From 0e610b056dbcd85affa23f64f9f8da4d197f110a Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 08 Sep 2016 05:46:10 +0000
Subject: [PATCH] and again
---
src/classifier.c | 360 ++++++++++++++++++++++++++++++++++++++++++++++++++++++-----
1 files changed, 329 insertions(+), 31 deletions(-)
diff --git a/src/classifier.c b/src/classifier.c
index 7060c5e..7ab70e2 100644
--- a/src/classifier.c
+++ b/src/classifier.c
@@ -3,6 +3,7 @@
#include "parser.h"
#include "option_list.h"
#include "blas.h"
+#include "assert.h"
#include "classifier.h"
#include <sys/time.h>
@@ -38,8 +39,23 @@
return options;
}
-void train_classifier(char *datacfg, char *cfgfile, char *weightfile)
+float *get_regression_values(char **labels, int n)
{
+ float *v = calloc(n, sizeof(float));
+ int i;
+ for(i = 0; i < n; ++i){
+ char *p = strchr(labels[i], ' ');
+ *p = 0;
+ v[i] = atof(p+1);
+ }
+ return v;
+}
+
+void train_classifier(char *datacfg, char *cfgfile, char *weightfile, int clear)
+{
+ int nthreads = 8;
+ int i;
+
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
@@ -49,8 +65,10 @@
if(weightfile){
load_weights(&net, weightfile);
}
+ if(clear) *net.seen = 0;
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = net.batch;
+ int imgs = net.batch*net.subdivisions/nthreads;
+ assert(net.batch*net.subdivisions % nthreads == 0);
list *options = read_data_cfg(datacfg);
@@ -65,9 +83,10 @@
printf("%d\n", plist->size);
int N = plist->size;
clock_t time;
- pthread_t load_thread;
- data train;
- data buffer;
+
+ pthread_t *load_threads = calloc(nthreads, sizeof(pthread_t));
+ data *trains = calloc(nthreads, sizeof(data));
+ data *buffers = calloc(nthreads, sizeof(data));
load_args args = {0};
args.w = net.w;
@@ -75,6 +94,11 @@
args.min = net.min_crop;
args.max = net.max_crop;
+ args.angle = net.angle;
+ args.aspect = net.aspect;
+ args.exposure = net.exposure;
+ args.saturation = net.saturation;
+ args.hue = net.hue;
args.size = net.w;
args.paths = paths;
@@ -82,41 +106,56 @@
args.n = imgs;
args.m = N;
args.labels = labels;
- args.d = &buffer;
args.type = CLASSIFICATION_DATA;
- load_thread = load_data_in_thread(args);
+ for(i = 0; i < nthreads; ++i){
+ args.d = buffers + i;
+ load_threads[i] = load_data_in_thread(args);
+ }
+
int epoch = (*net.seen)/N;
while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
time=clock();
- pthread_join(load_thread, 0);
- train = buffer;
+ for(i = 0; i < nthreads; ++i){
+ pthread_join(load_threads[i], 0);
+ trains[i] = buffers[i];
+ }
+ data train = concat_datas(trains, nthreads);
- load_thread = load_data_in_thread(args);
+ for(i = 0; i < nthreads; ++i){
+ args.d = buffers + i;
+ load_threads[i] = load_data_in_thread(args);
+ }
+
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
-/*
- int u;
- for(u = 0; u < net.batch; ++u){
- image im = float_to_image(net.w, net.h, 3, train.X.vals[u]);
- show_image(im, "loaded");
- cvWaitKey(0);
+ #ifdef OPENCV
+ if(0){
+ int u;
+ for(u = 0; u < imgs; ++u){
+ image im = float_to_image(net.w, net.h, 3, train.X.vals[u]);
+ show_image(im, "loaded");
+ cvWaitKey(0);
+ }
}
- */
+ #endif
float loss = train_network(net, train);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%d, %.3f: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), (float)(*net.seen)/N, loss, avg_loss, get_current_rate(net), sec(clock()-time), *net.seen);
free_data(train);
+ for(i = 0; i < nthreads; ++i){
+ free_data(trains[i]);
+ }
if(*net.seen/N > epoch){
epoch = *net.seen/N;
char buff[256];
sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
