From 0f645836f193e75c4c3b718369e6fab15b5d19c5 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 11 Feb 2015 03:41:03 +0000
Subject: [PATCH] Detection is back, baby\!
---
src/darknet.c | 306 ++++++++++++++++++++++++++++++++------------------
1 files changed, 197 insertions(+), 109 deletions(-)
diff --git a/src/darknet.c b/src/darknet.c
index 4f575dc..92a9196 100644
--- a/src/darknet.c
+++ b/src/darknet.c
@@ -57,8 +57,8 @@
int d = im.w/side;
int y = r*d+box[j+1]*d;
int x = c*d+box[j+2]*d;
- int h = box[j+3]*256;
- int w = box[j+4]*256;
+ int h = box[j+3]*im.h;
+ int w = box[j+4]*im.w;
//printf("%f %f %f %f\n", box[j+1], box[j+2], box[j+3], box[j+4]);
//printf("%d %d %d %d\n", x, y, w, h);
//printf("%d %d %d %d\n", x-w/2, y-h/2, x+w/2, y+h/2);
@@ -70,54 +70,79 @@
cvWaitKey(0);
}
-
-void train_detection_net(char *cfgfile)
+char *basename(char *cfgfile)
{
+ char *c = cfgfile;
+ char *next;
+ while((next = strchr(c, '/')))
+ {
+ c = next+1;
+ }
+ c = copy_string(c);
+ next = strchr(c, '_');
+ if (next) *next = 0;
+ next = strchr(c, '.');
+ if (next) *next = 0;
+ return c;
+}
+
+void train_detection_net(char *cfgfile, char *weightfile)
+{
+ char *base = basename(cfgfile);
+ printf("%s\n", base);
float avg_loss = 1;
- //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = 1024;
+ int imgs = 128;
srand(time(0));
//srand(23410);
- int i = 0;
- list *plist = get_paths("/home/pjreddie/data/imagenet/horse.txt");
+ int i = net.seen/imgs;
+ list *plist = get_paths("/home/pjreddie/data/imagenet/horse_pos.txt");
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
data train, buffer;
- pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, 256, 256, 7, 7, 256, &buffer);
+ int im_dim = 512;
+ int jitter = 64;
+ pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, im_dim, im_dim, 7, 7, jitter, &buffer);
clock_t time;
while(1){
i += 1;
time=clock();
pthread_join(load_thread, 0);
train = buffer;
- load_thread = load_data_detection_thread(imgs, paths, plist->size, 256, 256, 7, 7, 256, &buffer);
- //data train = load_data_detection_random(imgs, paths, plist->size, 224, 224, 7, 7, 256);
+ load_thread = load_data_detection_thread(imgs, paths, plist->size, im_dim, im_dim, 7, 7, jitter, &buffer);
-/*
- image im = float_to_image(224, 224, 3, train.X.vals[923]);
+ /*
+ image im = float_to_image(im_dim - jitter, im_dim-jitter, 3, train.X.vals[923]);
draw_detection(im, train.y.vals[923], 7);
+ show_image(im, "truth");
+ cvWaitKey(0);
*/
- normalize_data_rows(train);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
+ net.seen += imgs;
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%100==0){
char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/detnet_%d.cfg", i);
- save_network(net, buff);
+ sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
+ save_weights(net, buff);
}
free_data(train);
}
}
-void validate_detection_net(char *cfgfile)
+void validate_detection_net(char *cfgfile, char *weightfile)
{
network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
srand(time(0));
@@ -137,7 +162,6 @@
time=clock();
pthread_join(load_thread, 0);
val = buffer;
- normalize_data_rows(val);
num = (i+1)*m/splits - i*m/splits;
char **part = paths+(i*m/splits);
@@ -206,16 +230,27 @@
}
*/
-void train_imagenet(char *cfgfile)
+void convert(char *cfgfile, char *outfile, char *weightfile)
{
- float avg_loss = 1;
- //network net = parse_network_cfg("/home/pjreddie/imagenet_backup/alexnet_1270.cfg");
- srand(time(0));
network net = parse_network_cfg(cfgfile);
- //test_learn_bias(*(convolutional_layer *)net.layers[1]);
- //set_learning_network(&net, net.learning_rate, 0, net.decay);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ save_network(net, outfile);
+}
+
+void train_imagenet(char *cfgfile, char *weightfile)
+{
+ float avg_loss = -1;
+ srand(time(0));
+ char *base = basename(cfgfile);
+ printf("%s\n", base);
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
- int imgs = 3072;
+ int imgs = 1024;
int i = net.seen/imgs;
char **labels = get_labels("/home/pjreddie/data/imagenet/cls.labels.list");
list *plist = get_paths("/data/imagenet/cls.train.list");
