1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
| #include "network.h"
| #include "detection_layer.h"
| #include "utils.h"
| #include "parser.h"
|
|
| char *class_names[] = {"aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"};
| char *inet_class_names[] = {"bg", "accordion", "airplane", "ant", "antelope", "apple", "armadillo", "artichoke", "axe", "baby bed", "backpack", "bagel", "balance beam", "banana", "band aid", "banjo", "baseball", "basketball", "bathing cap", "beaker", "bear", "bee", "bell pepper", "bench", "bicycle", "binder", "bird", "bookshelf", "bow tie", "bow", "bowl", "brassiere", "burrito", "bus", "butterfly", "camel", "can opener", "car", "cart", "cattle", "cello", "centipede", "chain saw", "chair", "chime", "cocktail shaker", "coffee maker", "computer keyboard", "computer mouse", "corkscrew", "cream", "croquet ball", "crutch", "cucumber", "cup or mug", "diaper", "digital clock", "dishwasher", "dog", "domestic cat", "dragonfly", "drum", "dumbbell", "electric fan", "elephant", "face powder", "fig", "filing cabinet", "flower pot", "flute", "fox", "french horn", "frog", "frying pan", "giant panda", "goldfish", "golf ball", "golfcart", "guacamole", "guitar", "hair dryer", "hair spray", "hamburger", "hammer", "hamster", "harmonica", "harp", "hat with a wide brim", "head cabbage", "helmet", "hippopotamus", "horizontal bar", "horse", "hotdog", "iPod", "isopod", "jellyfish", "koala bear", "ladle", "ladybug", "lamp", "laptop", "lemon", "lion", "lipstick", "lizard", "lobster", "maillot", "maraca", "microphone", "microwave", "milk can", "miniskirt", "monkey", "motorcycle", "mushroom", "nail", "neck brace", "oboe", "orange", "otter", "pencil box", "pencil sharpener", "perfume", "person", "piano", "pineapple", "ping-pong ball", "pitcher", "pizza", "plastic bag", "plate rack", "pomegranate", "popsicle", "porcupine", "power drill", "pretzel", "printer", "puck", "punching bag", "purse", "rabbit", "racket", "ray", "red panda", "refrigerator", "remote control", "rubber eraser", "rugby ball", "ruler", "salt or pepper shaker", "saxophone", "scorpion", "screwdriver", "seal", "sheep", "ski", "skunk", "snail", "snake", "snowmobile", "snowplow", "soap dispenser", "soccer ball", "sofa", "spatula", "squirrel", "starfish", "stethoscope", "stove", "strainer", "strawberry", "stretcher", "sunglasses", "swimming trunks", "swine", "syringe", "table", "tape player", "tennis ball", "tick", "tie", "tiger", "toaster", "traffic light", "train", "trombone", "trumpet", "turtle", "tv or monitor", "unicycle", "vacuum", "violin", "volleyball", "waffle iron", "washer", "water bottle", "watercraft", "whale", "wine bottle", "zebra"};
| #define AMNT 3
| void draw_detection(image im, float *box, int side)
| {
| int classes = 20;
| int elems = 4+classes;
| int j;
| int r, c;
|
| for(r = 0; r < side; ++r){
| for(c = 0; c < side; ++c){
| j = (r*side + c) * elems;
| //printf("%d\n", j);
| //printf("Prob: %f\n", box[j]);
| int class = max_index(box+j, classes);
| if(box[j+class] > .2){
| //int z;
| //for(z = 0; z < classes; ++z) printf("%f %s\n", box[j+z], class_names[z]);
| printf("%f %s\n", box[j+class], class_names[class]);
| float red = get_color(0,class,classes);
| float green = get_color(1,class,classes);
| float blue = get_color(2,class,classes);
|
| //float maxheight = distance_from_edge(r, side);
| //float maxwidth = distance_from_edge(c, side);
| j += classes;
| float y = box[j+0];
| float x = box[j+1];
| x = (x+c)/side;
| y = (y+r)/side;
| float h = box[j+2]; //*maxheight;
| float w = box[j+3]; //*maxwidth;
| h = h*h;
| w = w*w;
| //printf("coords %f %f %f %f\n", x, y, w, h);
|
| int left = (x-w/2)*im.w;
| int right = (x+w/2)*im.w;
| int top = (y-h/2)*im.h;
| int bot = (y+h/2)*im.h;
| draw_box(im, left, top, right, bot, red, green, blue);
| }
| }
| }
| //printf("Done\n");
| show_image(im, "box");
| cvWaitKey(0);
| }
|
| void train_detection(char *cfgfile, char *weightfile)
| {
| srand(time(0));
| data_seed = time(0);
| int imgnet = 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);
| }
| detection_layer *layer = get_network_detection_layer(net);
| printf("Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
| int imgs = 128;
| int i = net.seen/imgs;
| data train, buffer;
|
| int classes = layer->classes;
| int background = layer->background;
| int side = sqrt(get_detection_layer_locations(*layer));
|
| char **paths;
| list *plist;
| if (imgnet){
| plist = get_paths("/home/pjreddie/data/imagenet/det.train.list");
| }else{
