merged

examples/attention.c

@@ -3,16 +3,64 @@
 #include <sys/time.h>
 #include <assert.h>
 
-void train_attention(char *datacfg, char *cfgfile, char *weightfile, char *cfgfile2, char *weightfile2, int *gpus, int ngpus, int clear)
+void extend_data_truth(data *d, int n, float val)
 {
-    int i;
+    int i, j;
+    for(i = 0; i < d->y.rows; ++i){
+        d->y.vals[i] = realloc(d->y.vals[i], (d->y.cols+n)*sizeof(float));
+        for(j = 0; j < n; ++j){
+            d->y.vals[i][d->y.cols + j] = val;
+        }
+    }
+    d->y.cols += n;
+}
 
-    float avg_loss = -1;
+matrix network_loss_data(network *net, data test)
+{
+    int i,b;
+    int k = 1;
+    matrix pred = make_matrix(test.X.rows, k);
+    float *X = calloc(net->batch*test.X.cols, sizeof(float));
+    float *y = calloc(net->batch*test.y.cols, sizeof(float));
+    for(i = 0; i < test.X.rows; i += net->batch){
+        for(b = 0; b < net->batch; ++b){
+            if(i+b == test.X.rows) break;
+            memcpy(X+b*test.X.cols, test.X.vals[i+b], test.X.cols*sizeof(float));
+            memcpy(y+b*test.y.cols, test.y.vals[i+b], test.y.cols*sizeof(float));
+        }
+
+        network orig = *net;
+        net->input = X;
+        net->truth = y;
+        net->train = 0;
+        net->delta = 0;
+        forward_network(net);
+        *net = orig;
+
+        float *delta = net->layers[net->n-1].output;
+        for(b = 0; b < net->batch; ++b){
+            if(i+b == test.X.rows) break;
+            int t = max_index(y + b*test.y.cols, 1000);
+            float err = sum_array(delta + b*net->outputs, net->outputs);
+            pred.vals[i+b][0] = -err;
+            //pred.vals[i+b][0] = 1-delta[b*net->outputs + t];
+        }
+    }
+    free(X);
+    free(y);
+    return pred;   
+}
+
+void train_attention(char *datacfg, char *cfgfile, char *weightfile, int *gpus, int ngpus, int clear)
+{
+    int i, j;
+
+    float avg_cls_loss = -1;
+    float avg_att_loss = -1;
     char *base = basecfg(cfgfile);
     printf("%s\n", base);
     printf("%d\n", ngpus);
-    network **attnets = calloc(ngpus, sizeof(network*));
+    network **nets = calloc(ngpus, sizeof(network*));
-    network **clsnets = calloc(ngpus, sizeof(network*));
 
     srand(time(0));
     int seed = rand();
@@ -21,14 +69,11 @@ void train_attention(char *datacfg, char *cfgfile, char *weightfile, char *cfgfi
 #ifdef GPU
         cuda_set_device(gpus[i]);
 #endif
-        attnets[i] = load_network(cfgfile, weightfile, clear);
+        nets[i] = load_network(cfgfile, weightfile, clear);
-        attnets[i]->learning_rate *= ngpus;
+        nets[i]->learning_rate *= ngpus;
-        clsnets[i] = load_network(cfgfile2, weightfile2, clear);
-        clsnets[i]->learning_rate *= ngpus;
     }
     srand(time(0));
-    network *net = attnets[0];
+    network *net = nets[0];
-    //network *clsnet = clsnets[0];
 
     int imgs = net->batch * net->subdivisions * ngpus;
 
@@ -47,15 +92,18 @@ void train_attention(char *datacfg, char *cfgfile, char *weightfile, char *cfgfi
     int N = plist->size;
     double time;
 
+    int divs=3;
+    int size=2;
+
     load_args args = {0};
-    args.w = 4*net->w;
+    args.w = divs*net->w/size;
-    args.h = 4*net->h;
+    args.h = divs*net->h/size;
-    args.size = 4*net->w;
+    args.size = divs*net->w/size;
     args.threads = 32;
     args.hierarchy = net->hierarchy;
 
