deconvolutional_layer parse_deconvolutional(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
int size = option_find_int(options, "size",1);
int stride = option_find_int(options, "stride",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before deconvolutional layer must output image.");
deconvolutional_layer layer = make_deconvolutional_layer(batch,h,w,c,n,size,stride,activation);
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
parse_data(weights, layer.filters, c*n*size*size);
parse_data(biases, layer.biases, n);
#ifdef GPU
if(weights || biases) push_deconvolutional_layer(layer);
#endif
return layer;
}
convolutional_layer parse_convolutional(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
int size = option_find_int(options, "size",1);
int stride = option_find_int(options, "stride",1);
int pad = option_find_int(options, "pad",0);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before convolutional layer must output image.");
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
int binary = option_find_int_quiet(options, "binary", 0);
int xnor = option_find_int_quiet(options, "xnor", 0);
convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation, batch_normalize, binary, xnor);
layer.flipped = option_find_int_quiet(options, "flipped", 0);
layer.dot = option_find_float_quiet(options, "dot", 0);
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
parse_data(weights, layer.filters, c*n*size*size);
parse_data(biases, layer.biases, n);
#ifdef GPU
if(weights || biases) push_convolutional_layer(layer);
#endif
return layer;
}
void label_classifier(char *datacfg, char *filename, char *weightfile)
{
int i;
network *net = load_network(filename, weightfile, 0);
set_batch_network(net, 1);
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 validate_classifier_full(char *datacfg, char *filename, char *weightfile)
{
int i, j;
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, "labels", "data/labels.list");
char *valid_list = option_find_str(options, "valid", "data/train.list");
int classes = option_find_int(options, "classes", 2);
int topk = option_find_int(options, "top", 1);
char **labels = get_labels(label_list);
list *plist = get_paths(valid_list);
char **paths = (char **)list_to_array(plist);
int m = plist->size;
free_list(plist);
float avg_acc = 0;
float avg_topk = 0;
int *indexes = calloc(topk, sizeof(int));
int size = net.w;
for(i = 0; i < m; ++i){
int class = -1;
char *path = paths[i];
for(j = 0; j < classes; ++j){
if(strstr(path, labels[j])){
class = j;
break;
}
}
image im = load_image_color(paths[i], 0, 0);
image resized = resize_min(im, size);
resize_network(&net, resized.w, resized.h);
//show_image(im, "orig");
//show_image(crop, "cropped");
//cvWaitKey(0);
float *pred = network_predict(net, resized.data);
if(net.hierarchy) hierarchy_predictions(pred, net.outputs, net.hierarchy, 1, 1);
free_image(im);
free_image(resized);
top_k(pred, classes, topk, indexes);
if(indexes[0] == class) avg_acc += 1;
for(j = 0; j < topk; ++j){
if(indexes[j] == class) avg_topk += 1;
}
printf("%d: top 1: %f, top %d: %f\n", i, avg_acc/(i+1), topk, avg_topk/(i+1));
}
}
void predict_classifier(char *datacfg, char *cfgfile, char *weightfile, char *filename, int top)
{
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");
if(top == 0) 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;
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 = letterbox_image(im, net.w, net.h);
//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);
if(net.hierarchy) hierarchy_predictions(predictions, net.outputs, net.hierarchy, 1, 1);
top_k(predictions, net.outputs, top, indexes);
fprintf(stderr, "%s: Predicted in %f seconds.\n", input, sec(clock()-time));
for(i = 0; i < top; ++i){
int index = indexes[i];
//if(net.hierarchy) printf("%d, %s: %f, parent: %s \n",index, names[index], predictions[index], (net.hierarchy->parent[index] >= 0) ? names[net.hierarchy->parent[index]] : "Root");
