From 846b3b4366c8d1a1ab7215db3ce4f4180ea53cb5 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 30 Jul 2015 23:19:14 +0000
Subject: [PATCH] Added COCO, fixed memory leaks
---
src/image.c | 1
src/box.h | 1
src/coco.c | 297 ++++++++++++++++++++++++++++++++++++++++++
src/detection.c | 20 --
Makefile | 2
src/convolutional_layer.c | 13 +
src/box.c | 20 ++
src/convolutional_layer.h | 2
src/darknet.c | 24 +++
src/detection_layer.c | 1
10 files changed, 359 insertions(+), 22 deletions(-)
diff --git a/Makefile b/Makefile
index 1f8c84b..eff05bc 100644
--- a/Makefile
+++ b/Makefile
@@ -34,7 +34,7 @@
LDFLAGS+= -L/usr/local/cuda/lib64 -lcuda -lcudart -lcublas -lcurand
endif
-OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o imagenet.o captcha.o detection.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o
+OBJ=gemm.o utils.o cuda.o deconvolutional_layer.o convolutional_layer.o list.o image.o activations.o im2col.o col2im.o blas.o crop_layer.o dropout_layer.o maxpool_layer.o softmax_layer.o data.o matrix.o network.o connected_layer.o cost_layer.o parser.o option_list.o darknet.o detection_layer.o imagenet.o captcha.o detection.o route_layer.o writing.o box.o nightmare.o normalization_layer.o avgpool_layer.o coco.o
ifeq ($(GPU), 1)
OBJ+=convolutional_kernels.o deconvolutional_kernels.o activation_kernels.o im2col_kernels.o col2im_kernels.o blas_kernels.o crop_layer_kernels.o dropout_layer_kernels.o maxpool_layer_kernels.o softmax_layer_kernels.o network_kernels.o avgpool_layer_kernels.o
endif
diff --git a/src/box.c b/src/box.c
index cce56bd..0518c05 100644
--- a/src/box.c
+++ b/src/box.c
@@ -211,3 +211,23 @@
return dd;
}
+void do_nms(box *boxes, float **probs, int num_boxes, int classes, float thresh)
+{
+ int i, j, k;
+ for(i = 0; i < num_boxes*num_boxes; ++i){
+ int any = 0;
+ for(k = 0; k < classes; ++k) any = any || (probs[i][k] > 0);
+ if(!any) {
+ continue;
+ }
+ for(j = i+1; j < num_boxes*num_boxes; ++j){
+ if (box_iou(boxes[i], boxes[j]) > thresh){
+ for(k = 0; k < classes; ++k){
+ if (probs[i][k] < probs[j][k]) probs[i][k] = 0;
+ else probs[j][k] = 0;
+ }
+ }
+ }
+ }
+}
+
diff --git a/src/box.h b/src/box.h
index e3831d8..998f58a 100644
--- a/src/box.h
+++ b/src/box.h
@@ -11,5 +11,6 @@
float box_iou(box a, box b);
dbox diou(box a, box b);
+void do_nms(box *boxes, float **probs, int num_boxes, int classes, float thresh);
#endif
diff --git a/src/coco.c b/src/coco.c
new file mode 100644
index 0000000..af76ecc
--- /dev/null
+++ b/src/coco.c
@@ -0,0 +1,297 @@
+#include "network.h"
+#include "detection_layer.h"
+#include "cost_layer.h"
+#include "utils.h"
+#include "parser.h"
+#include "box.h"
+
+
+char *coco_classes[] = {"person","bicycle","car","motorcycle","airplane","bus","train","truck","boat","traffic light","fire hydrant","stop sign","parking meter","bench","bird","cat","dog","horse","sheep","cow","elephant","bear","zebra","giraffe","backpack","umbrella","handbag","tie","suitcase","frisbee","skis","snowboard","sports ball","kite","baseball bat","baseball glove","skateboard","surfboard","tennis racket","bottle","wine glass","cup","fork","knife","spoon","bowl","banana","apple","sandwich","orange","broccoli","carrot","hot dog","pizza","donut","cake","chair","couch","potted plant","bed","dining table","toilet","tv","laptop","mouse","remote","keyboard","cell phone","microwave","oven","toaster","sink","refrigerator","book","clock","vase","scissors","teddy bear","hair drier","toothbrush"};
+
+void draw_coco(image im, float *box, int side, int objectness, char *label)
+{
+ int classes = 80;
+ int elems = 4+classes+objectness;
+ int j;
+ int r, c;
+
+ for(r = 0; r < side; ++r){
+ for(c = 0; c < side; ++c){
+ j = (r*side + c) * elems;
+ float scale = 1;
+ if(objectness) scale = 1 - box[j++];