-    args.min = net->min_ratio*net->w;
+    args.min = net->min_ratio*args.w;
-    args.max = net->max_ratio*net->w;
+    args.max = net->max_ratio*args.w;
     args.angle = net->angle;
     args.aspect = net->aspect;
     args.exposure = net->exposure;
@@ -83,25 +131,81 @@ void train_attention(char *datacfg, char *cfgfile, char *weightfile, char *cfgfi
         train = buffer;
         load_thread = load_data(args);
         data resized = resize_data(train, net->w, net->h);
+        extend_data_truth(&resized, divs*divs, 0);
+        data *tiles = tile_data(train, divs, size);
 
         printf("Loaded: %lf seconds\n", what_time_is_it_now()-time);
         time = what_time_is_it_now();
 
-        float loss = 0;
+        float aloss = 0;
+        float closs = 0;
+        int z;
+        for (i = 0; i < divs*divs/ngpus; ++i) {
+#pragma omp parallel for
+            for(j = 0; j < ngpus; ++j){
+                int index = i*ngpus + j;
+                extend_data_truth(tiles+index, divs*divs, SECRET_NUM);
+                matrix deltas = network_loss_data(nets[j], tiles[index]);
+                for(z = 0; z < resized.y.rows; ++z){
+                    resized.y.vals[z][train.y.cols + index] = deltas.vals[z][0];
+                }
+                free_matrix(deltas);
+            }
+        }
+        int *inds = calloc(resized.y.rows, sizeof(int));
+        for(z = 0; z < resized.y.rows; ++z){
+            int index = max_index(resized.y.vals[z] + train.y.cols, divs*divs);
+            inds[z] = index;
+            for(i = 0; i < divs*divs; ++i){
+                resized.y.vals[z][train.y.cols + i] = (i == index)? 1 : 0;
+            }
+        }
+        data best = select_data(tiles, inds);
+        free(inds);
         #ifdef GPU
         if (ngpus == 1) {
-            loss = train_network(net, train);
+            closs = train_network(net, best);
         } else {
-            loss = train_networks(attnets, ngpus, train, 4);
+            closs = train_networks(nets, ngpus, best, 4);
         }
-#else
-        loss = train_network(net, train);
         #endif
+        for (i = 0; i < divs*divs; ++i) {
+            printf("%.2f ", resized.y.vals[0][train.y.cols + i]);
+            if((i+1)%divs == 0) printf("\n");
+            free_data(tiles[i]);
+        }
+        free_data(best);
+        printf("\n");
+        image im = float_to_image(64,64,3,resized.X.vals[0]);
+        //show_image(im, "orig");
+        //cvWaitKey(100);
+        /*
+           image im1 = float_to_image(64,64,3,tiles[i].X.vals[0]);
+           image im2 = float_to_image(64,64,3,resized.X.vals[0]);
+           show_image(im1, "tile");
+           show_image(im2, "res");
+         */
+#ifdef GPU
+        if (ngpus == 1) {
+            aloss = train_network(net, resized);
+        } else {
+            aloss = train_networks(nets, ngpus, resized, 4);
+        }
+#endif
+        for(i = 0; i < divs*divs; ++i){
+            printf("%f ", nets[0]->output[1000 + i]);
+            if ((i+1) % divs == 0) printf("\n");
+        }
+        printf("\n");
+
         free_data(resized);
-        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), what_time_is_it_now()-time, *net->seen);
         free_data(train);
+        if(avg_cls_loss == -1) avg_cls_loss = closs;
+        if(avg_att_loss == -1) avg_att_loss = aloss;
+        avg_cls_loss = avg_cls_loss*.9 + closs*.1;
+        avg_att_loss = avg_att_loss*.9 + aloss*.1;
+
+        printf("%ld, %.3f: Att: %f, %f avg, Class: %f, %f avg, %f rate, %lf seconds, %ld images\n", get_current_batch(net), (float)(*net->seen)/N, aloss, avg_att_loss, closs, avg_cls_loss, get_current_rate(net), what_time_is_it_now()-time, *net->seen);
         if(*net->seen/N > epoch){
             epoch = *net->seen/N;
             char buff[256];
@@ -152,6 +256,11 @@ void validate_attention_single(char *datacfg, char *filename, char *weightfile)
     float avg_acc = 0;
     float avg_topk = 0;
     int *indexes = calloc(topk, sizeof(int));
+    int divs = 4;
+    int size = 2;
+    int extra = 0;
+    float *avgs = calloc(classes, sizeof(float));
+    int *inds = calloc(divs*divs, sizeof(int));
 
