From ae43c2bc32fbb838bfebeeaf2c2b058ccab5c83c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@burninator.cs.washington.edu>
Date: Thu, 23 Jun 2016 05:31:14 +0000
Subject: [PATCH] hi
---
src/yolo.c | 300 +++++++++++++++++++++++++++++++++++------------------------
1 files changed, 177 insertions(+), 123 deletions(-)
diff --git a/src/yolo.c b/src/yolo.c
index 9b229e2..057abcf 100644
--- a/src/yolo.c
+++ b/src/yolo.c
@@ -4,57 +4,18 @@
#include "utils.h"
#include "parser.h"
#include "box.h"
+#include "demo.h"
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#endif
-char *voc_class_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
-
-void draw_yolo(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_class_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);
-}
+char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
+image voc_labels[20];
void train_yolo(char *cfgfile, char *weightfile)
{
- char *train_images = "/home/pjreddie/data/voc/test/train.txt";
+ char *train_images = "/data/voc/train.txt";
char *backup_directory = "/home/pjreddie/backup/";
srand(time(0));
data_seed = time(0);
@@ -65,23 +26,21 @@
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer layer = get_network_detection_layer(net);
- int imgs = 128;
+ printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
+ int imgs = net.batch*net.subdivisions;
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));
+
+ layer l = net.layers[net.n - 1];
+
+ int side = l.side;
+ int classes = l.classes;
+ float jitter = l.jitter;
+
+ list *plist = get_paths(train_images);
+ //int N = plist->size;
+ char **paths = (char **)list_to_array(plist);
load_args args = {0};
args.w = net.w;
@@ -90,13 +49,14 @@
args.n = imgs;
args.m = plist->size;
args.classes = classes;
+ args.jitter = jitter;
args.num_boxes = side;
- args.background = background;
args.d = &buffer;
- args.type = DETECTION_DATA;
+ args.type = REGION_DATA;
pthread_t load_thread = load_data_in_thread(args);
clock_t time;
+ //while(i*imgs < N*120){
while(get_current_batch(net) < net.max_batches){
i += 1;
time=clock();
@@ -105,37 +65,14 @@
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){
+ printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", i, loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
+ if(i%1000==0 || (i < 1000 && i%100 == 0)){
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
@@ -143,36 +80,42 @@
free_data(train);
}
char buff[256];
- sprintf(buff, "%s/%s_rescore.weights", backup_directory, base);
+ sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
}
-void convert_yolo_detections(float *predictions, int classes, int objectness, int background, int num_boxes, int w, int h, float thresh, float **probs, box *boxes)
+void convert_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
{
- 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 i,j,n;
+ //int per_cell = 5*num+classes;
+ for (i = 0; i < side*side; ++i){
+ int row = i / side;
+ int col = i % side;
+ for(n = 0; n < num; ++n){
+ int index = i*num + n;
+ int p_index = side*side*classes + i*num + n;
+ float scale = predictions[p_index];
+ int box_index = side*side*(classes + num) + (i*num + n)*4;
+ boxes[index].x = (predictions[box_index + 0] + col) / side * w;
+ boxes[index].y = (predictions[box_index + 1] + row) / side * h;
+ boxes[index].w = pow(predictions[box_index + 2], (square?2:1)) * w;
+ boxes[index].h = pow(predictions[box_index + 3], (square?2:1)) * h;
+ for(j = 0; j < classes; ++j){
+ int class_index = i*classes;
+ float prob = scale*predictions[class_index+j];
+ probs[index][j] = (prob > thresh) ? prob : 0;
+ }
+ if(only_objectness){
+ probs[index][0] = scale;
+ }
}
- 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_yolo_detections(FILE **fps, char *id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
+void print_yolo_detections(FILE **fps, char *id, box *boxes, float **probs, int total, int classes, int w, int h)
{
int i, j;
- for(i = 0; i < num_boxes*num_boxes; ++i){
+ for(i = 0; i < total; ++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.;
@@ -197,29 +140,30 @@
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");
+ //list *plist = get_paths("data/voc.2007.test");
+ list *plist = get_paths("/home/pjreddie/data/voc/2007_test.txt");
+ //list *plist = get_paths("data/voc.2012.test");
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));
+ layer l = net.layers[net.n-1];
+ int classes = l.classes;
+ int square = l.sqrt;
+ int side = l.side;
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_class_names[j]);
+ 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 *));
+ box *boxes = calloc(side*side*l.n, sizeof(box));
+ float **probs = calloc(side*side*l.n, sizeof(float *));
+ for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
@@ -229,7 +173,7 @@
int nms = 1;
float iou_thresh = .5;
- int nthreads = 8;
+ int nthreads = 2;
