From c53e03348c65462bcba33f6352087dd6b9268e8f Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 16 Sep 2015 21:12:10 +0000
Subject: [PATCH] yolo working w/ regions
---
src/yolo.c | 58 ++++++++++++++++++++++++++++++++++------------------------
1 files changed, 34 insertions(+), 24 deletions(-)
diff --git a/src/yolo.c b/src/yolo.c
index 5ad9534..9b229e2 100644
--- a/src/yolo.c
+++ b/src/yolo.c
@@ -66,19 +66,14 @@
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;
+ 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*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;
}
@@ -88,35 +83,37 @@
int background = layer.objectness;
int side = sqrt(get_detection_layer_locations(layer));
- pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, net.w, net.h, side, side, background, &buffer);
+ 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(i*imgs < N*130){
+ while(get_current_batch(net) < net.max_batches){
i += 1;
time=clock();
pthread_join(load_thread, 0);
train = buffer;
- load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, net.w, net.h, side, side, background, &buffer);
+ load_thread = load_data_in_thread(args);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
- net.seen += imgs;
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);
@@ -126,7 +123,8 @@
pthread_join(load_thread, 0);
free_data(buffer);
- load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, net.w, net.h, side, side, background, &buffer);
+ args.background = background;
+ load_thread = load_data_in_thread(args);
}
if((i-1)*imgs <= 120*N && i*imgs > N*120){
@@ -237,8 +235,17 @@
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){
- thr[t] = load_image_thread(paths[i+t], &buf[t], &buf_resized[t], net.w, net.h);
+ 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){
@@ -249,7 +256,10 @@
val_resized[t] = buf_resized[t];
}
for(t = 0; t < nthreads && i+t < m; ++t){
- thr[t] = load_image_thread(paths[i+t], &buf[t], &buf_resized[t], net.w, net.h);
+ 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];
@@ -259,7 +269,7 @@
int w = val[t].w;
int h = val[t].h;
convert_yolo_detections(predictions, classes, objectness, background, num_boxes, w, h, thresh, probs, boxes);
- if (nms) do_nms(boxes, probs, num_boxes, classes, iou_thresh);
+ if (nms) do_nms(boxes, probs, num_boxes*num_boxes, classes, iou_thresh);
print_yolo_detections(fps, id, boxes, probs, num_boxes, classes, w, h);
free(id);
free_image(val[t]);
--
Gitblit v1.10.0