+ int class = max_index(box+j, classes);
+ if(scale * box[j+class] > 0.2){
+ int width = box[j+class]*5 + 1;
+ printf("%f %s\n", scale * box[j+class], coco_classes[class]);
+ float red = get_color(0,class,classes);
+ float green = get_color(1,class,classes);
+ float blue = get_color(2,class,classes);
+
+ j += classes;
+ float x = box[j+0];
+ float y = box[j+1];
+ x = (x+c)/side;
+ y = (y+r)/side;
+ float w = box[j+2]; //*maxwidth;
+ float h = box[j+3]; //*maxheight;
+ h = h*h;
+ w = w*w;
+
+ 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_width(im, left, top, right, bot, width, red, green, blue);
+ }
+ }
+ }
+ show_image(im, label);
+}
+
+void train_coco(char *cfgfile, char *weightfile)
+{
+ char *train_images = "/home/pjreddie/data/coco/train.txt";
+ char *backup_directory = "/home/pjreddie/backup/";
+ 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);
+ }
+ 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.objectness;
+ int side = sqrt(get_detection_layer_locations(layer));
+
+ char **paths;
+ list *plist = get_paths(train_images);
+ int N = plist->size;
+
+ 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(i*imgs < N*120){
+ 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);
+
+ printf("Loaded: %lf seconds\n", sec(clock()-time));
+
+ /*
+ image im = float_to_image(net.w, net.h, 3, train.X.vals[114]);
+ image copy = copy_image(im);
+ draw_coco(copy, train.y.vals[114], 7, layer.objectness, "truth");
+ cvWaitKey(0);
+ free_image(copy);
+ */
+
+ 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-1)*imgs <= 80*N && i*imgs > N*80){
+ fprintf(stderr, "First stage done.\n");
+ char buff[256];
+ sprintf(buff, "%s/%s_first_stage.weights", backup_directory, base);
+ save_weights(net, buff);
+ return;
+ }
+ if(i%1000==0 || 1){
+ char buff[256];
+ sprintf(buff, "%s/%s_%d.weights", backup_directory, base, i);
+ save_weights(net, buff);
+ }
+ free_data(train);
+ return;
+ }
+ char buff[256];
+ sprintf(buff, "%s/%s_final.weights", backup_directory, base);
+ save_weights(net, buff);
+}
+
+void convert_cocos(float *predictions, int classes, int objectness, int background, int num_boxes, int w, int h, float thresh, float **probs, box *boxes)
+{
+ int i,j;
+ int per_box = 4+classes+(background || objectness);
+ for (i = 0; i < num_boxes*num_boxes; ++i){
+ float scale = 1;
+ if(objectness) scale = 1-predictions[i*per_box];
+ int offset = i*per_box+(background||objectness);
+ for(j = 0; j < classes; ++j){
+ float prob = scale*predictions[offset+j];
+ probs[i][j] = (prob > thresh) ? prob : 0;
+ }
+ int row = i / num_boxes;
+ int col = i % num_boxes;
+ offset += classes;
+ boxes[i].x = (predictions[offset + 0] + col) / num_boxes * w;
+ boxes[i].y = (predictions[offset + 1] + row) / num_boxes * h;
+ boxes[i].w = pow(predictions[offset + 2], 2) * w;
+ boxes[i].h = pow(predictions[offset + 3], 2) * h;
+ }
+}
+
+void print_cocos(FILE **fps, char *id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
+{
+ int i, j;
+ for(i = 0; i < num_boxes*num_boxes; ++i){
+ float xmin = boxes[i].x - boxes[i].w/2.;
+ float xmax = boxes[i].x + boxes[i].w/2.;
+ float ymin = boxes[i].y - boxes[i].h/2.;
+ float ymax = boxes[i].y + boxes[i].h/2.;
+
+ if (xmin < 0) xmin = 0;
+ if (ymin < 0) ymin = 0;
+ if (xmax > w) xmax = w;
+ if (ymax > h) ymax = h;
+
+ for(j = 0; j < classes; ++j){
+ if (probs[i][j]) fprintf(fps[j], "%s %f %f %f %f %f\n", id, probs[i][j],
+ xmin, ymin, xmax, ymax);
+ }
+ }
+}
+
+void validate_coco(char *cfgfile, char *weightfile)
+{
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ set_batch_network(&net, 1);
+ 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));
+
+ char *base = "results/comp4_det_test_";
+ list *plist = get_paths("data/voc.2012test.list");
+ char **paths = (char **)list_to_array(plist);