     for(i = 0; i < m; ++i){
         int class = -1;
@@ -163,14 +272,38 @@ void validate_attention_single(char *datacfg, char *filename, char *weightfile)
             }
         }
         image im = load_image_color(paths[i], 0, 0);
-        image resized = resize_min(im, net->w);
+        image resized = resize_min(im, net->w*divs/size);
-        image crop = crop_image(resized, (resized.w - net->w)/2, (resized.h - net->h)/2, net->w, net->h);
+        image crop = crop_image(resized, (resized.w - net->w*divs/size)/2, (resized.h - net->h*divs/size)/2, net->w*divs/size, net->h*divs/size);
+        image rcrop = resize_image(crop, net->w, net->h);
         //show_image(im, "orig");
         //show_image(crop, "cropped");
         //cvWaitKey(0);
-        float *pred = network_predict(net, crop.data);
+        float *pred = network_predict(net, rcrop.data);
+        //pred[classes + 56] = 0;
+        for(j = 0; j < divs*divs; ++j){
+            printf("%.2f ", pred[classes + j]);
+            if((j+1)%divs == 0) printf("\n");
+        }
+        printf("\n");
+        copy_cpu(classes, pred, 1, avgs, 1);
+        top_k(pred + classes, divs*divs, divs*divs, inds);
+        show_image(crop, "crop");
+        for(j = 0; j < extra; ++j){
+            int index = inds[j];
+            int row = index / divs;
+            int col = index % divs;
+            int y = row * crop.h / divs - (net->h - crop.h/divs)/2;
+            int x = col * crop.w / divs - (net->w - crop.w/divs)/2;
+            printf("%d %d %d %d\n", row, col, y, x);
+            image tile = crop_image(crop, x, y, net->w, net->h);
+            float *pred = network_predict(net, tile.data);
+            axpy_cpu(classes, 1., pred, 1, avgs, 1);
+            show_image(tile, "tile");
+            //cvWaitKey(10);
+        }
         if(net->hierarchy) hierarchy_predictions(pred, net->outputs, net->hierarchy, 1, 1);
 
+        if(rcrop.data != resized.data) free_image(rcrop);
         if(resized.data != im.data) free_image(resized);
         free_image(im);
         free_image(crop);
@@ -318,7 +451,7 @@ void run_attention(int argc, char **argv)
     char *filename = (argc > 6) ? argv[6]: 0;
     char *layer_s = (argc > 7) ? argv[7]: 0;
     if(0==strcmp(argv[2], "predict")) predict_attention(data, cfg, weights, filename, top);
-    else if(0==strcmp(argv[2], "train")) train_attention(data, cfg, weights, filename, layer_s, gpus, ngpus, clear);
+    else if(0==strcmp(argv[2], "train")) train_attention(data, cfg, weights, gpus, ngpus, clear);
     else if(0==strcmp(argv[2], "valid")) validate_attention_single(data, cfg, weights);
     else if(0==strcmp(argv[2], "validmulti")) validate_attention_multi(data, cfg, weights);
 }

