void denormalize_net(char *cfgfile, char *weightfile, char *outfile)
{
gpu_index = -1;
network *net = load_network(cfgfile, weightfile, 0);
int i;
for (i = 0; i < net->n; ++i) {
layer l = net->layers[i];
if ((l.type == DECONVOLUTIONAL || l.type == CONVOLUTIONAL) && l.batch_normalize) {
denormalize_convolutional_layer(l);
net->layers[i].batch_normalize=0;
}
if (l.type == CONNECTED && l.batch_normalize) {
denormalize_connected_layer(l);
net->layers[i].batch_normalize=0;
}
if (l.type == GRU && l.batch_normalize) {
denormalize_connected_layer(*l.input_z_layer);
denormalize_connected_layer(*l.input_r_layer);
denormalize_connected_layer(*l.input_h_layer);
denormalize_connected_layer(*l.state_z_layer);
denormalize_connected_layer(*l.state_r_layer);
denormalize_connected_layer(*l.state_h_layer);
l.input_z_layer->batch_normalize = 0;
l.input_r_layer->batch_normalize = 0;
l.input_h_layer->batch_normalize = 0;
l.state_z_layer->batch_normalize = 0;
l.state_r_layer->batch_normalize = 0;
l.state_h_layer->batch_normalize = 0;
net->layers[i].batch_normalize=0;
}
}
save_weights(net, outfile);
free_network(net);
}
void normalize_net(char *cfgfile, char *weightfile, char *outfile)
{
gpu_index = -1;
network *net = load_network(cfgfile, weightfile, 0);
int i;
for(i = 0; i < net->n; ++i){
layer l = net->layers[i];
if(l.type == CONVOLUTIONAL && !l.batch_normalize){
net->layers[i] = normalize_layer(l, l.n);
}
if (l.type == CONNECTED && !l.batch_normalize) {
net->layers[i] = normalize_layer(l, l.outputs);
}
if (l.type == GRU && l.batch_normalize) {
*l.input_z_layer = normalize_layer(*l.input_z_layer, l.input_z_layer->outputs);
*l.input_r_layer = normalize_layer(*l.input_r_layer, l.input_r_layer->outputs);
*l.input_h_layer = normalize_layer(*l.input_h_layer, l.input_h_layer->outputs);
*l.state_z_layer = normalize_layer(*l.state_z_layer, l.state_z_layer->outputs);
*l.state_r_layer = normalize_layer(*l.state_r_layer, l.state_r_layer->outputs);
*l.state_h_layer = normalize_layer(*l.state_h_layer, l.state_h_layer->outputs);
net->layers[i].batch_normalize=1;
}
}
save_weights(net, outfile);
free_network(net);
}
void mkimg(char *cfgfile, char *weightfile, int h, int w, int num, char *prefix)
{
network *net = load_network(cfgfile, weightfile, 0);
image *ims = get_weights(net->layers[0]);
int n = net->layers[0].n;
int z;
for(z = 0; z < num; ++z){
image im = make_image(h, w, 3);
fill_image(im, .5);
int i;
for(i = 0; i < 100; ++i){
image r = copy_image(ims[rand()%n]);
rotate_image_cw(r, rand()%4);
random_distort_image(r, 1, 1.5, 1.5);
int dx = rand()%(w-r.w);
int dy = rand()%(h-r.h);
ghost_image(r, im, dx, dy);
free_image(r);
}
char buff[256];
sprintf(buff, "%s/gen_%d", prefix, z);
save_image(im, buff);
free_image(im);
}
free_network(net);
}
void partial(char *cfgfile, char *weightfile, char *outfile, int max)
{
gpu_index = -1;
network *net = load_network(cfgfile, weightfile, 1);
save_weights_upto(net, outfile, max);
free_network(net);
}
void predict_regressor(char *cfgfile, char *weightfile, char *filename)
{
network *net = load_network(cfgfile, weightfile, 0);
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 = letterbox_image(im, net->w, net->h);
float *X = sized.data;
time=clock();
float *predictions = network_predict(net, X);
printf("Predicted: %f\n", predictions[0]);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
free_image(im);
free_image(sized);
if (filename) break;
}
free_network(net);
}
void oneoff(char *cfgfile, char *weightfile, char *outfile)
{
gpu_index = -1;
network *net = parse_network_cfg(cfgfile);
int oldn = net->layers[net->n - 2].n;
int c = net->layers[net->n - 2].c;
scal_cpu(oldn*c, .1, net->layers[net->n - 2].weights, 1);
scal_cpu(oldn, 0, net->layers[net->n - 2].biases, 1);
net->layers[net->n - 2].n = 11921;
net->layers[net->n - 2].biases += 5;
net->layers[net->n - 2].weights += 5*c;
if(weightfile){
load_weights(net, weightfile);
}
net->layers[net->n - 2].biases -= 5;
net->layers[net->n - 2].weights -= 5*c;
net->layers[net->n - 2].n = oldn;
printf("%d\n", oldn);
layer l = net->layers[net->n - 2];
