From 028696bf15efeca3acb3db8c42a96f7b9e0f55ff Mon Sep 17 00:00:00 2001
From: iovodov <b@ovdv.ru>
Date: Thu, 03 May 2018 13:33:46 +0000
Subject: [PATCH] Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount
---
src/swag.c | 375 -----------------------------------------------------
1 files changed, 3 insertions(+), 372 deletions(-)
diff --git a/src/swag.c b/src/swag.c
index 4dc6bf9..2cb3093 100644
--- a/src/swag.c
+++ b/src/swag.c
@@ -1,5 +1,4 @@
#include "network.h"
-#include "region_layer.h"
#include "detection_layer.h"
#include "cost_layer.h"
#include "utils.h"
@@ -10,46 +9,11 @@
#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_swag(image im, int num, float thresh, box *boxes, float **probs, char *label)
-{
- int classes = 20;
- int i;
-
- 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);
- }
- }
- show_image(im, label);
-}
-
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 *train_images = "data/voc.0712.trainval";
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;
@@ -62,7 +26,6 @@
int i = *net.seen/imgs;
data train, buffer;
-
layer l = net.layers[net.n - 1];
int side = l.side;
@@ -97,21 +60,13 @@
printf("Loaded: %lf seconds\n", sec(clock()-time));
- /*
- image im = float_to_image(net.w, net.h, 3, train.X.vals[113]);
- image copy = copy_image(im);
- draw_swag(copy, train.y.vals[113], 7, "truth");
- cvWaitKey(0);
- free_image(copy);
- */
-
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, %f rate, %lf seconds, %d images\n", i, loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
- if(i%1000==0){
+ if(i%1000==0 || i == 600){
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
@@ -123,327 +78,8 @@
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, 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 = 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;
- }
- }
- }
-}
-
-void print_swag_detections(FILE **fps, char *id, box *boxes, float **probs, int total, int classes, int w, int h)
-{
- int i, j;
- 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.;
- 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_swag(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_";
- //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);
-
- 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_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;
- int t;
-
- float thresh = .001;
- int nms = 1;
- float iou_thresh = .5;
-
- int nthreads = 2;
- 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_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]);
- free_image(val_resized[t]);
- }
- }
- 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)
-{
-
- network net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- 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);
- } else {
- printf("Enter Image Path: ");
- fflush(stdout);
- input = fgets(input, 256, stdin);
- if(!input) return;
- 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));
- 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);
-#ifdef OPENCV
- cvWaitKey(0);
- cvDestroyAllWindows();
-#endif
- if (filename) break;
- }
-}
-
-
-/*
-#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);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
@@ -451,10 +87,5 @@
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_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);
+ if(0==strcmp(argv[2], "train")) train_swag(cfg, weights);
}
--
Gitblit v1.10.0