//else printf("%s: %f\n",names[index], predictions[index]);
printf("%5.2f%%: %s\n", predictions[index]*100, names[index]);
}
if(r.data != im.data) free_image(r);
free_image(im);
if (filename) break;
}
}
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;
}
}
layer parse_region(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 4);
int classes = option_find_int(options, "classes", 20);
int num = option_find_int(options, "num", 1);
layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords);
assert(l.outputs == params.inputs);
l.log = option_find_int_quiet(options, "log", 0);
l.sqrt = option_find_int_quiet(options, "sqrt", 0);
l.softmax = option_find_int(options, "softmax", 0);
l.background = option_find_int_quiet(options, "background", 0);
l.max_boxes = option_find_int_quiet(options, "max",30);
l.jitter = option_find_float(options, "jitter", .2);
l.rescore = option_find_int_quiet(options, "rescore",0);
l.thresh = option_find_float(options, "thresh", .5);
l.classfix = option_find_int_quiet(options, "classfix", 0);
l.absolute = option_find_int_quiet(options, "absolute", 0);
l.random = option_find_int_quiet(options, "random", 0);
l.coord_scale = option_find_float(options, "coord_scale", 1);
l.object_scale = option_find_float(options, "object_scale", 1);
l.noobject_scale = option_find_float(options, "noobject_scale", 1);
l.mask_scale = option_find_float(options, "mask_scale", 1);
l.class_scale = option_find_float(options, "class_scale", 1);
l.bias_match = option_find_int_quiet(options, "bias_match",0);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) l.softmax_tree = read_tree(tree_file);
char *map_file = option_find_str(options, "map", 0);
if (map_file) l.map = read_map(map_file);
char *a = option_find_str(options, "anchors", 0);
if(a){
int len = strlen(a);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (a[i] == ',') ++n;
}
for(i = 0; i < n; ++i){
float bias = atof(a);
l.biases[i] = bias;
a = strchr(a, ',')+1;
}
}
return l;
}
convolutional_layer parse_convolutional(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
int size = option_find_int(options, "size",1);
int stride = option_find_int(options, "stride",1);
int pad = option_find_int_quiet(options, "pad",0);
int padding = option_find_int_quiet(options, "padding",0);
if(pad) padding = size/2;
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before convolutional layer must output image.");
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
int binary = option_find_int_quiet(options, "binary", 0);
int xnor = option_find_int_quiet(options, "xnor", 0);
convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,padding,activation, batch_normalize, binary, xnor, params.net.adam);
layer.flipped = option_find_int_quiet(options, "flipped", 0);
layer.dot = option_find_float_quiet(options, "dot", 0);
if(params.net.adam){
layer.B1 = params.net.B1;
layer.B2 = params.net.B2;
layer.eps = params.net.eps;
}
return layer;
}
cost_layer parse_cost(list *options, size_params params)
{
char *type_s = option_find_str(options, "type", "sse");
COST_TYPE type = get_cost_type(type_s);
cost_layer layer = make_cost_layer(params.batch, params.inputs, type);
return layer;
}
void parse_net_options(list *options, network *net)
{
net->batch = option_find_int(options, "batch",1);
net->learning_rate = option_find_float(options, "learning_rate", .001);
net->momentum = option_find_float(options, "momentum", .9);
net->decay = option_find_float(options, "decay", .0001);
int subdivs = option_find_int(options, "subdivisions",1);
net->time_steps = option_find_int_quiet(options, "time_steps",1);
net->batch /= subdivs;
net->batch *= net->time_steps;
net->subdivisions = subdivs;
net->h = option_find_int_quiet(options, "height",0);
net->w = option_find_int_quiet(options, "width",0);
net->c = option_find_int_quiet(options, "channels",0);
net->inputs = option_find_int_quiet(options, "inputs", net->h * net->w * net->c);
net->max_crop = option_find_int_quiet(options, "max_crop",net->w*2);