copy_cpu(l.n/3, l.biases, 1, l.biases + l.n/3, 1);
copy_cpu(l.n/3, l.biases, 1, l.biases + 2*l.n/3, 1);
copy_cpu(l.n/3*l.c, l.weights, 1, l.weights + l.n/3*l.c, 1);
copy_cpu(l.n/3*l.c, l.weights, 1, l.weights + 2*l.n/3*l.c, 1);
*net->seen = 0;
save_weights(net, outfile);
free_network(net);
}
void test_cgm(char *cfgfile, char *weightfile, char *session)
{
char *base = basecfg(cfgfile);
printf("%s\n", base);
network net = parse_network_cfg(cfgfile);
load_weights(&net, weightfile);
freopen("out.txt", "w", stdout);
int input_len = net.w;
int stride = net.w/4;
int i,j,k;
data train;
train.shallow = 0;
train.X = make_matrix(128, net.w*net.h*net.c);
train.y = make_matrix(128, 1);
float cbuf[4096*16];
int cidx = 0;
int cnt = 0;
int cntstride = 0;
int freq[16] = {0};
FILE *fp = fopen(session, "rb");
if(!fp) file_error(session);
while (!feof(fp))
{
unsigned short bytes[11];
fread(bytes, 2, 11, fp);
float fbytes[2];
fread(fbytes, 4, 2, fp);
// put into circular buffer
for (j=0;j<10;j++)
cbuf[cidx+(j<<12)] = (float)(bytes[j])/65536.f;
cidx = (1+cidx)&4095;
cnt++;
cntstride++;
if (fbytes[0]>54 && cnt>input_len && cntstride>stride)
{
cntstride = 0;
train.y.vals[0][0] = (fbytes[0]-50)/200.0;
for (k=0;k<net.w;k++)
for (j=0;j<10;j++)
{
train.X.vals[0][(j*net.w)+k] = cbuf[(j<<12)+(((cidx-1-net.w+k)+4096)&4095)];
}
float *p = network_predict(net, train.X.vals[0]);
// fprintf(stderr, "%f, %f\n", train.y.vals[0][0], p[0]);
p[0] = (p[0]*200.0)+50.0;
fprintf(stdout, "%f, %f\n", fbytes[0], p[0]);
fprintf(stderr, "%f, %f\n", fbytes[0], p[0]);
}
}
fclose(fp);
free_network(net);
free_data(train);
}
void statistics_net(char *cfgfile, char *weightfile)
{
gpu_index = -1;
network *net = load_network(cfgfile, weightfile, 0);
int i;
for (i = 0; i < net->n; ++i) {
layer l = net->layers[i];
if (l.type == CONNECTED && l.batch_normalize) {
printf("Connected Layer %d\n", i);
statistics_connected_layer(l);
}
if (l.type == GRU && l.batch_normalize) {
printf("GRU Layer %d\n", i);
printf("Input Z\n");
statistics_connected_layer(*l.input_z_layer);
printf("Input R\n");
statistics_connected_layer(*l.input_r_layer);
printf("Input H\n");
statistics_connected_layer(*l.input_h_layer);
printf("State Z\n");
statistics_connected_layer(*l.state_z_layer);
printf("State R\n");
statistics_connected_layer(*l.state_r_layer);
printf("State H\n");
statistics_connected_layer(*l.state_h_layer);
}
printf("\n");
}
free_network(net);
}
int main(int argc, char** argv) {
int NUM_PASSES = 100;
if (argc < 3) {
fprintf(stderr, "Usage: ./mnist <test|inference> [NUMBER_PASSES]\n");
return 2;
}
else{
NUM_PASSES = atoi(argv[2]);
}
Network* net = construct_scene_labeling_net();
initialize_network(net, 1);
if (!strcmp(argv[1], "inference")) {
//net_measure_inference_time(net);
return 1;
}
if (!strcmp(argv[1], "test")){
// net_test(net, input, labels, NUM_PASSES);
}
free_network(net);
return 2;
}
void operations(char *cfgfile)
{
gpu_index = -1;
network *net = parse_network_cfg(cfgfile);
long ops = numops(net);
printf("Floating Point Operations: %ld\n", ops);
printf("Floating Point Operations: %.2f Bn\n", (float)ops/1000000000.);
free_network( net );
}
void train_mnist_distill(char *cfgfile, char *weightfile)
{
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
char *base = basecfg(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);
char *backup_directory = "backup";
int classes = 10;
int N = 50000;
int epoch = (*net.seen)/N;
data train;// = load_all_mnist10();
matrix soft = csv_to_matrix("results/ensemble.csv");
float weight = .9;
scale_matrix(soft, weight);
scale_matrix(train.y, 1. - weight);
matrix_add_matrix(soft, train.y);
while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
clock_t time=clock();
float loss = train_network_sgd(net, train, 1);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.95 + loss*.05;
if(get_current_batch(net)%100 == 0)
{
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);
}
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(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
}
}
char buff[256];
