From ae43c2bc32fbb838bfebeeaf2c2b058ccab5c83c Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@burninator.cs.washington.edu>
Date: Thu, 23 Jun 2016 05:31:14 +0000
Subject: [PATCH] hi
---
src/swag.c | 330 ------------------------------------------------------
1 files changed, 4 insertions(+), 326 deletions(-)
diff --git a/src/swag.c b/src/swag.c
index 8c9ce3c..f06db4c 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"
@@ -10,49 +9,9 @@
#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 *predictions, int side, int num, char *label, float thresh)
-{
- int classes = 20;
- int i,n;
-
- 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;
-
- 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/test/train.txt";
+ char *train_images = "data/voc.0712.trainval";
char *backup_directory = "/home/pjreddie/backup/";
srand(time(0));
data_seed = time(0);
@@ -68,7 +27,6 @@
int i = *net.seen/imgs;
data train, buffer;
-
layer l = net.layers[net.n - 1];
int side = l.side;
@@ -103,21 +61,13 @@
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);
@@ -129,276 +79,8 @@
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_";
- 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, 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);
- 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);
- 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)
-{
-
- network net = parse_network_cfg(cfgfile);
- if(weightfile){
- load_weights(&net, weightfile);
- }
- region_layer layer = net.layers[net.n-1];
- set_batch_network(&net, 1);
- srand(2222222);
- clock_t time;
- char buff[256];
- char *input = buff;
- 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));
- draw_swag(im, predictions, layer.side, layer.n, "predictions", thresh);
- show_image(sized, "resized");
- 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;
@@ -406,9 +88,5 @@
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);
+ if(0==strcmp(argv[2], "train")) train_swag(cfg, weights);
}
--
Gitblit v1.10.0