From 1b5afb45838e603fa6780762eb8cc59246dc2d81 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Tue, 08 May 2018 11:09:35 +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 | 240 +----------------------------------------------------------
1 files changed, 7 insertions(+), 233 deletions(-)
diff --git a/src/swag.c b/src/swag.c
index 4dcf36b..2cb3093 100644
--- a/src/swag.c
+++ b/src/swag.c
@@ -9,55 +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, 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_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);
-}
-
void train_swag(char *cfgfile, char *weightfile)
{
- char *train_images = "/home/pjreddie/data/voc/test/train.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;
@@ -70,14 +26,14 @@
int i = *net.seen/imgs;
data train, buffer;
-
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;
+ //int N = plist->size;
char **paths = (char **)list_to_array(plist);
load_args args = {0};
@@ -87,6 +43,7 @@
args.n = imgs;
args.m = plist->size;
args.classes = classes;
+ args.jitter = jitter;
args.num_boxes = side;
args.d = &buffer;
args.type = REGION_DATA;
@@ -103,21 +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, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs);
- 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 == 600){
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
@@ -129,180 +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 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 offset = i*per_cell + 5*n;
- float scale = predictions[offset];
- int index = i*num + n;
- boxes[index].x = (predictions[offset + 1] + col) / side * w;
- boxes[index].y = (predictions[offset + 2] + row) / side * h;
- boxes[index].w = pow(predictions[offset + 3], (square?2:1)) * w;
- boxes[index].h = pow(predictions[offset + 4], (square?2:1)) * h;
- for(j = 0; j < classes; ++j){
- offset = i*per_cell + 5*num;
- float prob = scale*predictions[offset+j];
- probs[index][j] = (prob > thresh) ? prob : 0;
- }
- }
- }
-}
-
-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_";
- 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 = 8;
- 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);
- if (nms) do_nms(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 test_swag(char *cfgfile, char *weightfile, char *filename, float thresh)
-{
-
- network net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- detection_layer layer = get_network_detection_layer(net);
- set_batch_network(&net, 1);
- srand(2222222);
- clock_t time;
- char input[256];
- while(1){
- if(filename){
- strncpy(input, filename, 256);
- } else {
- printf("Enter Image Path: ");
- fflush(stdout);
- fgets(input, 256, stdin);
- 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));
- draw_swag(im, predictions, 7, layer.objectness, "predictions", thresh);
- free_image(im);
- free_image(sized);
-#ifdef OPENCV
- cvWaitKey(0);
- cvDestroyAllWindows();
-#endif
- if (filename) break;
- }
-}
-
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;
@@ -310,8 +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);
+ if(0==strcmp(argv[2], "train")) train_swag(cfg, weights);
}
--
Gitblit v1.10.0