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);
free_network(net);
free(base);
free_data(train);
}
void train_go(char *cfgfile, char *weightfile)
{
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
char *base = basecfg(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);
char *backup_directory = "/home/pjreddie/backup/";
char buff[256];
float *board = calloc(19*19*net.batch, sizeof(float));
float *move = calloc(19*19*net.batch, sizeof(float));
moves m = load_go_moves("/home/pjreddie/go.train");
//moves m = load_go_moves("games.txt");
int N = m.n;
int epoch = (*net.seen)/N;
while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
clock_t time=clock();
random_go_moves(m, board, move, net.batch);
float loss = train_network_datum(net, board, move) / net.batch;
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.95 + loss*.05;
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);
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(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
}
if(get_current_batch(net)%10000 == 0){
char buff[256];
sprintf(buff, "%s/%s_%d.backup",backup_directory,base,get_current_batch(net));
save_weights(net, buff);
}
}
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);
free_network(net);
free(base);
}
void oneoff2(char *cfgfile, char *weightfile, char *outfile, int l)
{
gpu_index = -1;
network *net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights_upto(net, weightfile, 0, net->n);
load_weights_upto(net, weightfile, l, net->n);
}
*net->seen = 0;
save_weights_upto(net, outfile, net->n);
free_network(net);
}
void test_lsd(char *cfg, char *weights, char *filename, int gray)
{
network *net = load_network(cfg, weights, 0);
set_batch_network(net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
int i, imlayer = 0;
for (i = 0; i < net->n; ++i) {
if (net->layers[i].out_c == 3) {
imlayer = i;
printf("%d\n", i);
break;
}
}
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 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);
if(gray) grayscale_image_3c(crop);
float *X = crop.data;
time=clock();
network_predict(net, X);
image out = get_network_image_layer(net, imlayer);
//yuv_to_rgb(out);
constrain_image(out);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
save_image(out, "out");
show_image(out, "out", 1);
show_image(crop, "crop", 0);
free_image(im);
free_image(resized);
free_image(crop);
if (filename) break;
}
free_network(net);
}
void rgbgr_net(char *cfgfile, char *weightfile, char *outfile)
{
gpu_index = -1;
network *net = load_network(cfgfile, weightfile, 0);
int i;
for(i = 0; i < net->n; ++i){
layer l = net->layers[i];
if(l.type == CONVOLUTIONAL){
rgbgr_weights(l);
break;
}
}
save_weights(net, outfile);
free_network(net);
}
void demo_regressor(char *datacfg, char *cfgfile, char *weightfile, int cam_index, const char *filename)
{
#ifdef OPENCV
printf("Regressor Demo\n");
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
srand(2222222);
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 1);
char *name_list = option_find_str(options, "names", 0);
char **names = get_labels(name_list);
void * cap = open_video_stream(filename, cam_index, 0,0,0);
if(!cap) error("Couldn't connect to webcam.\n");
float fps = 0;
while(1){
struct timeval tval_before, tval_after, tval_result;
gettimeofday(&tval_before, NULL);
image in = get_image_from_stream(cap);
image crop = center_crop_image(in, net->w, net->h);
grayscale_image_3c(crop);
float *predictions = network_predict(net, crop.data);
printf("\033[2J");
printf("\033[1;1H");
printf("\nFPS:%.0f\n",fps);
int i;
for(i = 0; i < classes; ++i){
printf("%s: %f\n", names[i], predictions[i]);
}
show_image(crop, "Regressor", 10);
free_image(in);
free_image(crop);
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;
}
free_network(net);
#endif
}
void train_cifar(char *cfgfile, char *weightfile)
{
srand(time(0));
float avg_loss = -1;
char *base = basecfg(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);
char *backup_directory = "/home/pjreddie/backup/";
int classes = 10;
int N = 50000;