examples/classifier.c

@@ -447,7 +447,7 @@ void validate_classifier_multi(char *datacfg, char *cfg, char *weights)
         float *pred = calloc(classes, sizeof(float));
         image im = load_image_color(paths[i], 0, 0);
         for(j = 0; j < nscales; ++j){
-            image r = resize_min(im, scales[j]);
+            image r = resize_max(im, scales[j]);
             resize_network(net, r.w, r.h);
             float *p = network_predict(net, r.data);
             if(net->hierarchy) hierarchy_predictions(p, net->outputs, net->hierarchy, 1 , 1);

examples/darknet.c

@@ -12,6 +12,7 @@ extern void run_coco(int argc, char **argv);
 extern void run_captcha(int argc, char **argv);
 extern void run_nightmare(int argc, char **argv);
 extern void run_classifier(int argc, char **argv);
+extern void run_attention(int argc, char **argv);
 extern void run_regressor(int argc, char **argv);
 extern void run_segmenter(int argc, char **argv);
 extern void run_char_rnn(int argc, char **argv);
@@ -431,6 +432,8 @@ int main(int argc, char **argv)
         predict_classifier("cfg/imagenet1k.data", argv[2], argv[3], argv[4], 5);
     } else if (0 == strcmp(argv[1], "classifier")){
         run_classifier(argc, argv);
+    } else if (0 == strcmp(argv[1], "attention")){
+        run_attention(argc, argv);
     } else if (0 == strcmp(argv[1], "regressor")){
         run_regressor(argc, argv);
     } else if (0 == strcmp(argv[1], "segmenter")){

examples/detector-scipy-opencv.py

@@ -0,0 +1,56 @@
+# Stupid python path shit.
+# Instead just add darknet.py to somewhere in your python path
+# OK actually that might not be a great idea, idk, work in progress
+# Use at your own risk. or don't, i don't care
+
+from scipy.misc import imread
+import cv2
+
+def array_to_image(arr):
+    arr = arr.transpose(2,0,1)
+    c = arr.shape[0]
+    h = arr.shape[1]
+    w = arr.shape[2]
+    arr = (arr/255.0).flatten()
+    data = dn.c_array(dn.c_float, arr)
+    im = dn.IMAGE(w,h,c,data)
+    return im
+
+def detect2(net, meta, image, thresh=.5, hier_thresh=.5, nms=.45):
+    boxes = dn.make_boxes(net)
+    probs = dn.make_probs(net)
+    num =   dn.num_boxes(net)
+    dn.network_detect(net, image, thresh, hier_thresh, nms, boxes, probs)
+    res = []
+    for j in range(num):
+        for i in range(meta.classes):
+            if probs[j][i] > 0:
+                res.append((meta.names[i], probs[j][i], (boxes[j].x, boxes[j].y, boxes[j].w, boxes[j].h)))
+    res = sorted(res, key=lambda x: -x[1])
+    dn.free_ptrs(dn.cast(probs, dn.POINTER(dn.c_void_p)), num)
+    return res
+
+import sys, os
+sys.path.append(os.path.join(os.getcwd(),'python/'))
+
+import darknet as dn
+
+# Darknet
+net = dn.load_net("cfg/tiny-yolo.cfg", "tiny-yolo.weights", 0)
+meta = dn.load_meta("cfg/coco.data")
+r = dn.detect(net, meta, "data/dog.jpg")
+print r
+
+# scipy
+arr= imread('data/dog.jpg')
+im = array_to_image(arr)
+r = detect2(net, meta, im)
+print r
+
+# OpenCV
+arr = cv2.imread('data/dog.jpg')
+im = array_to_image(arr)
+dn.rgbgr_image(im)
+r = detect2(net, meta, im)
+print r
+

