From 8fd18add6e060a433629fae3fa2a7ef75df4644e Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 04 Nov 2015 03:23:42 +0000
Subject: [PATCH] CVPR Experiments
---
src/swag.c | 213 ++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 177 insertions(+), 36 deletions(-)
diff --git a/src/swag.c b/src/swag.c
index ec58f0d..4dc6bf9 100644
--- a/src/swag.c
+++ b/src/swag.c
@@ -12,39 +12,28 @@
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_swag(image im, float *predictions, int side, int num, char *label, float thresh)
+void draw_swag(image im, int num, float thresh, box *boxes, float **probs, char *label)
{
int classes = 20;
- int i,n;
+ int i;
- for(i = 0; i < side*side; ++i){
- int row = i / side;
- int col = i % side;
- for(n = 0; n < num; ++n){
- int p_index = side*side*classes + i*num + n;
- int box_index = side*side*(classes + num) + (i*num + n)*4;
- int class_index = i*classes;
- float scale = predictions[p_index];
- int class = max_index(predictions+class_index, classes);
- float prob = scale * predictions[class_index + class];
- if(prob > thresh){
- int width = sqrt(prob)*5 + 1;
- printf("%f %s\n", prob, voc_names[class]);
- float red = get_color(0,class,classes);
- float green = get_color(1,class,classes);
- float blue = get_color(2,class,classes);
- box b = float_to_box(predictions+box_index);
- b.x = (b.x + col)/side;
- b.y = (b.y + row)/side;
- b.w = b.w*b.w;
- b.h = b.h*b.h;
+ for(i = 0; i < num; ++i){
+ int class = max_index(probs[i], classes);
+ float prob = probs[i][class];
+ if(prob > thresh){
+ int width = pow(prob, 1./3.)*10 + 1;
+ printf("%f %s\n", prob, voc_names[class]);
+ float red = get_color(0,class,classes);
+ float green = get_color(1,class,classes);
+ float blue = get_color(2,class,classes);
+ //red = green = blue = 0;
+ box b = boxes[i];
- int left = (b.x-b.w/2)*im.w;
- int right = (b.x+b.w/2)*im.w;
- int top = (b.y-b.h/2)*im.h;
- int bot = (b.y+b.h/2)*im.h;
- draw_box_width(im, left, top, right, bot, width, red, green, blue);
- }
+ int left = (b.x-b.w/2.)*im.w;
+ int right = (b.x+b.w/2.)*im.w;
+ int top = (b.y-b.h/2.)*im.h;
+ int bot = (b.y+b.h/2.)*im.h;
+ draw_box_width(im, left, top, right, bot, width, red, green, blue);
}
}
show_image(im, label);
@@ -52,7 +41,12 @@
void train_swag(char *cfgfile, char *weightfile)
{
+ //char *train_images = "/home/pjreddie/data/voc/person_detection/2010_person.txt";
+ //char *train_images = "/home/pjreddie/data/people-art/train.txt";
+ //char *train_images = "/home/pjreddie/data/voc/test/2012_trainval.txt";
char *train_images = "/home/pjreddie/data/voc/test/train.txt";
+ //char *train_images = "/home/pjreddie/data/voc/test/train_all.txt";
+ //char *train_images = "/home/pjreddie/data/voc/test/2007_trainval.txt";
char *backup_directory = "/home/pjreddie/backup/";
srand(time(0));
data_seed = time(0);
@@ -73,6 +67,7 @@
int side = l.side;
int classes = l.classes;
+ float jitter = l.jitter;
list *plist = get_paths(train_images);
//int N = plist->size;
@@ -85,6 +80,7 @@
args.n = imgs;
args.m = plist->size;
args.classes = classes;
+ args.jitter = jitter;
args.num_boxes = side;
args.d = &buffer;
args.type = REGION_DATA;
@@ -114,7 +110,7 @@
if (avg_loss < 0) 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), i*imgs);
+ 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){
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
@@ -127,7 +123,7 @@
save_weights(net, buff);
}
-void convert_swag_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes)
+void convert_swag_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;
@@ -148,6 +144,9 @@
float prob = scale*predictions[class_index+j];
probs[index][j] = (prob > thresh) ? prob : 0;
}
+ if(only_objectness){