char **labels = get_labels("data/cifar/labels.txt");
int epoch = (*net.seen)/N;
data train = load_all_cifar10();
while(get_current_batch(net) < net.max_batches || net.max_batches == 0){
clock_t time=clock();
float loss = train_network_sgd(net, train, 1);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.95 + loss*.05;
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);
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(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
}
}
char buff[256];
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);
free_network(net);
free_ptrs((void**)labels, classes);
free(base);
free_data(train);
}
// Perform the classification (this calls into the functions from cnn.c
double run_classification(int* samples, int n, double** keep_output) {
fprintf(stderr, "Making network...\n");
network_t* net = load_cnn_snapshot();
fprintf(stderr, "Loading batches...\n");
for (int i = 0; i < n; i++) {
int batch = samples[i]/10000;
if (batches[batch] == NULL) {
batches[batch] = load_batch(batch);
}
}
vol_t** input = (vol_t**)malloc(sizeof(vol_t*)*n);
double* output = (double*)malloc(sizeof(double)*n);
for (int i = 0; i < n; i++) {
input[i] = batches[samples[i]/10000][samples[i]%10000];
}
fprintf(stderr, "Running classification...\n");
uint64_t start_time = timestamp_us();
net_classify_cats(net, input, output, n);
uint64_t end_time = timestamp_us();
for (int i = 0; i < n; i++) {
samples[i] = (output[i] > 0.5) ? 0 : -1;
}
double dt = (double)(end_time-start_time) / 1000.0;
fprintf(stderr, "TIME: %lf ms\n", dt);
free_network(net);
free(input);
if (keep_output == NULL)
free(output);
else
*keep_output = output;
return dt;
}
int main(int argc, char** argv) {
int NUM_PASSES = 100;
if (argc < 3) {
fprintf(stderr, "Usage: ./gtsrb <test|inference> [NUMBER_PASSES]\n");
return 2;
}
else{
NUM_PASSES = atoi(argv[2]);
}
Network* net = construct_gtsrb_net();
initialize_network(net, 1);
vol_t** input = (vol_t**)malloc(sizeof(vol_t*)*NUM_PASSES);
label_t* labels = (label_t*)malloc(sizeof(label_t)*NUM_PASSES);
load_gtsrb_data(input, labels, NUM_PASSES);
int valid = 0;
if (!strcmp(argv[1], "inference")) {
net_predict_Multiple(net, input, NUM_PASSES);
valid = 1;
}
if (!strcmp(argv[1], "test")){
net_test(net, input, labels, NUM_PASSES);
valid = 1;
}
#ifdef DEBUGG
print_vol(net->buffer[4][0],0);
#endif
free_network(net);
for(int i = 0; i < NUM_PASSES; i++)
free(input[i]);
free(input);
free(labels);
if(valid) return 0;
fprintf(stderr,"unrecognised command\n");
return 2;
}
void test_yolo(char *cfgfile, char *weightfile, char *filename, float thresh)
{
image **alphabet = load_alphabet();
network *net = load_network(cfgfile, weightfile, 0);
layer l = net->layers[net->n-1];
set_batch_network(net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
float nms=.4;
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();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
int nboxes = 0;
detection *dets = get_network_boxes(net, 1, 1, thresh, 0, 0, 0, &nboxes);
if (nms) do_nms_sort(dets, l.side*l.side*l.n, l.classes, nms);
draw_detections(im, dets, l.side*l.side*l.n, thresh, voc_names, alphabet, 20);
save_image(im, "predictions");
show_image(im, "predictions", 0);
free_detections(dets, nboxes);
free_image(im);
free_image(sized);
if (filename) break;
}
free_network(net);
}
void demo_segmenter(char *datacfg, char *cfg, char *weights, int cam_index, const char *filename)
{
#ifdef OPENCV
printf("Classifier Demo\n");
network *net = load_network(cfg, weights, 0);
set_batch_network(net, 1);
srand(2222222);
void * cap = open_video_stream(filename, cam_index, 0,0,0);
if(!cap) error("Couldn't connect to webcam.\n");
float fps = 0;
while(1){
struct timeval tval_before, tval_after, tval_result;
gettimeofday(&tval_before, NULL);
image in = get_image_from_stream(cap);
image in_s = letterbox_image(in, net->w, net->h);
network_predict(net, in_s.data);
printf("\033[2J");
printf("\033[1;1H");
printf("\nFPS:%.0f\n",fps);
image pred = get_network_image(net);
image prmask = mask_to_rgb(pred);