@@ -231,34 +266,35 @@
time=clock();
pthread_join(load_thread, 0);
train = buffer;
- //normalize_data_rows(train);
- //translate_data_rows(train, -128);
- //scale_data_rows(train, 1./128);
load_thread = load_data_thread(paths, imgs, plist->size, labels, 1000, 256, 256, &buffer);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
net.seen += imgs;
+ if(avg_loss == -1) 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), net.seen);
free_data(train);
if(i%100==0){
char buff[256];
- sprintf(buff, "/home/pjreddie/imagenet_backup/alexnet_%d.cfg", i);
- save_network(net, buff);
+ sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
+ save_weights(net, buff);
}
}
}
-void validate_imagenet(char *filename)
+void validate_imagenet(char *filename, char *weightfile)
{
int i = 0;
network net = parse_network_cfg(filename);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
srand(time(0));
char **labels = get_labels("/home/pjreddie/data/imagenet/cls.val.labels.list");
- list *plist = get_paths("/home/pjreddie/data/imagenet/cls.val.list");
+ list *plist = get_paths("/data/imagenet/cls.val.list");
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
@@ -276,7 +312,6 @@
pthread_join(load_thread, 0);
val = buffer;
- //normalize_data_rows(val);
num = (i+1)*m/splits - i*m/splits;
char **part = paths+(i*m/splits);
@@ -292,9 +327,12 @@
}
}
-void test_detection(char *cfgfile)
+void test_detection(char *cfgfile, char *weightfile)
{
network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
@@ -303,7 +341,8 @@
fgets(filename, 256, stdin);
strtok(filename, "\n");
image im = load_image_color(filename, 224, 224);
- z_normalize_image(im);
+ translate_image(im, -128);
+ scale_image(im, 1/128.);
printf("%d %d %d\n", im.h, im.w, im.c);
float *X = im.data;
time=clock();
@@ -316,6 +355,7 @@
void test_init(char *cfgfile)
{
+ gpu_index = -1;
network net = parse_network_cfg(cfgfile);
set_batch_network(&net, 1);
srand(2222222);
@@ -347,10 +387,52 @@
}
free_image(im);
}
-
-void test_imagenet()
+void test_dog(char *cfgfile)
{
- network net = parse_network_cfg("cfg/imagenet_test.cfg");
+ image im = load_image_color("data/dog.jpg", 256, 256);
+ translate_image(im, -128);
+ print_image(im);
+ float *X = im.data;
+ network net = parse_network_cfg(cfgfile);
+ set_batch_network(&net, 1);
+ network_predict(net, X);
+ image crop = get_network_image_layer(net, 0);
+ show_image(crop, "cropped");
+ print_image(crop);
+ show_image(im, "orig");
+ float * inter = get_network_output(net);
+ pm(1000, 1, inter);
+ cvWaitKey(0);
+}
+
+void test_voc_segment(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+ while(1){
+ char filename[256];
+ fgets(filename, 256, stdin);
+ strtok(filename, "\n");
+ image im = load_image_color(filename, 500, 500);
+ //resize_network(net, im.h, im.w, im.c);
+ translate_image(im, -128);
+ scale_image(im, 1/128.);
+ //float *predictions = network_predict(net, im.data);
+ network_predict(net, im.data);
+ free_image(im);
+ image output = get_network_image_layer(net, net.n-2);
+ show_image(output, "Segment Output");
+ cvWaitKey(0);
+ }
+}
+
+void test_imagenet(char *cfgfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ set_batch_network(&net, 1);
//imgs=1;
srand(2222222);
int i = 0;
@@ -362,7 +444,8 @@
fgets(filename, 256, stdin);
strtok(filename, "\n");
image im = load_image_color(filename, 256, 256);
- z_normalize_image(im);
+ translate_image(im, -128);
+ scale_image(im, 1/128.);
printf("%d %d %d\n", im.h, im.w, im.c);
float *X = im.data;
time=clock();
@@ -472,28 +555,28 @@
}
/*
-void train_nist_distributed(char *address)
-{
- srand(time(0));
- network net = parse_network_cfg("cfg/nist.client");
- data train = load_categorical_data_csv("data/mnist/mnist_train.csv", 0, 10);
- //data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
- normalize_data_rows(train);
- //normalize_data_rows(test);
- int count = 0;
- int iters = 50000/net.batch;
- iters = 1000/net.batch + 1;
- while(++count <= 2000){
- clock_t start = clock(), end;
- float loss = train_network_sgd(net, train, iters);
- client_update(net, address);
- end = clock();