net->min_crop = option_find_int_quiet(options, "min_crop",net->w);
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
char *policy_s = option_find_str(options, "policy", "constant");
net->policy = get_policy(policy_s);
if(net->policy == STEP){
net->step = option_find_int(options, "step", 1);
net->scale = option_find_float(options, "scale", 1);
} else if (net->policy == STEPS){
char *l = option_find(options, "steps");
char *p = option_find(options, "scales");
if(!l || !p) error("STEPS policy must have steps and scales in cfg file");
int len = strlen(l);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (l[i] == ',') ++n;
}
int *steps = calloc(n, sizeof(int));
float *scales = calloc(n, sizeof(float));
for(i = 0; i < n; ++i){
int step = atoi(l);
float scale = atof(p);
l = strchr(l, ',')+1;
p = strchr(p, ',')+1;
steps[i] = step;
scales[i] = scale;
}
net->scales = scales;
net->steps = steps;
net->num_steps = n;
} else if (net->policy == EXP){
net->gamma = option_find_float(options, "gamma", 1);
} else if (net->policy == SIG){
net->gamma = option_find_float(options, "gamma", 1);
net->step = option_find_int(options, "step", 1);
} else if (net->policy == POLY || net->policy == RANDOM){
net->power = option_find_float(options, "power", 1);
}
net->max_batches = option_find_int(options, "max_batches", 0);
}
metadata get_metadata(char *file)
{
metadata m = {0};
list *options = read_data_cfg(file);
char *name_list = option_find_str(options, "names", 0);
if(!name_list) name_list = option_find_str(options, "labels", 0);
if(!name_list) {
fprintf(stderr, "No names or labels found\n");
} else {
m.names = get_labels(name_list);
}
m.classes = option_find_int(options, "classes", 2);
free_list(options);
return m;
}
void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filename, float thresh, float hier_thresh)
{
int show_flag = 1;
list *options = read_data_cfg(datacfg);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
image **alphabet = load_alphabet();
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
set_batch_network(&net, 1);
srand(2222222);
clock_t time;
char buff[256];
char *input = buff;
int j;
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);
layer l = net.layers[net.n-1];
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes + 1, sizeof(float *));
float *X = sized.data;
time=clock();
network_predict(net, X);
printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
get_region_boxes(l, 1, 1, thresh, probs, boxes, 0, 0, hier_thresh);
if (l.softmax_tree && nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
else if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, l.classes, nms);
draw_detections(im, l.w*l.h*l.n, thresh, boxes, probs, names, alphabet, l.classes, show_flag);
save_image(im, "predictions");
show_image(im, "predictions");
free_image(im);
free_image(sized);
free(boxes);
free_ptrs((void **)probs, l.w*l.h*l.n);
#ifdef OPENCV
cvWaitKey(0);
cvDestroyAllWindows();
#endif
if (filename) break;
}
}
connected_layer parse_connected(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
connected_layer layer = make_connected_layer(params.batch, params.inputs, output, activation);
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
parse_data(biases, layer.biases, output);
parse_data(weights, layer.weights, params.inputs*output);
#ifdef GPU
if(weights || biases) push_connected_layer(layer);
#endif
return layer;
}
cost_layer parse_cost(list *options, size_params params)
{
char *type_s = option_find_str(options, "type", "sse");
COST_TYPE type = get_cost_type(type_s);
float scale = option_find_float_quiet(options, "scale",1);
cost_layer layer = make_cost_layer(params.batch, params.inputs, type, scale);
layer.ratio = option_find_float_quiet(options, "ratio",0);
return layer;
}
softmax_layer parse_softmax(list *options, size_params params)
{
int groups = option_find_int_quiet(options, "groups",1);
softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