show_image(prmask, "Segmenter", 10);
free_image(in_s);
free_image(in);
free_image(prmask);
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;
}
free_network(net);
#endif
}
void test_dcgan(char *cfgfile, char *weightfile)
{
network *net = load_network(cfgfile, weightfile, 0);
set_batch_network(net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
int imlayer = 0;
imlayer = net->n-1;
while(1){
image im = make_image(net->w, net->h, net->c);
int i;
for(i = 0; i < im.w*im.h*im.c; ++i){
im.data[i] = rand_normal();
}
//float mag = mag_array(im.data, im.w*im.h*im.c);
//scale_array(im.data, im.w*im.h*im.c, 1./mag);
float *X = im.data;
time=clock();
network_predict(net, X);
image out = get_network_image_layer(net, imlayer);
//yuv_to_rgb(out);
normalize_image(out);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
save_image(out, "out");
show_image(out, "out", 0);
free_image(im);
}
free_network(net);
}
void train_compare(char *cfgfile, char *weightfile)
{
data_seed = time(0);
srand(time(0));
float avg_loss = -1;
char *base = basecfg(cfgfile);
char *backup_directory = "/home/pjreddie/backup/";
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 = 1024;
list *plist = get_paths("data/compare.train.list");
char **paths = (char **)list_to_array(plist);
int N = plist->size;
printf("%d\n", N);
clock_t time;
#ifndef _MSC_VER
pthread_t load_thread;
#endif
data train;
data buffer;
load_args args = {0};
args.w = net.w;
args.h = net.h;
args.paths = paths;
args.classes = 20;
args.n = imgs;
args.m = N;
args.d = &buffer;
args.type = COMPARE_DATA;
#ifndef _MSC_VER
load_thread = load_data_in_thread(args);
#endif
int epoch = *net.seen/N;
int i = 0;
while(1){
++i;
time=clock();
#ifndef _MSC_VER
pthread_join(load_thread, 0);
#else
load_data_in_thread(args);
#endif
train = buffer;
#ifndef _MSC_VER
load_thread = load_data_in_thread(args);
#endif
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = train_network(net, train);
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%.3f: %f, %f avg, %lf seconds, %d images\n", (float)*net.seen/N, loss, avg_loss, sec(clock()-time), *net.seen);
free_data(train);
if(i%100 == 0){
char buff[256];
sprintf(buff, "%s/%s_%d_minor_%d.weights",backup_directory,base, epoch, i);
save_weights(net, buff);
}
if(*net.seen/N > epoch){
epoch = *net.seen/N;
i = 0;
char buff[256];
sprintf(buff, "%s/%s_%d.weights",backup_directory,base, epoch);
save_weights(net, buff);
if(epoch%22 == 0) net.learning_rate *= .1;
}
}
#ifndef _MSC_VER
pthread_join(load_thread, 0);
#endif
free_data(buffer);
free_network(net);
free_ptrs((void**)paths, plist->size);
free_list(plist);
free(base);
}
void free_state(struct State *S)
{
free_network(&S->ntw);
free_simulation(&S->sim);
}
void validate_yolo(char *cfg, char *weights)
{
network *net = load_network(cfg, weights, 0);
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("data/voc.2007.test");
list *plist = get_paths("/home/pjreddie/data/voc/2007_test.txt");
//list *plist = get_paths("data/voc.2012.test");
char **paths = (char **)list_to_array(plist);
layer l = net->layers[net->n-1];
int classes = l.classes;
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");
}
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;
network_predict(net, X);
int w = val[t].w;
int h = val[t].h;
int nboxes = 0;
detection *dets = get_network_boxes(net, w, h, thresh, 0, 0, 0, &nboxes);
if (nms) do_nms_sort(dets, l.side*l.side*l.n, classes, iou_thresh);
print_yolo_detections(fps, id, l.side*l.side*l.n, classes, w, h, dets);
free_detections(dets, nboxes);
free(id);
free_image(val[t]);
free_image(val_resized[t]);
}
}
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
free_network( net );
}
void train_yolo(char *cfgfile, char *weightfile)
{
char *train_images = "/data/voc/train.txt";
char *backup_directory = "/home/kunle12/backup/";
srand(time(0));
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
network * net = load_network(cfgfile, weightfile, 0);
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net->learning_rate, net->momentum, net->decay);
int imgs = net->batch*net->subdivisions;