- //float test_acc = network_accuracy_gpu(net, test);
- //float test_acc = 0;
- printf("%d: Loss: %f, Time: %lf seconds\n", count, loss, (float)(end-start)/CLOCKS_PER_SEC);
- }
+ void train_nist_distributed(char *address)
+ {
+ srand(time(0));
+ network net = parse_network_cfg("cfg/nist.client");
+ data train = load_categorical_data_csv("data/mnist/mnist_train.csv", 0, 10);
+//data test = load_categorical_data_csv("data/mnist/mnist_test.csv",0,10);
+normalize_data_rows(train);
+//normalize_data_rows(test);
+int count = 0;
+int iters = 50000/net.batch;
+iters = 1000/net.batch + 1;
+while(++count <= 2000){
+clock_t start = clock(), end;
+float loss = train_network_sgd(net, train, iters);
+client_update(net, address);
+end = clock();
+//float test_acc = network_accuracy_gpu(net, test);
+//float test_acc = 0;
+printf("%d: Loss: %f, Time: %lf seconds\n", count, loss, (float)(end-start)/CLOCKS_PER_SEC);
}
-*/
+}
+ */
void test_ensemble()
{
@@ -535,7 +618,7 @@
void visualize_cat()
{
network net = parse_network_cfg("cfg/voc_imagenet.cfg");
- image im = load_image("data/cat.png", 0, 0);
+ image im = load_image_color("data/cat.png", 0, 0);
printf("Processing %dx%d image\n", im.h, im.w);
resize_network(net, im.h, im.w, im.c);
forward_network(net, im.data, 0, 0);
@@ -544,24 +627,6 @@
cvWaitKey(0);
}
-void test_convolutional_layer()
-{
- network net = parse_network_cfg("cfg/nist_conv.cfg");
- int size = get_network_input_size(net);
- float *in = calloc(size, sizeof(float));
- int i;
- for(i = 0; i < size; ++i) in[i] = rand_normal();
- float *in_gpu = cuda_make_array(in, size);
- convolutional_layer layer = *(convolutional_layer *)net.layers[0];
- int out_size = convolutional_out_height(layer)*convolutional_out_width(layer)*layer.batch;
- cuda_compare(layer.output_gpu, layer.output, out_size, "nothing");
- cuda_compare(layer.biases_gpu, layer.biases, layer.n, "biases");
- cuda_compare(layer.filters_gpu, layer.filters, layer.n*layer.size*layer.size*layer.c, "filters");
- bias_output(layer);
- bias_output_gpu(layer);
- cuda_compare(layer.output_gpu, layer.output, out_size, "biased output");
-}
-
void test_correct_nist()
{
network net = parse_network_cfg("cfg/nist_conv.cfg");
@@ -586,7 +651,7 @@
gpu_index = -1;
count = 0;
srand(222222);
- net = parse_network_cfg("cfg/nist_conv.cfg");
+ net = parse_network_cfg("cfg/nist_conv.cfg");
while(++count <= 5){
clock_t start = clock(), end;
float loss = train_network_sgd(net, train, iters);
@@ -641,40 +706,44 @@
}
/*
-void run_server()
-{
- srand(time(0));
- network net = parse_network_cfg("cfg/net.cfg");
- set_batch_network(&net, 1);
- server_update(net);
-}
+ void run_server()
+ {
+ srand(time(0));
+ network net = parse_network_cfg("cfg/net.cfg");
+ set_batch_network(&net, 1);
+ server_update(net);
+ }
-void test_client()
-{
- network net = parse_network_cfg("cfg/alexnet.client");
- clock_t time=clock();
- client_update(net, "localhost");
- printf("1\n");
- client_update(net, "localhost");
- printf("2\n");
- client_update(net, "localhost");
- printf("3\n");
- printf("Transfered: %lf seconds\n", sec(clock()-time));
-}
-*/
+ void test_client()
+ {
+ network net = parse_network_cfg("cfg/alexnet.client");
+ clock_t time=clock();
+ client_update(net, "localhost");
+ printf("1\n");
+ client_update(net, "localhost");
+ printf("2\n");
+ client_update(net, "localhost");
+ printf("3\n");
+ printf("Transfered: %lf seconds\n", sec(clock()-time));
+ }
+ */
void del_arg(int argc, char **argv, int index)
{
int i;
for(i = index; i < argc-1; ++i) argv[i] = argv[i+1];
+ argv[i] = 0;
}
int find_arg(int argc, char* argv[], char *arg)
{
int i;
- for(i = 0; i < argc; ++i) if(0==strcmp(argv[i], arg)) {
- del_arg(argc, argv, i);
- return 1;
+ for(i = 0; i < argc; ++i) {
+ if(!argv[i]) continue;
+ if(0==strcmp(argv[i], arg)) {
+ del_arg(argc, argv, i);
+ return 1;
+ }
}
return 0;
}
@@ -683,6 +752,7 @@
{
int i;
for(i = 0; i < argc-1; ++i){
+ if(!argv[i]) continue;
if(0==strcmp(argv[i], arg)){
def = atoi(argv[i+1]);
del_arg(argc, argv, i);
@@ -693,6 +763,20 @@
return def;
}
+void scale_rate(char *filename, float scale)
+{
+ // Ready for some weird shit??