layer.temperature = option_find_float_quiet(options, "temperature", 1);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) layer.softmax_tree = read_tree(tree_file);
return layer;
}
layer parse_connected(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
layer l = make_connected_layer(params.batch, params.inputs, output, activation, batch_normalize, params.net->adam);
return l;
}
layer parse_activation(list *options, size_params params)
{
char *activation_s = option_find_str(options, "activation", "linear");
ACTIVATION activation = get_activation(activation_s);
layer l = make_activation_layer(params.batch, params.inputs, activation);
l.h = l.out_h = params.h;
l.w = l.out_w = params.w;
l.c = l.out_c = params.c;
return l;
}
void run_detector(int argc, char **argv)
{
char *prefix = find_char_arg(argc, argv, "-prefix", 0);
float thresh = find_float_arg(argc, argv, "-thresh", .24);
int cam_index = find_int_arg(argc, argv, "-c", 0);
int frame_skip = find_int_arg(argc, argv, "-s", 0);
if(argc < 4){
fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
return;
}
char *gpu_list = find_char_arg(argc, argv, "-gpus", 0);
int *gpus = 0;
int gpu = 0;
int ngpus = 0;
if(gpu_list){
printf("%s\n", gpu_list);
int len = strlen(gpu_list);
ngpus = 1;
int i;
for(i = 0; i < len; ++i){
if (gpu_list[i] == ',') ++ngpus;
}
gpus = calloc(ngpus, sizeof(int));
for(i = 0; i < ngpus; ++i){
gpus[i] = atoi(gpu_list);
gpu_list = strchr(gpu_list, ',')+1;
}
} else {
gpu = gpu_index;
gpus = &gpu;
ngpus = 1;
}
int clear = find_arg(argc, argv, "-clear");
char *datacfg = argv[3];
char *cfg = argv[4];
char *weights = (argc > 5) ? argv[5] : 0;
char *filename = (argc > 6) ? argv[6]: 0;
if(0==strcmp(argv[2], "test")) test_detector(datacfg, cfg, weights, filename, thresh);
else if(0==strcmp(argv[2], "train")) train_detector(datacfg, cfg, weights, gpus, ngpus, clear);
else if(0==strcmp(argv[2], "valid")) validate_detector(datacfg, cfg, weights);
else if(0==strcmp(argv[2], "recall")) validate_detector_recall(cfg, weights);
else if(0==strcmp(argv[2], "demo")) {
list *options = read_data_cfg(datacfg);
int classes = option_find_int(options, "classes", 20);
char *name_list = option_find_str(options, "names", "data/names.list");
char **names = get_labels(name_list);
demo(cfg, weights, thresh, cam_index, filename, names, classes, frame_skip, prefix);
}
}
layer parse_crnn(list *options, size_params params)
{
int output_filters = option_find_int(options, "output_filters",1);
int hidden_filters = option_find_int(options, "hidden_filters",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
layer l = make_crnn_layer(params.batch, params.w, params.h, params.c, hidden_filters, output_filters, params.time_steps, activation, batch_normalize);
l.shortcut = option_find_int_quiet(options, "shortcut", 0);
return l;
}
layer parse_softmax(list *options, size_params params)
{
int groups = option_find_int_quiet(options, "groups",1);
layer l = make_softmax_layer(params.batch, params.inputs, groups);
l.temperature = option_find_float_quiet(options, "temperature", 1);
char *tree_file = option_find_str(options, "tree", 0);
if (tree_file) l.softmax_tree = read_tree(tree_file);
l.w = params.w;
l.h = params.h;
l.c = params.c;
l.spatial = option_find_float_quiet(options, "spatial", 0);
l.noloss = option_find_int_quiet(options, "noloss", 0);
return l;
}
layer parse_yolo(list *options, size_params params)
{
int classes = option_find_int(options, "classes", 20);
int total = option_find_int(options, "num", 1);
int num = total;
char *a = option_find_str(options, "mask", 0);
int *mask = parse_yolo_mask(a, &num);
layer l = make_yolo_layer(params.batch, params.w, params.h, num, total, mask, classes);
assert(l.outputs == params.inputs);
l.max_boxes = option_find_int_quiet(options, "max",90);
l.jitter = option_find_float(options, "jitter", .2);
l.ignore_thresh = option_find_float(options, "ignore_thresh", .5);
l.truth_thresh = option_find_float(options, "truth_thresh", 1);
l.random = option_find_int_quiet(options, "random", 0);