| plist = get_paths("/home/pjreddie/data/voc/trainall.txt");
| }
| paths = (char **)list_to_array(plist);
| pthread_t load_thread = load_data_detection_thread(imgs, paths, plist->size, classes, net.w, net.h, side, side, background, &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, classes, net.w, net.h, side, side, background, &buffer);
|
| /*
| image im = float_to_image(net.w, net.h, 3, train.X.vals[114]);
| image copy = copy_image(im);
| translate_image(copy, 1);
| scale_image(copy, .5);
| draw_detection(copy, train.y.vals[114], 7);
| free_image(copy);
| */
|
| printf("Loaded: %lf seconds\n", sec(clock()-time));
| time=clock();
| float loss = train_network(net, train);
| net.seen += imgs;
| if (avg_loss < 0) avg_loss = loss;
| avg_loss = avg_loss*.9 + loss*.1;
| printf("%d: %f, %f avg, %lf seconds, %d images\n", i, loss, avg_loss, sec(clock()-time), i*imgs);
| if(i%100==0){
| char buff[256];
| sprintf(buff, "/home/pjreddie/imagenet_backup/%s_%d.weights",base, i);
| save_weights(net, buff);
| }
| free_data(train);
| }
| }
|
| void validate_detection(char *cfgfile, char *weightfile)
| {
| network net = parse_network_cfg(cfgfile);
| if(weightfile){
| load_weights(&net, weightfile);
| }
| detection_layer *layer = get_network_detection_layer(net);
| fprintf(stderr, "Learning Rate: %g, Momentum: %g, Decay: %g\n", net.learning_rate, net.momentum, net.decay);
| srand(time(0));
|
| list *plist = get_paths("/home/pjreddie/data/voc/val.txt");
| //list *plist = get_paths("/home/pjreddie/data/voc/val.expanded.txt");
| //list *plist = get_paths("/home/pjreddie/data/voc/train.txt");
| char **paths = (char **)list_to_array(plist);
|
| int classes = layer->classes;
| int nuisance = layer->nuisance;
| int background = (layer->background && !nuisance);
| int num_boxes = sqrt(get_detection_layer_locations(*layer));
|
| int per_box = 4+classes+background+nuisance;
| int num_output = num_boxes*num_boxes*per_box;
|
| int m = plist->size;
| int i = 0;
| int splits = 100;
| int num = (i+1)*m/splits - i*m/splits;
|
| fprintf(stderr, "%d\n", m);
| data val, buffer;
| pthread_t load_thread = load_data_thread(paths, num, 0, 0, num_output, net.w, net.h, &buffer);
| clock_t time;
| for(i = 1; i <= splits; ++i){
| time=clock();
| pthread_join(load_thread, 0);
| val = buffer;
|
| num = (i+1)*m/splits - i*m/splits;
| char **part = paths+(i*m/splits);
| if(i != splits) load_thread = load_data_thread(part, num, 0, 0, num_output, net.w, net.h, &buffer);
|
| fprintf(stderr, "%d: Loaded: %lf seconds\n", i, sec(clock()-time));
| matrix pred = network_predict_data(net, val);
| int j, k, class;
| for(j = 0; j < pred.rows; ++j){
| for(k = 0; k < pred.cols; k += per_box){
| float scale = 1.;
| int index = k/per_box;
| int row = index / num_boxes;
| int col = index % num_boxes;
| if (nuisance) scale = 1.-pred.vals[j][k];
| for (class = 0; class < classes; ++class){
| int ci = k+classes+background+nuisance;
| float y = (pred.vals[j][ci + 0] + row)/num_boxes;
| float x = (pred.vals[j][ci + 1] + col)/num_boxes;
| float h = pred.vals[j][ci + 2]; //* distance_from_edge(row, num_boxes);
| h = h*h;
| float w = pred.vals[j][ci + 3]; //* distance_from_edge(col, num_boxes);
| w = w*w;
| float prob = scale*pred.vals[j][k+class+background+nuisance];
| if(prob < .001) continue;
| printf("%d %d %f %f %f %f %f\n", (i-1)*m/splits + j, class, prob, y, x, h, w);
| }
| }
| }
| time=clock();
| free_data(val);
| }
| }
|
| void test_detection(char *cfgfile, char *weightfile)
| {
| network net = parse_network_cfg(cfgfile);
| if(weightfile){
| load_weights(&net, weightfile);
| }
| int im_size = 448;
| set_batch_network(&net, 1);
| srand(2222222);
| clock_t time;
| char filename[256];
| while(1){
| fgets(filename, 256, stdin);
| strtok(filename, "\n");
| image im = load_image_color(filename, im_size, im_size);
| printf("%d %d %d\n", im.h, im.w, im.c);
| float *X = im.data;
| time=clock();
| float *predictions = network_predict(net, X);
| printf("%s: Predicted in %f seconds.\n", filename, sec(clock()-time));
| draw_detection(im, predictions, 7);
| free_image(im);
| }
| }
|
| void run_detection(int argc, char **argv)
| {
| if(argc < 4){
| fprintf(stderr, "usage: %s %s [train/test/valid] [cfg] [weights (optional)]\n", argv[0], argv[1]);
| return;
| }
|
| char *cfg = argv[3];
| char *weights = (argc > 4) ? argv[4] : 0;
| if(0==strcmp(argv[2], "test")) test_detection(cfg, weights);
| else if(0==strcmp(argv[2], "train")) train_detection(cfg, weights);
| else if(0==strcmp(argv[2], "valid")) validate_detection(cfg, weights);
| }
|
|