+ probs[index][0] = scale;
+ }
}
}
}
@@ -184,6 +183,9 @@
srand(time(0));
char *base = "results/comp4_det_test_";
+ //base = "/home/pjreddie/comp4_det_test_";
+ //list *plist = get_paths("/home/pjreddie/data/people-art/test.txt");
+ //list *plist = get_paths("/home/pjreddie/data/cubist/test.txt");
list *plist = get_paths("/home/pjreddie/data/voc/test/2007_test.txt");
char **paths = (char **)list_to_array(plist);
@@ -211,7 +213,7 @@
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));
@@ -250,8 +252,8 @@
float *predictions = network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
- convert_swag_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes);
- if (nms) do_nms(boxes, probs, side*side*l.n, classes, iou_thresh);
+ convert_swag_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_swag_detections(fps, id, boxes, probs, side*side*l.n, classes, w, h);
free(id);
free_image(val[t]);
@@ -261,6 +263,93 @@
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
+void validate_swag_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("/home/pjreddie/data/voc/test/2007_test.txt");
+ 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;
+ int nms = 0;
+ float iou_thresh = .5;
+ float nms_thresh = .5;
+
+ 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_swag_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_thresh);
+
+ 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_swag(char *cfgfile, char *weightfile, char *filename, float thresh)
{
@@ -268,12 +357,17 @@
if(weightfile){
load_weights(&net, weightfile);
}
- region_layer layer = net.layers[net.n-1];
+ region_layer l = net.layers[net.n-1];
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
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);
@@ -290,7 +384,10 @@
time=clock();
float *predictions = network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
- draw_swag(im, predictions, layer.side, layer.n, "predictions", thresh);
+ convert_swag_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_swag(im, l.side*l.side*l.n, thresh, boxes, probs, "predictions");
+
show_image(sized, "resized");
free_image(im);
free_image(sized);
@@ -302,6 +399,48 @@
}
}
+
+/*
+#ifdef OPENCV
+image ipl_to_image(IplImage* src);
+#include "opencv2/highgui/highgui_c.h"
+#include "opencv2/imgproc/imgproc_c.h"
+
+void demo_swag(char *cfgfile, char *weightfile, float thresh)
+{
+network net = parse_network_cfg(cfgfile);
+if(weightfile){
+load_weights(&net, weightfile);
+}
+region_layer layer = net.layers[net.n-1];
+CvCapture *capture = cvCaptureFromCAM(-1);
+set_batch_network(&net, 1);
+srand(2222222);
+while(1){
+IplImage* frame = cvQueryFrame(capture);
+image im = ipl_to_image(frame);
+cvReleaseImage(&frame);
+rgbgr_image(im);
+
+image sized = resize_image(im, net.w, net.h);
+float *X = sized.data;
+float *predictions = network_predict(net, X);
+draw_swag(im, predictions, layer.side, layer.n, "predictions", thresh);
+free_image(im);
+free_image(sized);
+cvWaitKey(10);
+}
+}
+#else
+void demo_swag(char *cfgfile, char *weightfile, float thresh){}
+#endif
+ */
+
+void demo_swag(char *cfgfile, char *weightfile, float thresh);
+#ifndef GPU
+void demo_swag(char *cfgfile, char *weightfile, float thresh){}
+#endif
+
void run_swag(int argc, char **argv)
{
float thresh = find_float_arg(argc, argv, "-thresh", .2);
@@ -316,4 +455,6 @@
if(0==strcmp(argv[2], "test")) test_swag(cfg, weights, filename, thresh);
else if(0==strcmp(argv[2], "train")) train_swag(cfg, weights);
else if(0==strcmp(argv[2], "valid")) validate_swag(cfg, weights);
+ else if(0==strcmp(argv[2], "recall")) validate_swag_recall(cfg, weights);
+ else if(0==strcmp(argv[2], "demo")) demo_swag(cfg, weights, thresh);
}
--
Gitblit v1.10.0