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;
char **paths = (char **)list_to_array(plist);
load_args args = {0};
args.w = net->w;
args.h = net->h;
args.paths = paths;
args.n = imgs;
args.m = plist->size;
args.classes = classes;
args.jitter = jitter;
args.num_boxes = side;
args.d = &buffer;
args.type = REGION_DATA;
args.angle = net->angle;
args.exposure = net->exposure;
args.saturation = net->saturation;
args.hue = net->hue;
pthread_t load_thread = load_data_in_thread(args);
clock_t time;
//while(i*imgs < N*120){
while(get_current_batch(net) < net->max_batches){
i += 1;
time=clock();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data_in_thread(args);
printf("Loaded: %lf seconds\n", sec(clock()-time));
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, %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 < 1000 && i%100 == 0)){
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
}
free_data(train);
}
char buff[256];
sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
free_network( net );
}
void validate_yolo_recall(char *cfg, char *weights)
{
network *net = load_network(cfg, weights, 0);
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("data/voc.2007.test");
char **paths = (char **)list_to_array(plist);
layer l = net->layers[net->n-1];
int classes = l.classes;
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");
}
int m = plist->size;
int i=0;
float thresh = .001;
float iou_thresh = .5;
float nms = 0;
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);
network_predict(net, sized.data);
int nboxes = 0;
detection *dets = get_network_boxes(net, orig.w, orig.h, thresh, 0, 0, 1, &nboxes);
if (nms) do_nms_obj(dets, side*side*l.n, 1, nms);
char labelpath[4096];
find_replace(path, "images", "labels", labelpath);
find_replace(labelpath, "JPEGImages", "labels", labelpath);
find_replace(labelpath, ".jpg", ".txt", labelpath);
find_replace(labelpath, ".JPEG", ".txt", labelpath);
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < side*side*l.n; ++k){
if(dets[k].objectness > 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(dets[k].bbox, t);
if(dets[k].objectness > 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_detections(dets, nboxes);
free(id);
free_image(orig);
free_image(sized);
}
free_network( net );
}
void train_regressor(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
{
int i;
float avg_loss = -1;
char *base = basecfg(cfgfile);
printf("%s\n", base);
printf("%d\n", ngpus);
network **nets = calloc(ngpus, sizeof(network*));
srand(time(0));
int seed = rand();
for(i = 0; i < ngpus; ++i){
srand(seed);
#ifdef GPU
cuda_set_device(gpus[i]);
#endif
nets[i] = load_network(cfgfile, weightfile, clear);
nets[i]->learning_rate *= ngpus;
}
srand(time(0));
network *net = nets[0];
int imgs = net->batch * net->subdivisions * ngpus;
printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net->learning_rate, net->momentum, net->decay);
list *options = read_data_cfg(datacfg);
char *backup_directory = option_find_str(options, "backup", "/backup/");
char *train_list = option_find_str(options, "train", "data/train.list");
int classes = option_find_int(options, "classes", 1);
list *plist = get_paths(train_list);
char **paths = (char **)list_to_array(plist);
printf("%d\n", plist->size);
int N = plist->size;
clock_t time;
load_args args = {0};
args.w = net->w;
args.h = net->h;
args.threads = 32;
args.classes = classes;
args.min = net->min_ratio*net->w;
args.max = net->max_ratio*net->w;
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;
args.n = imgs;
args.m = N;
args.type = REGRESSION_DATA;
data train;
data buffer;
pthread_t load_thread;
args.d = &buffer;
load_thread = load_data(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;
load_thread = load_data(args);
printf("Loaded: %lf seconds\n", sec(clock()-time));
time=clock();
float loss = 0;
#ifdef GPU
if(ngpus == 1){
loss = train_network(net, train);
} else {
loss = train_networks(nets, ngpus, train, 4);
}
#else
loss = train_network(net, train);
#endif