examples/detector.c

@@ -609,8 +609,8 @@ void test_detector(char *datacfg, char *cfgfile, char *weightfile, char *filenam
         network_predict(net, X);
         printf("%s: Predicted in %f seconds.\n", input, what_time_is_it_now()-time);
         get_region_boxes(l, im.w, im.h, net->w, net->h, thresh, probs, boxes, masks, 0, 0, hier_thresh, 1);
+        //if (nms) do_nms_obj(boxes, probs, l.w*l.h*l.n, l.classes, nms);
         if (nms) do_nms_sort(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, masks, names, alphabet, l.classes);
         if(outfile){
             save_image(im, outfile);

examples/detector.py

@@ -9,12 +9,20 @@ sys.path.append(os.path.join(os.getcwd(),'python/'))
 import darknet as dn
 import pdb
 
+<<<<<<< HEAD
 net = dn.load_net("cfg/yolo-tag.cfg", "yolo-tag_final.weights", 0)
 meta = dn.load_meta("cfg/openimages.data")
 pdb.set_trace()
 rr = dn.detect(net, meta, 'data/dog.jpg')
 print rr
 pdb.set_trace()
+=======
+dn.set_gpu(0)
+net = dn.load_net("cfg/tiny-yolo.cfg", "tiny-yolo.weights", 0)
+meta = dn.load_meta("cfg/coco.data")
+r = dn.detect(net, meta, "data/dog.jpg")
+print r
+>>>>>>> 16686cec576580489ab3c7c78183e6efeafae780
 
 # And then down here you could detect a lot more images like:
 rr = dn.detect(net, meta, "data/eagle.jpg")

include/darknet.h

@@ -56,6 +56,10 @@ typedef enum{
     LOGISTIC, RELU, RELIE, LINEAR, RAMP, TANH, PLSE, LEAKY, ELU, LOGGY, STAIR, HARDTAN, LHTAN
 } ACTIVATION;
 
+typedef enum{
+    MULT, ADD, SUB, DIV
+} BINARY_ACTIVATION;
+
 typedef enum {
     CONVOLUTIONAL,
     DECONVOLUTIONAL,
@@ -578,6 +582,8 @@ list *read_data_cfg(char *filename);
 list *read_cfg(char *filename);
 unsigned char *read_file(char *filename);
 data resize_data(data orig, int w, int h);
+data *tile_data(data orig, int divs, int size);
+data select_data(data *orig, int *inds);
 
 void forward_network(network *net);
 void backward_network(network *net);
@@ -588,6 +594,7 @@ void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY);
 void copy_cpu(int N, float *X, int INCX, float *Y, int INCY);
 void scal_cpu(int N, float ALPHA, float *X, int INCX);
 void normalize_cpu(float *x, float *mean, float *variance, int batch, int filters, int spatial);
+void softmax(float *input, int n, float temp, int stride, float *output);
 
 int best_3d_shift_r(image a, image b, int min, int max);
 #ifdef GPU
@@ -744,12 +751,15 @@ void top_k(float *a, int n, int k, int *index);
 int *read_map(char *filename);
 void error(const char *s);
 int max_index(float *a, int n);
+int max_int_index(int *a, int n);
 int sample_array(float *a, int n);
+int *random_index_order(int min, int max);
 void free_list(list *l);
 float mse_array(float *a, int n);
 float variance_array(float *a, int n);
 float mag_array(float *a, int n);
 float mean_array(float *a, int n);
+float sum_array(float *a, int n);
 void normalize_array(float *a, int n);
 int *read_intlist(char *s, int *n, int d);
 size_t rand_size_t();

python/darknet.py

@@ -31,6 +31,8 @@ class METADATA(Structure):
     _fields_ = [("classes", c_int),
                 ("names", POINTER(c_char_p))]
 
+    
+
 #lib = CDLL("/home/pjreddie/documents/darknet/libdarknet.so", RTLD_GLOBAL)
 lib = CDLL("libdarknet.so", RTLD_GLOBAL)
 lib.network_width.argtypes = [c_void_p]
@@ -42,6 +44,13 @@ predict = lib.network_predict
 predict.argtypes = [c_void_p, POINTER(c_float)]
 predict.restype = POINTER(c_float)
 