save_weights(net, buff);
}
- if(*net.seen%100 == 0){
+ if(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
@@ -126,8 +165,14 @@
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);
- pthread_join(load_thread, 0);
- free_data(buffer);
+ for(i = 0; i < nthreads; ++i){
+ pthread_join(load_threads[i], 0);
+ free_data(buffers[i]);
+ }
+ free(buffers);
+ free(trains);
+ free(load_threads);
+
free_network(net);
free_ptrs((void**)labels, classes);
free_ptrs((void**)paths, plist->size);
@@ -135,7 +180,7 @@
free(base);
}
-void validate_classifier(char *datacfg, char *filename, char *weightfile)
+void validate_classifier_crop(char *datacfg, char *filename, char *weightfile)
{
int i = 0;
network net = parse_network_cfg(filename);
@@ -337,10 +382,10 @@
{
int i, j;
network net = parse_network_cfg(filename);
- set_batch_network(&net, 1);
if(weightfile){
load_weights(&net, weightfile);
}
+ set_batch_network(&net, 1);
srand(time(0));
list *options = read_data_cfg(datacfg);
@@ -378,8 +423,8 @@
//cvWaitKey(0);
float *pred = network_predict(net, crop.data);
+ if(resized.data != im.data) free_image(resized);
free_image(im);
- free_image(resized);
free_image(crop);
top_k(pred, classes, topk, indexes);
@@ -411,7 +456,7 @@
char **labels = get_labels(label_list);
list *plist = get_paths(valid_list);
- int scales[] = {192, 224, 288, 320, 352};
+ int scales[] = {224, 288, 320, 352, 384};
int nscales = sizeof(scales)/sizeof(scales[0]);
char **paths = (char **)list_to_array(plist);
@@ -441,7 +486,7 @@
flip_image(r);
p = network_predict(net, r.data);
axpy_cpu(classes, 1, p, 1, pred, 1);
- free_image(r);
+ if(r.data != im.data) free_image(r);
}
free_image(im);
top_k(pred, classes, topk, indexes);
@@ -455,7 +500,7 @@
}
}
-void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename)
+void try_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int layer_num)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
@@ -486,10 +531,45 @@
if(!input) return;
strtok(input, "\n");
}
- image im = load_image_color(input, net.w, net.h);
+ image orig = load_image_color(input, 0, 0);
+ image r = resize_min(orig, 256);
+ image im = crop_image(r, (r.w - 224 - 1)/2 + 1, (r.h - 224 - 1)/2 + 1, 224, 224);
+ float mean[] = {0.48263312050943, 0.45230225481413, 0.40099074308742};
+ float std[] = {0.22590347483426, 0.22120921437787, 0.22103996251583};
+ float var[3];
+ var[0] = std[0]*std[0];
+ var[1] = std[1]*std[1];
+ var[2] = std[2]*std[2];
+
+ normalize_cpu(im.data, mean, var, 1, 3, im.w*im.h);
+
float *X = im.data;
time=clock();
float *predictions = network_predict(net, X);
+
+ layer l = net.layers[layer_num];
+ for(i = 0; i < l.c; ++i){
+ if(l.rolling_mean) printf("%f %f %f\n", l.rolling_mean[i], l.rolling_variance[i], l.scales[i]);
+ }
+ #ifdef GPU
+ cuda_pull_array(l.output_gpu, l.output, l.outputs);
+ #endif
+ for(i = 0; i < l.outputs; ++i){
+ printf("%f\n", l.output[i]);
+ }
+ /*
+
+ printf("\n\nWeights\n");
+ for(i = 0; i < l.n*l.size*l.size*l.c; ++i){
+ printf("%f\n", l.filters[i]);
+ }
+
+ printf("\n\nBiases\n");
+ for(i = 0; i < l.n; ++i){
+ printf("%f\n", l.biases[i]);
+ }
+ */
+
top_predictions(net, top, indexes);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < top; ++i){
@@ -501,6 +581,99 @@
}
}
+
+void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename)
+{
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+ srand(2222222);
+
+ list *options = read_data_cfg(datacfg);
+
+ char *name_list = option_find_str(options, "names", 0);