char *map_file = option_find_str(options, "map", 0);
if (map_file) l.map = read_map(map_file);
a = option_find_str(options, "anchors", 0);
if(a){
int len = strlen(a);
int n = 1;
int i;
for(i = 0; i < len; ++i){
if (a[i] == ',') ++n;
}
for(i = 0; i < n; ++i){
float bias = atof(a);
l.biases[i] = bias;
a = strchr(a, ',')+1;
}
}
return l;
}
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
}
layer parse_shortcut(list *options, size_params params, network net)
{
char *l = option_find(options, "from");
int index = atoi(l);
if(index < 0) index = params.index + index;
int batch = params.batch;
layer from = net.layers[index];
layer s = make_shortcut_layer(batch, index, params.w, params.h, params.c, from.out_w, from.out_h, from.out_c);
char *activation_s = option_find_str(options, "activation", "linear");
ACTIVATION activation = get_activation(activation_s);
s.activation = activation;
return s;
}
local_layer parse_local(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
int size = option_find_int(options, "size",1);
int stride = option_find_int(options, "stride",1);
int pad = option_find_int(options, "pad",0);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before local layer must output image.");
local_layer layer = make_local_layer(batch,h,w,c,n,size,stride,pad,activation);
return layer;
}
layer parse_deconvolutional(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
int size = option_find_int(options, "size",1);
int stride = option_find_int(options, "stride",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
int batch,h,w,c;
h = params.h;
w = params.w;
c = params.c;
batch=params.batch;
if(!(h && w && c)) error("Layer before deconvolutional layer must output image.");
int batch_normalize = option_find_int_quiet(options, "batch_normalize", 0);
int pad = option_find_int_quiet(options, "pad",0);
int padding = option_find_int_quiet(options, "padding",0);
if(pad) padding = size/2;
layer l = make_deconvolutional_layer(batch,h,w,c,n,size,stride,padding, activation, batch_normalize, params.net->adam);
return l;
}
void validate_yolo(char *datacfg, char *cfgfile, char *weightfile)
{
list *options = read_data_cfg(datacfg);
//char *train_list = option_find_str(options, "train", "data/train_list.txt");
//char *test_list = option_find_str(options, "test", "data/test_list.txt");
char *valid_list = option_find_str(options, "valid", "data/valid_list.txt");
//char *backup_directory = option_find_str(options, "backup", "/backup/");
//char *label_list = option_find_str(options, "labels", "data/labels_list.txt");
//int classes = option_find_int(options, "classes", 2);
//char **labels = get_labels(label_list);
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(valid_list);
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 = 2;
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_yolo_detections(predictions, classes, l.n, square, side, w, h, thresh, probs, boxes, 0);
if (nms) do_nms_sort(boxes, probs, side*side*l.n, classes, iou_thresh);
print_yolo_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_detector(char *datacfg, char *cfgfile, char *weightfile, char *outfile)
{
int j;
list *options = read_data_cfg(datacfg);
char *valid_images = option_find_str(options, "valid", "data/train.list");
char *name_list = option_find_str(options, "names", "data/names.list");
char *prefix = option_find_str(options, "results", "results");
char **names = get_labels(name_list);
char *mapf = option_find_str(options, "map", 0);
int *map = 0;
if (mapf) map = read_map(mapf);
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));
list *plist = get_paths(valid_images);
char **paths = (char **)list_to_array(plist);
layer l = net.layers[net.n-1];
int classes = l.classes;
char buff[1024];
char *type = option_find_str(options, "eval", "voc");
FILE *fp = 0;
FILE **fps = 0;
int coco = 0;
int imagenet = 0;
if(0==strcmp(type, "coco")){
if(!outfile) outfile = "coco_results";
snprintf(buff, 1024, "%s/%s.json", prefix, outfile);
fp = fopen(buff, "w");