+set_gpu = lib.cuda_set_device
+set_gpu.argtypes = [c_int]
+
+make_image = lib.make_image
+make_image.argtypes = [c_int, c_int, c_int]
+make_image.restype = IMAGE
+
 make_boxes = lib.make_boxes
 make_boxes.argtypes = [c_void_p]
 make_boxes.restype = POINTER(BOX)
@@ -82,6 +91,9 @@ load_image = lib.load_image_color
 load_image.argtypes = [c_char_p, c_int, c_int]
 load_image.restype = IMAGE
 
+rgbgr_image = lib.rgbgr_image
+rgbgr_image.argtypes = [IMAGE]
+
 predict_image = lib.network_predict_image
 predict_image.argtypes = [c_void_p, IMAGE]
 predict_image.restype = POINTER(c_float)

src/activation_kernels.cu

@@ -140,6 +140,41 @@ __device__ float gradient_kernel(float x, ACTIVATION a)
     return 0;
 }
 
+__global__ void binary_gradient_array_kernel(float *x, float *dy, int n, int s, BINARY_ACTIVATION a, float *dx)
+{
+    int id = (blockIdx.x + blockIdx.y*gridDim.x) * blockDim.x + threadIdx.x;
+    int i = id % s;
+    int b = id / s;
+    float x1 = x[b*s + i];
+    float x2 = x[b*s + s/2 + i];
+    if(id < n) {
+        float de = dy[id];
+        dx[b*s + i] = x2*de;
+        dx[b*s + s/2 + i] = x1*de; 
+    }
+}
+
+extern "C" void binary_gradient_array_gpu(float *x, float *dx, int n, int size, BINARY_ACTIVATION a, float *y) 
+{
+    binary_gradient_array_kernel<<<cuda_gridsize(n/2), BLOCK>>>(x, dx, n/2, size, a, y);
+    check_error(cudaPeekAtLastError());
+}
+__global__ void binary_activate_array_kernel(float *x, int n, int s, BINARY_ACTIVATION a, float *y)
+{
+    int id = (blockIdx.x + blockIdx.y*gridDim.x) * blockDim.x + threadIdx.x;
+    int i = id % s;
+    int b = id / s;
+    float x1 = x[b*s + i];
+    float x2 = x[b*s + s/2 + i];
+    if(id < n) y[id] = x1*x2;
+}
+
+extern "C" void binary_activate_array_gpu(float *x, int n, int size, BINARY_ACTIVATION a, float *y) 
+{
+    binary_activate_array_kernel<<<cuda_gridsize(n/2), BLOCK>>>(x, n/2, size, a, y);
+    check_error(cudaPeekAtLastError());
+}
+
 __global__ void activate_array_kernel(float *x, int n, ACTIVATION a)
 {
     int i = (blockIdx.x + blockIdx.y*gridDim.x) * blockDim.x + threadIdx.x;

src/cuda.c

@@ -172,5 +172,7 @@ float cuda_mag_array(float *x_gpu, size_t n)
     free(temp);
     return m;
 }
+#else
+void cuda_set_device(int n){}
 
 #endif

src/data.c

@@ -1172,6 +1172,56 @@ data load_data_regression(char **paths, int n, int m, int min, int max, int size
     return d;
 }
 
