sizeof(pthread_t));
+
+ load_args args = {0};
+ args.w = net.w;
+ args.h = net.h;
+ args.type = IMAGE_DATA;
+
+ for(t = 0; t < nthreads; ++t){
+ args.path = paths[i+t];
+ args.im = &buf[t];
+ args.resized = &buf_resized[t];
+ thr[t] = load_data_in_thread(args);
+ }
+ time_t start = time(0);
+ for(i = nthreads; i < m+nthreads; i += nthreads){
+ fprintf(stderr, "%d\n", i);
+ for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
+ pthread_join(thr[t], 0);
+ val[t] = buf[t];
+ val_resized[t] = buf_resized[t];
+ }
+ for(t = 0; t < nthreads && i+t < m; ++t){
+ args.path = paths[i+t];
+ args.im = &buf[t];
+ args.resized = &buf_resized[t];
+ thr[t] = load_data_in_thread(args);
+ }
+ for(t = 0; t < nthreads && i+t-nthreads < m; ++t){
+ char *path = paths[i+t-nthreads];
+ char *id = basecfg(path);
+ float *X = val_resized[t].data;
+ float *predictions = network_predict(net, X);
+ int w = val[t].w;
+ int h = val[t].h;
+ convert_yoloplus_detections(predictions, classes, objectness, background, num_boxes, w, h, thresh, probs, boxes);
+ if (nms) do_nms(boxes, probs, num_boxes*num_boxes, classes, iou_thresh);
+ print_yoloplus_detections(fps, id, boxes, probs, num_boxes, classes, w, h);
+ free(id);
+ free_image(val[t]);
+ free_image(val_resized[t]);
+ }
+ }
+ fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
+}
+
+void test_yoloplus(char *cfgfile, char *weightfile, char *filename, float thresh)
+{
+
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ detection_layer layer = get_network_detection_layer(net);
+ set_batch_network(&net, 1);
+ srand(2222222);
+ clock_t time;
+ char input[256];
+ while(1){
+ if(filename){
+ strncpy(input, filename, 256);
+ } else {
+ printf("Enter Image Path: ");
+ fflush(stdout);
+ fgets(input, 256, stdin);
+ strtok(input, "\n");
+ }
+ image im = load_image_color(input,0,0);
+ image sized = resize_image(im, net.w, net.h);
+ float *X = sized.data;
+ time=clock();
+ float *predictions = network_predict(net, X);
+ printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
+ draw_yoloplus(im, predictions, 7, layer.objectness, "predictions", thresh);
+ free_image(im);
+ free_image(sized);
+#ifdef OPENCV
+ cvWaitKey(0);
+ cvDestroyAllWindows();
+#endif
+ if (filename) break;
+ }
+}
+
+void run_yoloplus(int argc, char **argv)
+{
+ float thresh = find_float_arg(argc, argv, "-thresh", .2);
+ 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;
+ char *filename = (argc > 5) ? argv[5]: 0;
+ if(0==strcmp(argv[2], "test")) test_yoloplus(cfg, weights, filename, thresh);
+ else if(0==strcmp(argv[2], "train")) train_yoloplus(cfg, weights);
+ else if(0==strcmp(argv[2], "valid")) validate_yoloplus(cfg, weights);
+}
--
GitLab