fprintf(fp, "[\n");
coco = 1;
} else if(0==strcmp(type, "imagenet")){
if(!outfile) outfile = "imagenet-detection";
snprintf(buff, 1024, "%s/%s.txt", prefix, outfile);
fp = fopen(buff, "w");
imagenet = 1;
classes = 200;
} else {
if(!outfile) outfile = "comp4_det_test_";
fps = calloc(classes, sizeof(FILE *));
for(j = 0; j < classes; ++j){
snprintf(buff, 1024, "%s/%s%s.txt", prefix, outfile, names[j]);
fps[j] = fopen(buff, "w");
}
}
box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
for(j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(classes, sizeof(float *));
int m = plist->size;
int i=0;
int t;
float thresh = .005;
float nms = .45;
int nthreads = 4;
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;
get_region_boxes(l, w, h, thresh, probs, boxes, 0, map, .5);
if (nms) do_nms_sort(boxes, probs, l.w*l.h*l.n, classes, nms);
if (coco){
print_cocos(fp, path, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else if (imagenet){
print_imagenet_detections(fp, i+t-nthreads+1, boxes, probs, l.w*l.h*l.n, classes, w, h);
} else {
print_detector_detections(fps, id, boxes, probs, l.w*l.h*l.n, classes, w, h);
}
free(id);
free_image(val[t]);
free_image(val_resized[t]);
}
}
for(j = 0; j < classes; ++j){
if(fps) fclose(fps[j]);
}
if(coco){
fseek(fp, -2, SEEK_CUR);
fprintf(fp, "\n]\n");
fclose(fp);
}
fprintf(stderr, "Total Detection Time: %f Seconds\n", (double)(time(0) - start));
}
void train_detector(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
{
list *options = read_data_cfg(datacfg);
char *train_images = option_find_str(options, "train", "data/train.list");
char *backup_directory = option_find_str(options, "backup", "/backup/");
srand(time(0));
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
network *nets = calloc(ngpus, sizeof(network));
srand(time(0));
int seed = rand();
int i;
for(i = 0; i < ngpus; ++i){
srand(seed);
#ifdef GPU
cuda_set_device(gpus[i]);
#endif
nets[i] = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&nets[i], weightfile);
}
if(clear) *nets[i].seen = 0;
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);
data train, buffer;
layer l = net.layers[net.n - 1];
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 = l.max_boxes;
args.d = &buffer;
args.type = DETECTION_DATA;
args.threads = 8;
args.angle = net.angle;
args.exposure = net.exposure;
args.saturation = net.saturation;
args.hue = net.hue;
pthread_t load_thread = load_data(args);
clock_t time;
int count = 0;
//while(i*imgs < N*120){
while(get_current_batch(net) < net.max_batches){
if(l.random && count++%10 == 0){
printf("Resizing\n");
//int dim = (rand() % 10 + 10) * 32;
//if (get_current_batch(net)+200 > net.max_batches) dim = 608;
//int dim = (rand() % 4 + 16) * 32;
int dim = (args.w <= args.h ? args.w : args.h);
printf("%d\n", dim);
args.w = dim;
args.h = dim;
pthread_join(load_thread, 0);
train = buffer;
free_data(train);
load_thread = load_data(args);
for(i = 0; i < ngpus; ++i){
resize_network(nets + i, dim, dim);
}
net = nets[0];
}
time=clock();
pthread_join(load_thread, 0);
train = buffer;
load_thread = load_data(args);
/*
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[10] + 1 + k*5);
if(!b.x) break;
printf("loaded: %f %f %f %f\n", b.x, b.y, b.w, b.h);
}
image im = float_to_image(448, 448, 3, train.X.vals[10]);
int k;
for(k = 0; k < l.max_boxes; ++k){
box b = float_to_box(train.y.vals[10] + 1 + k*5);
printf("%d %d %d %d\n", truth.x, truth.y, truth.w, truth.h);
draw_bbox(im, b, 8, 1,0,0);
}
save_image(im, "truth11");
*/
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 < 0) avg_loss = loss;
avg_loss = avg_loss*.9 + loss*.1;
i = get_current_batch(net);
printf("%d: %f, %f avg, %f rate, %lf seconds, %d images\n", get_current_batch(net), loss, avg_loss, get_current_rate(net), sec(clock()-time), i*imgs);
if(i%1000==0 || (i < 1000 && i%100 == 0)){
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
save_weights(net, buff);
}
free_data(train);
}
#ifdef GPU
if(ngpus != 1) sync_nets(nets, ngpus, 0);
#endif