+ FILE *fp = fopen(filename, "r+b");
+ if(!fp) file_error(filename);
+ float rate = 0;
+ fread(&rate, sizeof(float), 1, fp);
+ printf("Scaling learning rate from %f to %f\n", rate, rate*scale);
+ rate = rate*scale;
+ fseek(fp, 0, SEEK_SET);
+ fwrite(&rate, sizeof(float), 1, fp);
+ fclose(fp);
+}
+
int main(int argc, char **argv)
{
//test_convolutional_layer();
@@ -713,7 +797,6 @@
if(0==strcmp(argv[1], "test_correct")) test_correct_alexnet();
else if(0==strcmp(argv[1], "test_correct_nist")) test_correct_nist();
- else if(0==strcmp(argv[1], "test")) test_imagenet();
//else if(0==strcmp(argv[1], "server")) run_server();
#ifdef GPU
@@ -724,23 +807,28 @@
fprintf(stderr, "usage: %s <function> <filename>\n", argv[0]);
return 0;
}
- else if(0==strcmp(argv[1], "detection")) train_detection_net(argv[2]);
+ else if(0==strcmp(argv[1], "detection")) train_detection_net(argv[2], (argc > 3)? argv[3] : 0);
+ else if(0==strcmp(argv[1], "test")) test_imagenet(argv[2]);
+ else if(0==strcmp(argv[1], "dog")) test_dog(argv[2]);
else if(0==strcmp(argv[1], "ctrain")) train_cifar10(argv[2]);
else if(0==strcmp(argv[1], "nist")) train_nist(argv[2]);
else if(0==strcmp(argv[1], "ctest")) test_cifar10(argv[2]);
- else if(0==strcmp(argv[1], "train")) train_imagenet(argv[2]);
+ else if(0==strcmp(argv[1], "train")) train_imagenet(argv[2], (argc > 3)? argv[3] : 0);
+ else if(0==strcmp(argv[1], "testseg")) test_voc_segment(argv[2], (argc > 3)? argv[3] : 0);
//else if(0==strcmp(argv[1], "client")) train_imagenet_distributed(argv[2]);
- else if(0==strcmp(argv[1], "detect")) test_detection(argv[2]);
+ else if(0==strcmp(argv[1], "detect")) test_detection(argv[2], (argc > 3)? argv[3] : 0);
else if(0==strcmp(argv[1], "init")) test_init(argv[2]);
else if(0==strcmp(argv[1], "visualize")) test_visualize(argv[2]);
- else if(0==strcmp(argv[1], "valid")) validate_imagenet(argv[2]);
+ else if(0==strcmp(argv[1], "valid")) validate_imagenet(argv[2], (argc > 3)? argv[3] : 0);
else if(0==strcmp(argv[1], "testnist")) test_nist(argv[2]);
- else if(0==strcmp(argv[1], "validetect")) validate_detection_net(argv[2]);
+ else if(0==strcmp(argv[1], "validetect")) validate_detection_net(argv[2], (argc > 3)? argv[3] : 0);
else if(argc < 4){
fprintf(stderr, "usage: %s <function> <filename> <filename>\n", argv[0]);
return 0;
}
else if(0==strcmp(argv[1], "compare")) compare_nist(argv[2], argv[3]);
+ else if(0==strcmp(argv[1], "convert")) convert(argv[2], argv[3], (argc > 4)? argv[4] : 0);
+ else if(0==strcmp(argv[1], "scale")) scale_rate(argv[2], atof(argv[3]));
fprintf(stderr, "Success!\n");
return 0;
}
--
Gitblit v1.10.0