+data select_data(data *orig, int *inds)
+{
+    data d = {0};
+    d.shallow = 1;
+    d.w = orig[0].w;
+    d.h = orig[0].h;
+
+    d.X.rows = orig[0].X.rows;
+    d.y.rows = orig[0].X.rows;
+
+    d.X.cols = orig[0].X.cols;
+    d.y.cols = orig[0].y.cols;
+
+    d.X.vals = calloc(orig[0].X.rows, sizeof(float *));
+    d.y.vals = calloc(orig[0].y.rows, sizeof(float *));
+    int i;
+    for(i = 0; i < d.X.rows; ++i){
+        d.X.vals[i] = orig[inds[i]].X.vals[i];
+        d.y.vals[i] = orig[inds[i]].y.vals[i];
+    }
+    return d;
+}
+
+data *tile_data(data orig, int divs, int size)
+{
+    data *ds = calloc(divs*divs, sizeof(data));
+    int i, j;
+    #pragma omp parallel for
+    for(i = 0; i < divs*divs; ++i){
+        data d;
+        d.shallow = 0;
+        d.w = orig.w/divs * size;
+        d.h = orig.h/divs * size;
+        d.X.rows = orig.X.rows;
+        d.X.cols = d.w*d.h*3;
+        d.X.vals = calloc(d.X.rows, sizeof(float*));
+
+        d.y = copy_matrix(orig.y);
+        #pragma omp parallel for
+        for(j = 0; j < orig.X.rows; ++j){
+            int x = (i%divs) * orig.w / divs - (d.w - orig.w/divs)/2;
+            int y = (i/divs) * orig.h / divs - (d.h - orig.h/divs)/2;
+            image im = float_to_image(orig.w, orig.h, 3, orig.X.vals[j]);
+            d.X.vals[j] = crop_image(im, x, y, d.w, d.h).data;
+        }
+        ds[i] = d;
+    }
+    return ds;
+}
+
 data resize_data(data orig, int w, int h)
 {
     data d = {0};
@@ -1181,9 +1231,10 @@ data resize_data(data orig, int w, int h)
     int i;
     d.X.rows = orig.X.rows;
     d.X.cols = w*h*3;
-    d.X.vals = calloc(d.X.rows, sizeof(float));
+    d.X.vals = calloc(d.X.rows, sizeof(float*));
 
     d.y = copy_matrix(orig.y);
+    #pragma omp parallel for
     for(i = 0; i < orig.X.rows; ++i){
         image im = float_to_image(orig.w, orig.h, 3, orig.X.vals[i]);
         d.X.vals[i] = resize_image(im, w, h).data;
@@ -1239,6 +1290,8 @@ data concat_data(data d1, data d2)
     d.shallow = 1;
     d.X = concat_matrix(d1.X, d2.X);
     d.y = concat_matrix(d1.y, d2.y);
+    d.w = d1.w;
+    d.h = d1.h;
     return d;
 }
 

src/utils.c

@@ -91,6 +91,22 @@ void shuffle(void *arr, size_t n, size_t size)
     }
 }
 
+int *random_index_order(int min, int max)
+{
+    int *inds = calloc(max-min, sizeof(int));
+    int i;
+    for(i = min; i < max; ++i){
+        inds[i] = i;
+    }
+    for(i = min; i < max-1; ++i){
+        int swap = inds[i];
+        int index = i + rand()%(max-i);
+        inds[i] = inds[index];
+        inds[index] = swap;
+    }
+    return inds;
+}
+
 void del_arg(int argc, char **argv, int index)
 {
     int i;
@@ -583,6 +599,20 @@ int sample_array(float *a, int n)
     return n-1;
 }
 
+int max_int_index(int *a, int n)
+{
+    if(n <= 0) return -1;
+    int i, max_i = 0;
+    int max = a[0];
+    for(i = 1; i < n; ++i){
+        if(a[i] > max){
+            max = a[i];
+            max_i = i;
+        }
+    }
+    return max_i;
+}
+
 int max_index(float *a, int n)
 {
     if(n <= 0) return -1;

src/utils.h

@@ -44,7 +44,6 @@ int constrain_int(int a, int min, int max);
 float rand_uniform(float min, float max);
 float rand_scale(float s);
 int rand_int(int min, int max);
-float sum_array(float *a, int n);
 void mean_arrays(float **a, int n, int els, float *avg);
 float dist_array(float *a, float *b, int n, int sub);
 float **one_hot_encode(float *a, int n, int k);