From 481b57a96a9ef29b112caec1bb3e17ffb043ceae Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sun, 25 Sep 2016 06:12:54 +0000
Subject: [PATCH] So I have this new programming paradigm.......
---
src/detector.c | 121 +++++++++++++---------------------------
1 files changed, 39 insertions(+), 82 deletions(-)
diff --git a/src/detector.c b/src/detector.c
index 9498750..1f48c61 100644
--- a/src/detector.c
+++ b/src/detector.c
@@ -1,16 +1,16 @@
#include "network.h"
-#include "detection_layer.h"
+#include "region_layer.h"
#include "cost_layer.h"
#include "utils.h"
#include "parser.h"
#include "box.h"
+#include "demo.h"
#ifdef OPENCV
#include "opencv2/highgui/highgui_c.h"
#endif
static char *voc_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
-static image voc_labels[20];
void train_detector(char *cfgfile, char *weightfile)
{
@@ -49,13 +49,14 @@
args.num_boxes = l.max_boxes;
args.d = &buffer;
args.type = DETECTION_DATA;
+ args.threads = 4;
args.angle = net.angle;
args.exposure = net.exposure;
args.saturation = net.saturation;
args.hue = net.hue;
- pthread_t load_thread = load_data_in_thread(args);
+ pthread_t load_thread = load_data(args);
clock_t time;
//while(i*imgs < N*120){
while(get_current_batch(net) < net.max_batches){
@@ -63,7 +64,7 @@
time=clock();
pthread_join(load_thread, 0);
train = buffer;
- load_thread = load_data_in_thread(args);
+ load_thread = load_data(args);
/*
int k;
@@ -102,44 +103,6 @@
save_weights(net, buff);
}
-static 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,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 = index * (classes + 5) + 4;
- float scale = predictions[p_index];
- int box_index = index * (classes + 5);
- boxes[index].x = (predictions[box_index + 0] + col + .5) / side * w;
- boxes[index].y = (predictions[box_index + 1] + row + .5) / side * h;
- if(0){
- boxes[index].x = (logistic_activate(predictions[box_index + 0]) + col) / side * w;
- boxes[index].y = (logistic_activate(predictions[box_index + 1]) + row) / side * h;
- }
- boxes[index].w = pow(logistic_activate(predictions[box_index + 2]), (square?2:1)) * w;
- boxes[index].h = pow(logistic_activate(predictions[box_index + 3]), (square?2:1)) * h;
- if(1){
- boxes[index].x = ((col + .5)/side + predictions[box_index + 0] * .5) * w;
- boxes[index].y = ((row + .5)/side + predictions[box_index + 1] * .5) * h;
- boxes[index].w = (exp(predictions[box_index + 2]) * .5) * w;
- boxes[index].h = (exp(predictions[box_index + 3]) * .5) * h;
- }
- for(j = 0; j < classes; ++j){
- int class_index = index * (classes + 5) + 5;
- float prob = scale*predictions[class_index+j];
- probs[index][j] = (prob > thresh) ? prob : 0;
- }
- if(only_objectness){
- probs[index][0] = scale;
- }
- }
- }
-}
-
void print_detector_detections(FILE **fps, char *id, box *boxes, float **probs, int total, int classes, int w, int h)
{
int i, j;
@@ -179,7 +142,6 @@
layer l = net.layers[net.n-1];
int classes = l.classes;
- int side = l.w;
int j;
FILE **fps = calloc(classes, sizeof(FILE *));
@@ -188,9 +150,9 @@
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 *));
+ box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
+ float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
+ for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
@@ -235,12 +197,12 @@
char *path = paths[i+t-nthreads];
char *id = basecfg(path);
float *X = val_resized[t].data;
- float *predictions = network_predict(net, X);
+ network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
- convert_detections(predictions, classes, l.n, 0, side, w, h, thresh, probs, boxes, 0);
- if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, nms);
- print_detector_detections(fps, id, boxes, probs, side*side*l.n, classes, w, h);
+ get_region_boxes(l, w, h, thresh, probs, boxes, 0);
+ if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
+ print_detector_detections(fps, id, boxes, probs, l.w*l.h*l.n, classes, w, h);
free(id);
free_image(val[t]);
free_image(val_resized[t]);
@@ -268,8 +230,6 @@
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 *));
@@ -278,9 +238,9 @@
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 *));
+ box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
+ float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
+ for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
@@ -299,18 +259,19 @@
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, l.w, 1, 1, thresh, probs, boxes, 1);
- if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms);
+ network_predict(net, sized.data);
+ get_region_boxes(l, 1, 1, thresh, probs, boxes, 1);
+ if (nms) do_nms(boxes, probs, l.w*l.h*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");
+ char labelpath[4096];
+ find_replace(path, "images", "labels", labelpath);
+ find_replace(labelpath, "JPEGImages", "labels", labelpath);
+ find_replace(labelpath, ".jpg", ".txt", labelpath);
+ find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
- for(k = 0; k < side*side*l.n; ++k){
+ for(k = 0; k < l.w*l.h*l.n; ++k){
if(probs[k][0] > thresh){
++proposals;
}
@@ -319,7 +280,7 @@
++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){
+ for(k = 0; k < l.w*l.h*l.n; ++k){
float iou = box_iou(boxes[k], t);
if(probs[k][0] > thresh && iou > best_iou){
best_iou = iou;
@@ -340,13 +301,12 @@
void test_detector(char *cfgfile, char *weightfile, char *filename, float thresh)
{
-
+ image *alphabet = load_alphabet();
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer l = net.layers[net.n-1];
- l.side = l.w;
+ layer l = net.layers[net.n-1];
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
@@ -354,9 +314,9 @@
char *input = buff;
int j;
float nms=.4;
- 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 *));
+ box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
+ float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
+ for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
while(1){
if(filename){
strncpy(input, filename, 256);
@@ -371,12 +331,12 @@
image sized = resize_image(im, net.w, net.h);
float *X = sized.data;
time=clock();
- float *predictions = network_predict(net, X);
+ network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- convert_detections(predictions, l.classes, l.n, 0, l.w, 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);
+ get_region_boxes(l, 1, 1, thresh, probs, boxes, 0);
+ if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
+ //draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, voc_names, voc_labels, 20);
+ draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, voc_names, alphabet, 20);
save_image(im, "predictions");
show_image(im, "predictions");
@@ -392,14 +352,10 @@
void run_detector(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);
- }
-
+ char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .2);
+ int cam_index = find_int_arg(argc, argv, "-c", 0);
+ int frame_skip = find_int_arg(argc, argv, "-s", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@@ -412,4 +368,5 @@
else if(0==strcmp(argv[2], "train")) train_detector(cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_detector(cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
+ else if(0==strcmp(argv[2], "demo")) demo(cfg, weights, thresh, cam_index, filename, voc_names, 20, frame_skip, prefix);
}
--
Gitblit v1.10.0