char buff[256];
sprintf(buff, "%s/%s_final.weights", backup_directory, base);
save_weights(net, buff);
}
void train_yolo(char *datacfg, char *cfgfile, char *weightfile)
{
list *options = read_data_cfg(datacfg);
char *train_list = option_find_str(options, "train", "data/train_list.txt");
//char *test_list = option_find_str(options, "test", "data/test_list.txt");
//char *valid_list = option_find_str(options, "valid", "data/valid_list.txt");
char *backup_directory = option_find_str(options, "backup", "/backup/");
//char *label_list = option_find_str(options, "labels", "data/labels_list.txt");
//int classes = option_find_int(options, "classes", 2);
srand(time(0));
data_seed = time(0);
char *base = basecfg(cfgfile);
printf("%s\n", base);
float avg_loss = -1;
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 = 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_list);
//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;
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_%06d.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);
}
void validate_yolo_classify(char *datacfg, char *cfgfile, char *weightfile)
{
list *options = read_data_cfg(datacfg);
//char *train_list = option_find_str(options, "train", "data/train_list.txt");
//char *test_list = option_find_str(options, "test", "data/test_list.txt");
char *valid_list = option_find_str(options, "valid", "data/valid_list.txt");
//char *backup_directory = option_find_str(options, "backup", "/backup/");
//char *label_list = option_find_str(options, "labels", "data/labels_list.txt");
//int classes = option_find_int(options, "classes", 2);
//char **labels = get_labels(label_list);
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("data/voc.2007.test");
list *plist = get_paths(valid_list);
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;
float thresh = .2;
float iou_thresh = .5;
//float nms = 0;
float nms = 0.5;
int total = 0;
int correct = 0;
int class_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);
convert_yolo_detections(predictions, classes, l.n, square, side, 1, 1, thresh, probs, boxes, 0);
//if (nms) do_nms(boxes, probs, side*side*l.n, 1, nms);
if (nms) do_nms(boxes, probs, side*side*l.n, classes, nms);
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");
labelpath = find_replace(labelpath, ".bmp", ".txt");
labelpath = find_replace(labelpath, ".dib", ".txt");
labelpath = find_replace(labelpath, ".jpe", ".txt");
labelpath = find_replace(labelpath, ".jp2", ".txt");
labelpath = find_replace(labelpath, ".png", ".txt");
labelpath = find_replace(labelpath, ".pbm", ".txt");
labelpath = find_replace(labelpath, ".pgm", ".txt");
labelpath = find_replace(labelpath, ".ppm", ".txt");
labelpath = find_replace(labelpath, ".sr", ".txt");
labelpath = find_replace(labelpath, ".ras", ".txt");
labelpath = find_replace(labelpath, ".tiff", ".txt");
labelpath = find_replace(labelpath, ".tif", ".txt");
int num_labels = 0;
box_label *truth = read_boxes(labelpath, &num_labels);
for(k = 0; k < side*side*l.n; ++k){
int class = max_index(probs[k], classes);
float prob = probs[k][class];
//fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class);
if(prob > 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;
int pre_class = -1;
for(k = 0; k < side*side*l.n; ++k){
float iou = box_iou(boxes[k], t);
int class = max_index(probs[k], classes);
float prob = probs[k][class];
//fprintf(stderr, "path=%s\t\tk=%d\tprob=%f\tclass=%d\n", path, k, prob, class);
if(prob > thresh && iou > best_iou){
best_iou = iou;
pre_class = class;
}
}
avg_iou += best_iou;
if(best_iou > iou_thresh){
++correct;
}
if(pre_class == truth[j].id){
++class_correct;
}
//fprintf(stderr, "true_class=%d\tpre_class=%d\n", truth[j].id, pre_class);
}
fprintf(stderr, "%5d %5d %5d\tRPs/Img: %.2f\tIOU: %.2f%%\tRecall:%.2f%%\t\tClassify:%.2f%%\n", i, correct, total, (float)proposals/(i+1), avg_iou*100/total, 100.*correct/total, 100.*class_correct/total);
free(id);
free_image(orig);
free_image(sized);
}