image *val = calloc(nthreads, sizeof(image));
image *val_resized = calloc(nthreads, sizeof(image));
image *buf = calloc(nthreads, sizeof(image));
@@ -268,9 +212,9 @@
float *predictions = network_predict(net, X);
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*num_boxes, classes, iou_thresh);
- print_yolo_detections(fps, id, boxes, probs, num_boxes, classes, w, h);
+ convert_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
+ if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh);
+ print_yolo_detections(fps, id, boxes, probs, side*side*l.n, classes, w, h);
free(id);
free_image(val[t]);
free_image(val_resized[t]);
@@ -279,6 +223,92 @@
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
+void validate_yolo_recall(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+ 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("data/voc.2007.test");
+ char **paths = (char **)list_to_array(plist);
+
+ layer l = net.layers[net.n-1];
+ int classes = l.classes;
+ int square = l.sqrt;
+ int side = l.side;
+
+ int j, k;
+ 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(side*side*l.n, sizeof(box));
+ float **probs = calloc(side*side*l.n, sizeof(float *));
+ for(j = 0; j < side*side*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
+
+ int m = plist->size;
+ int i=0;
+
+ float thresh = .001;
+ float iou_thresh = .5;
+ float nms = 0;
+
+ int total = 0;
+ int correct = 0;
+ int proposals = 0;
+ float avg_iou = 0;
+
+ for(i = 0; i < m; ++i){
+ char *path = paths[i];
+ image orig = load_image_color(path, 0, 0);
+ image sized = resize_image(orig, net.w, net.h);
+ char *id = basecfg(path);
+ float *predictions = network_predict(net, sized.data);
+ convert_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 1);
+ if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms);
+
+ char *labelpath = find_replace(path, "images", "labels");
+ labelpath = find_replace(labelpath, "JPEGImages", "labels");
+ labelpath = find_replace(labelpath, ".jpg", ".txt");
+ labelpath = find_replace(labelpath, ".JPEG", ".txt");
+
+ int num_labels = 0;
+ box_label *truth = read_boxes(labelpath, &num_labels);
+ for(k = 0; k < side*side*l.n; ++k){
+ if(probs[k][0] > thresh){
+ ++proposals;
+ }
+ }
+ for (j = 0; j < num_labels; ++j) {
+ ++total;
+ box t = {truth[j].x, truth[j].y, truth[j].w, truth[j].h};
+ float best_iou = 0;
+ for(k = 0; k < side*side*l.n; ++k){
+ float iou = box_iou(boxes[k], t);
+ if(probs[k][0] > thresh && iou > best_iou){
+ best_iou = iou;
+ }
+ }
+ avg_iou += best_iou;
+ if(best_iou > iou_thresh){
+ ++correct;
+ }
+ }
+
+ fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total);
+ free(id);
+ free_image(orig);
+ free_image(sized);
+ }
+}
+
void test_yolo(char *cfgfile, char *weightfile, char *filename, float thresh)
{
@@ -286,18 +316,25 @@
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer layer = get_network_detection_layer(net);
+ detection_layer l = net.layers[net.n-1];
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
- char input[256];
+ char buff[256];
+ char *input = buff;
+ int j;
+ float nms=.5;
+ box *boxes = calloc(l.side*l.side*l.n, sizeof(box));
+ float **probs = calloc(l.side*l.side*l.n, sizeof(float *));
+ for(j = 0; j < l.side*l.side*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
while(1){
if(filename){
strncpy(input, filename, 256);
} else {
printf("Enter Image Path: ");
fflush(stdout);
- fgets(input, 256, stdin);
+ input = fgets(input, 256, stdin);
+ if(!input) return;
strtok(input, "\n");
}
image im = load_image_color(input,0,0);
@@ -306,7 +343,14 @@
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- draw_yolo(im, predictions, 7, layer.objectness, "predictions", thresh);
+ convert_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
+ if (nms) do_nms_sort(boxes, probs, l.side*l.side*l.n, l.classes, nms);
+ //draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
+ draw_detections(im, l.side*l.side*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
+ save_image(im, "predictions");
+ show_image(im, "predictions");
+
+ show_image(sized, "resized");
free_image(im);
free_image(sized);
#ifdef OPENCV
@@ -319,7 +363,15 @@
void run_yolo(int argc, char **argv)
{
+ int i;
+ for(i = 0; i < 20; ++i){
+ char buff[256];
+ sprintf(buff, "data/labels/%s.png", voc_names[i]);
+ voc_labels[i] = load_image_color(buff, 0, 0);
+ }
+
float thresh = find_float_arg(argc, argv, "-thresh", .2);
+ int cam_index = find_int_arg(argc, argv, "-c", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@@ -331,4 +383,6 @@
if(0==strcmp(argv[2], "test")) test_yolo(cfg, weights, filename, thresh);
else if(0==strcmp(argv[2], "train")) train_yolo(cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_yolo(cfg, weights);
+ else if(0==strcmp(argv[2], "recall")) validate_yolo_recall(cfg, weights);
+ else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, voc_names, voc_labels, 20);
}
--
Gitblit v1.10.0