+ if(!name_list) name_list = option_find_str(options, "labels", "data/labels.list");
+ int top = option_find_int(options, "top", 1);
+
+ int i = 0;
+ char **names = get_labels(name_list);
+ clock_t time;
+ int *indexes = calloc(top, sizeof(int));
+ char buff[256];
+ char *input = buff;
+ int size = net.w;
+ 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 r = resize_min(im, size);
+ resize_network(&net, r.w, r.h);
+ printf("%d %d\n", r.w, r.h);
+
+ float *X = r.data;
+ time=clock();
+ float *predictions = network_predict(net, X);
+ top_predictions(net, top, indexes);
+ printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
+ for(i = 0; i < top; ++i){
+ int index = indexes[i];
+ printf("%s: %f\n", names[index], predictions[index]);
+ }
+ if(r.data != im.data) free_image(r);
+ free_image(im);
+ if (filename) break;
+ }
+}
+
+
+void label_classifier(char *datacfg, char *filename, char *weightfile)
+{
+ int i;
+ network net = parse_network_cfg(filename);
+ set_batch_network(&net, 1);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ srand(time(0));
+
+ list *options = read_data_cfg(datacfg);
+
+ char *label_list = option_find_str(options, "names", "data/labels.list");
+ char *test_list = option_find_str(options, "test", "data/train.list");
+ int classes = option_find_int(options, "classes", 2);
+
+ char **labels = get_labels(label_list);
+ list *plist = get_paths(test_list);
+
+ char **paths = (char **)list_to_array(plist);
+ int m = plist->size;
+ free_list(plist);
+
+ for(i = 0; i < m; ++i){
+ image im = load_image_color(paths[i], 0, 0);
+ image resized = resize_min(im, net.w);
+ image crop = crop_image(resized, (resized.w - net.w)/2, (resized.h - net.h)/2, net.w, net.h);
+ float *pred = network_predict(net, crop.data);
+
+ if(resized.data != im.data) free_image(resized);
+ free_image(im);
+ free_image(crop);
+ int ind = max_index(pred, classes);
+
+ printf("%s\n", labels[ind]);
+ }
+}
+
+
void test_classifier(char *datacfg, char *cfgfile, char *weightfile, int target_layer)
{
int curr = 0;
@@ -574,6 +747,127 @@
}
+void threat_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
+{
+#ifdef OPENCV
+ float threat = 0;
+ float roll = .2;
+
+ printf("Classifier Demo\n");
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+ list *options = read_data_cfg(datacfg);
+
+ srand(2222222);
+ CvCapture * cap;
+
+ if(filename){
+ cap = cvCaptureFromFile(filename);
+ }else{
+ cap = cvCaptureFromCAM(cam_index);
+ }
+
+ int top = option_find_int(options, "top", 1);
+
+ char *name_list = option_find_str(options, "names", 0);
+ char **names = get_labels(name_list);
+
+ int *indexes = calloc(top, sizeof(int));
+
+ if(!cap) error("Couldn't connect to webcam.\n");
+ //cvNamedWindow("Threat", CV_WINDOW_NORMAL);
+ //cvResizeWindow("Threat", 512, 512);
+ float fps = 0;
+ int i;
+
+ int count = 0;
+
+ while(1){
+ ++count;
+ struct timeval tval_before, tval_after, tval_result;
+ gettimeofday(&tval_before, NULL);
+
+ image in = get_image_from_stream(cap);
+ if(!in.data) break;
+ image in_s = resize_image(in, net.w, net.h);
+
+ image out = in;
+ int x1 = out.w / 20;
+ int y1 = out.h / 20;
+ int x2 = 2*x1;
+ int y2 = out.h - out.h/20;
+
+ int border = .01*out.h;
+ int h = y2 - y1 - 2*border;
+ int w = x2 - x1 - 2*border;
+
+ float *predictions = network_predict(net, in_s.data);
+ float curr_threat = predictions[0] * 0 + predictions[1] * .6 + predictions[2];
+ threat = roll * curr_threat + (1-roll) * threat;
+