if(avg_loss == -1) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
printf("%ld, %.3f: %f, %f avg, %f rate, %lf seconds, %ld 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);
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(get_current_batch(net)%100 == 0){
char buff[256];
sprintf(buff, "%s/%s.backup",backup_directory,base);
save_weights(net, buff);
}
}
char buff[256];
sprintf(buff, "%s/%s.weights", backup_directory, base);
save_weights(net, buff);
for(i = 0; i < ngpus; ++i){
free_network(nets[i]);
}
free(nets);
free_ptrs((void**)paths, plist->size);
free_list(plist);
free(base);
}
/* Function to be called from R */
void R_epidemics(int *seqLength, double *mutRate, int *npop, int *nHostPerPop, double *beta, int *nStart, int *t1, int *t2, int *Nsample, int *Tsample, int *duration, int *nbnb, int *listnb, double *pdisp){
int i, nstep, counter_sample = 0, tabidx;
/* Initialize random number generator */
int j;
time_t t;
t = time(NULL); // time in seconds, used to change the seed of the random generator
gsl_rng * rng;
const gsl_rng_type *typ;
gsl_rng_env_setup();
typ=gsl_rng_default;
rng=gsl_rng_alloc(typ);
gsl_rng_set(rng,t); // changes the seed of the random generator
/* transfer simulation parameters */
struct param * par;
par = (struct param *) malloc(sizeof(struct param));
par->L = *seqLength;
par->mu = *mutRate;
par->muL = par->mu * par->L;
par->rng = rng;
par->npop = *npop;
par->popsizes = nHostPerPop;
par->beta = *beta;
par->nstart = *nStart;
par->t1 = *t1;
par->t2 = *t2;
par->t_sample = Tsample;
par->n_sample = *Nsample;
par->duration = *duration;
par->cn_nb_nb = nbnb;
par->cn_list_nb = listnb;
par->cn_weights = pdisp;
/* check/print parameters */
check_param(par);
print_param(par);
/* dispersal matrix */
struct network *cn = create_network(par);
/* print_network(cn, TRUE); */
/* group sizes */
struct ts_groupsizes * grpsizes = create_ts_groupsizes(par);
/* initiate population */
struct metapopulation * metapop;
metapop = create_metapopulation(par);
/* get sampling schemes (timestep+effectives) */
translate_dates(par);
struct table_int *tabdates = get_table_int(par->t_sample, par->n_sample);
printf("\n\nsampling at timesteps:");
print_table_int(tabdates);
/* create sample */
struct sample ** samplist = (struct sample **) malloc(tabdates->n * sizeof(struct sample *));
struct sample *samp;
/* MAKE METAPOPULATION EVOLVE */
nstep = 0;
while(get_total_nsus(metapop)>0 && (get_total_ninf(metapop)+get_total_nexp(metapop))>0 && nstep<par->duration){
nstep++;
/* age metapopulation */
age_metapopulation(metapop, par);
/* process infections */
for(j=0;j<get_npop(metapop);j++){
process_infections(get_populations(metapop)[j], metapop, cn, par);
}
/* draw samples */
if((tabidx = int_in_vec(nstep, tabdates->items, tabdates->n)) > -1){ /* TRUE if step must be sampled */
samplist[counter_sample++] = draw_sample(metapop, tabdates->times[tabidx], par);
}
fill_ts_groupsizes(grpsizes, metapop, nstep);
}
/* we stopped after 'nstep' steps */
if(nstep < par->duration){
printf("\nEpidemics ended at time %d, before last sampling time (%d).\n", nstep, par->duration);
} else {
/* printf("\n\n-- FINAL METAPOPULATION --"); */
/* print_metapopulation(metapop, FALSE); */
/* merge samples */
samp = merge_samples(samplist, tabdates->n, par);
/* write sample to file */
printf("\n\nWriting sample to file 'out-sample.txt'\n");
write_sample(samp);
/* free memory */
free_sample(samp);
}
/* write group sizes to file */
printf("\n\nPrinting group sizes to file 'out-popsize.txt'\n");
write_ts_groupsizes(grpsizes);
/* free memory */
free_metapopulation(metapop);
free_param(par);
for(i=0;i<counter_sample;i++) free_sample(samplist[i]);
free(samplist);
free_table_int(tabdates);
free_network(cn);
free_ts_groupsizes(grpsizes);
}
/* all-in-one function testing epidemics growth, summary statistics, etc. */
void test_epidemics(int seqLength, double mutRate, int npop, int *nHostPerPop, double beta, int nStart, int t1, int t2, int Nsample, int *Tsample, int duration, int *nbnb, int *listnb, double *pdisp){
int i, j, nstep=0, tabidx, counter_sample = 0;
