From c40cdeb4021fc1a638969563972f13c9f5e90d74 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 09 Oct 2015 19:50:43 +0000
Subject: [PATCH] lots of comparator stuff
---
src/swag.c | 197 ++++++++++++++++++++++++++++++++++++------------
1 files changed, 147 insertions(+), 50 deletions(-)
diff --git a/src/swag.c b/src/swag.c
index 4dcf36b..8c9ce3c 100644
--- a/src/swag.c
+++ b/src/swag.c
@@ -1,4 +1,5 @@
#include "network.h"
+#include "region_layer.h"
#include "detection_layer.h"
#include "cost_layer.h"
#include "utils.h"
@@ -11,40 +12,37 @@
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)
+void draw_swag(image im, float *predictions, int side, int num, char *label, float thresh)
{
int classes = 20;
- int elems = 4+classes+objectness;
- int j;
- int r, c;
+ int i,n;
- 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]);
+ 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;
- 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;
+ 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);
}
}
@@ -75,9 +73,10 @@
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 +86,7 @@
args.n = imgs;
args.m = plist->size;
args.classes = classes;
+ args.jitter = jitter;
args.num_boxes = side;
args.d = &buffer;
args.type = REGION_DATA;
@@ -103,13 +103,13 @@
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);
- */
+ /*
+ 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);
@@ -129,26 +129,30 @@
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;
+ //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;
+ 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){
- offset = i*per_cell + 5*num;
- float prob = scale*predictions[offset+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;
+ }
}
}
}
@@ -251,7 +255,7 @@
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);
+ convert_swag_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
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);
@@ -262,6 +266,95 @@
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);
+ int w = orig.w;
+ int h = orig.h;
+ 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)
{
@@ -269,18 +362,20 @@
if(weightfile){
load_weights(&net, weightfile);
}
- detection_layer layer = get_network_detection_layer(net);
+ region_layer layer = net.layers[net.n-1];
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
- char input[256];
+ char buff[256];
+ char *input = buff;
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);
@@ -289,7 +384,8 @@
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);
+ draw_swag(im, predictions, layer.side, layer.n, "predictions", thresh);
+ show_image(sized, "resized");
free_image(im);
free_image(sized);
#ifdef OPENCV
@@ -314,4 +410,5 @@
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);
}
--
Gitblit v1.10.0