+ draw_box_width(out, x2 + border, y1 + .02*h, x2 + .5 * w, y1 + .02*h + border, border, 0,0,0);
+ if(threat > .97) {
+ draw_box_width(out, x2 + .5 * w + border,
+ y1 + .02*h - 2*border,
+ x2 + .5 * w + 6*border,
+ y1 + .02*h + 3*border, 3*border, 1,0,0);
+ }
+ draw_box_width(out, x2 + .5 * w + border,
+ y1 + .02*h - 2*border,
+ x2 + .5 * w + 6*border,
+ y1 + .02*h + 3*border, .5*border, 0,0,0);
+ draw_box_width(out, x2 + border, y1 + .42*h, x2 + .5 * w, y1 + .42*h + border, border, 0,0,0);
+ if(threat > .57) {
+ draw_box_width(out, x2 + .5 * w + border,
+ y1 + .42*h - 2*border,
+ x2 + .5 * w + 6*border,
+ y1 + .42*h + 3*border, 3*border, 1,1,0);
+ }
+ draw_box_width(out, x2 + .5 * w + border,
+ y1 + .42*h - 2*border,
+ x2 + .5 * w + 6*border,
+ y1 + .42*h + 3*border, .5*border, 0,0,0);
+
+ draw_box_width(out, x1, y1, x2, y2, border, 0,0,0);
+ for(i = 0; i < threat * h ; ++i){
+ float ratio = (float) i / h;
+ float r = (ratio < .5) ? (2*(ratio)) : 1;
+ float g = (ratio < .5) ? 1 : 1 - 2*(ratio - .5);
+ draw_box_width(out, x1 + border, y2 - border - i, x2 - border, y2 - border - i, 1, r, g, 0);
+ }
+ top_predictions(net, top, indexes);
+ char buff[256];
+ sprintf(buff, "/home/pjreddie/tmp/threat_%06d", count);
+ save_image(out, buff);
+
+ printf("\033[2J");
+ printf("\033[1;1H");
+ printf("\nFPS:%.0f\n",fps);
+
+ for(i = 0; i < top; ++i){
+ int index = indexes[i];
+ printf("%.1f%%: %s\n", predictions[index]*100, names[index]);
+ }
+
+ if(0){
+ show_image(out, "Threat");
+ cvWaitKey(10);
+ }
+ free_image(in_s);
+ free_image(in);
+
+ gettimeofday(&tval_after, NULL);
+ timersub(&tval_after, &tval_before, &tval_result);
+ float curr = 1000000.f/((long int)tval_result.tv_usec);
+ fps = .9*fps + .1*curr;
+ }
+#endif
+}
+
+
void demo_classifier(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
{
#ifdef OPENCV
@@ -649,6 +943,7 @@
}
int cam_index = find_int_arg(argc, argv, "-c", 0);
+ int clear = find_arg(argc, argv, "-clear");
char *data = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
@@ -656,13 +951,16 @@
char *layer_s = (argc > 7) ? argv[7]: 0;
int layer = layer_s ? atoi(layer_s) : -1;
if(0==strcmp(argv[2], "predict")) predict_classifier(data, cfg, weights, filename);
- else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights);
+ else if(0==strcmp(argv[2], "try")) try_classifier(data, cfg, weights, filename, atoi(layer_s));
+ else if(0==strcmp(argv[2], "train")) train_classifier(data, cfg, weights, clear);
else if(0==strcmp(argv[2], "demo")) demo_classifier(data, cfg, weights, cam_index, filename);
+ else if(0==strcmp(argv[2], "threat")) threat_classifier(data, cfg, weights, cam_index, filename);
else if(0==strcmp(argv[2], "test")) test_classifier(data, cfg, weights, layer);
- else if(0==strcmp(argv[2], "valid")) validate_classifier(data, cfg, weights);
- else if(0==strcmp(argv[2], "valid10")) validate_classifier_10(data, cfg, weights);
+ else if(0==strcmp(argv[2], "label")) label_classifier(data, cfg, weights);
+ else if(0==strcmp(argv[2], "valid")) validate_classifier_single(data, cfg, weights);
else if(0==strcmp(argv[2], "validmulti")) validate_classifier_multi(data, cfg, weights);
- else if(0==strcmp(argv[2], "validsingle")) validate_classifier_single(data, cfg, weights);
+ else if(0==strcmp(argv[2], "valid10")) validate_classifier_10(data, cfg, weights);
+ else if(0==strcmp(argv[2], "validcrop")) validate_classifier_crop(data, cfg, weights);
else if(0==strcmp(argv[2], "validfull")) validate_classifier_full(data, cfg, weights);
}
--
Gitblit v1.10.0