/* Initialize random number generator */
time_t t;
t = time(NULL); // time in seconds, used to change the seed of the random generator
gsl_rng * rng;
const gsl_rng_type *typ;
gsl_rng_env_setup();
typ=gsl_rng_default;
rng=gsl_rng_alloc(typ);
gsl_rng_set(rng,t); // changes the seed of the random generator
/* transfer simulation parameters */
struct param * par;
par = (struct param *) malloc(sizeof(struct param));
par->L = seqLength;
par->mu = mutRate;
par->muL = par->mu * par->L;
par->rng = rng;
par->npop = npop;
par->npop = npop;
par->popsizes = nHostPerPop;
par->beta = beta;
par->nstart = nStart;
par->t1 = t1;
par->t2 = t2;
par->t_sample = Tsample;
par->n_sample = Nsample;
par->duration = duration;
par->cn_nb_nb = nbnb;
par->cn_list_nb = listnb;
par->cn_weights = pdisp;
/* check/print parameters */
check_param(par);
print_param(par);
/* dispersal matrix */
struct network *cn = create_network(par);
/* group sizes */
struct ts_groupsizes * grpsizes = create_ts_groupsizes(par);
/* initiate population */
struct metapopulation * metapop;
metapop = create_metapopulation(par);
/* get sampling schemes (timestep+effectives) */
translate_dates(par);
struct table_int *tabdates = get_table_int(par->t_sample, par->n_sample);
printf("\n\nsampling at timesteps:");
print_table_int(tabdates);
/* create sample */
struct sample ** samplist = (struct sample **) malloc(tabdates->n * sizeof(struct sample *));
struct sample *samp;
/* MAKE METAPOPULATION EVOLVE */
nstep = 0;
while(get_total_nsus(metapop)>0 && (get_total_ninf(metapop)+get_total_nexp(metapop))>0 && nstep<par->duration){
nstep++;
/* age metapopulation */
age_metapopulation(metapop, par);
/* process infections */
for(j=0;j<get_npop(metapop);j++){
process_infections(get_populations(metapop)[j], metapop, cn, par);
}
/* draw samples */
if((tabidx = int_in_vec(nstep, tabdates->items, tabdates->n)) > -1){ /* TRUE if step must be sampled */
samplist[counter_sample++] = draw_sample(metapop, tabdates->times[tabidx], par);
}
fill_ts_groupsizes(grpsizes, metapop, nstep);
}
/* we stopped after 'nstep' steps */
if(nstep < par->duration){
printf("\nEpidemics ended at time %d, before last sampling time (%d).\n", nstep, par->duration);
} else {
printf("\n\n-- FINAL METAPOPULATION --");
print_metapopulation(metapop, TRUE);
/* test samples */
for(i=0;i<tabdates->n;i++) {
printf("\nsample %d\n", i);
print_sample(samplist[i], TRUE);
}
samp = merge_samples(samplist, tabdates->n, par) ;
print_sample(samp, TRUE);
/* test allele listing */
struct snplist *snpbilan;
snpbilan = list_snps(samp, par);
print_snplist(snpbilan);
/* test allele frequencies */
struct allfreq *freq;
freq = get_frequencies(samp, par);
print_allfreq(freq);
/* test Hs*/
double Hs = hs(samp,par);
printf("\nHs = %0.3f\n", Hs);
/* test Hs full genome */
Hs = hs_full_genome(samp,par);
printf("\nHs (full genome) = %0.5f\n", Hs);
/* test nb of snps */
int nball = nb_snps(samp,par);
printf("\nnumber of SNPs = %d\n", nball);
/* test mean nb of snps */
double temp = mean_nb_snps(samp);
printf("\nmean number of SNPs = %.2f\n", temp);
/* test var nb of snps */
temp = var_nb_snps(samp);
printf("\nvariance of number of alleles = %.2f\n", temp);
/* test pairwise distances */
struct distmat_int *mat = pairwise_dist(samp, par);
print_distmat_int(mat);
/* test mean pairwise distances */
temp = mean_pairwise_dist(samp,par);
printf("\nmean pairwise distance: %.2f", temp);
/* test variance of pairwise distances */
temp = var_pairwise_dist(samp,par);
printf("\nvar pairwise distance: %.2f", temp);
/* test Fst */
temp = fst(samp,par);
printf("\nfst: %.2f", temp);
printf("\n\n");
/* free memory */
free_sample(samp);
free_snplist(snpbilan);
free_allfreq(freq);
free_distmat_int(mat);
}
/* write group sizes to file */
printf("\n\nPrinting group sizes to file 'out-popsize.txt'");
write_ts_groupsizes(grpsizes);
/* free memory */
free_metapopulation(metapop);
free_param(par);
for(i=0;i<counter_sample;i++) free_sample(samplist[i]);
free(samplist);
free_table_int(tabdates);
free_network(cn);
free_ts_groupsizes(grpsizes);
}