+
+ int classes = layer.classes;
+ int objectness = layer.objectness;
+ int background = layer.background;
+ int num_boxes = sqrt(get_detection_layer_locations(layer));
+
+ int j;
+ FILE **fps = calloc(classes, sizeof(FILE *));
+ for(j = 0; j < classes; ++j){
+ char buff[1024];
+ snprintf(buff, 1024, "%s%s.txt", base, coco_classes[j]);
+ fps[j] = fopen(buff, "w");
+ }
+ box *boxes = calloc(num_boxes*num_boxes, sizeof(box));
+ float **probs = calloc(num_boxes*num_boxes, sizeof(float *));
+ for(j = 0; j < num_boxes*num_boxes; ++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 = 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));
+ for(t = 0; t < nthreads; ++t){
+ thr[t] = load_image_thread(paths[i+t], &buf[t], &buf_resized[t], net.w, net.h);
+ }
+ 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){
+ thr[t] = load_image_thread(paths[i+t], &buf[t], &buf_resized[t], net.w, net.h);
+ }
+ 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_cocos(predictions, classes, objectness, background, num_boxes, w, h, thresh, probs, boxes);
+ if (nms) do_nms(boxes, probs, num_boxes, classes, iou_thresh);
+ print_cocos(fps, id, boxes, probs, num_boxes, 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 test_coco(char *cfgfile, char *weightfile, char *filename)
+{
+
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ detection_layer layer = get_network_detection_layer(net);
+ set_batch_network(&net, 1);
+ srand(2222222);
+ clock_t time;
+ char input[256];
+ while(1){
+ if(filename){
+ strncpy(input, filename, 256);
+ } else {
+ printf("Enter Image Path: ");
+ fflush(stdout);
+ fgets(input, 256, stdin);
+ 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();
+ float *predictions = network_predict(net, X);
+ printf("%s: Predicted in %f seconds.\n", input, sec(clock()-time));
+ draw_coco(im, predictions, 7, layer.objectness, "predictions");
+ free_image(im);
+ free_image(sized);
+#ifdef OPENCV
+ cvWaitKey(0);
+ cvDestroyAllWindows();
+#endif
+ if (filename) break;
+ }
+}
+
+void run_coco(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;
+ char *filename = (argc > 5) ? argv[5]: 0;
+ if(0==strcmp(argv[2], "test")) test_coco(cfg, weights, filename);
+ else if(0==strcmp(argv[2], "train")) train_coco(cfg, weights);
+ else if(0==strcmp(argv[2], "valid")) validate_coco(cfg, weights);
+}
diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
index 378e23f..7dcf5a4 100644
--- a/src/convolutional_layer.c
+++ b/src/convolutional_layer.c
@@ -242,6 +242,19 @@
}
}
+void rescale_filters(convolutional_layer l, float scale, float trans)
+{
+ int i;
+ for(i = 0; i < l.n; ++i){
+ image im = get_convolutional_filter(l, i);
+ if (im.c == 3) {
+ scale_image(im, scale);
+ float sum = sum_array(im.data, im.w*im.h*im.c);
+ l.biases[i] += sum*trans;
+ }
+ }
+}
+
image *get_filters(convolutional_layer l)
{
image *filters = calloc(l.n, sizeof(image));
diff --git a/src/convolutional_layer.h b/src/convolutional_layer.h
index 3954f8a..7452c3c 100644
--- a/src/convolutional_layer.h
+++ b/src/convolutional_layer.h
@@ -38,6 +38,8 @@
int convolutional_out_height(convolutional_layer layer);
int convolutional_out_width(convolutional_layer layer);
+void rescale_filters(convolutional_layer l, float scale, float trans);
+void rgbgr_filters(convolutional_layer l);
#endif
diff --git a/src/darknet.c b/src/darknet.c
index 321b5a9..d7fb1f5 100644
--- a/src/darknet.c
+++ b/src/darknet.c
@@ -11,6 +11,7 @@
extern void run_imagenet(int argc, char **argv);
extern void run_detection(int argc, char **argv);
+extern void run_coco(int argc, char **argv);
extern void run_writing(int argc, char **argv);
extern void run_captcha(int argc, char **argv);
extern void run_nightmare(int argc, char **argv);
@@ -40,7 +41,24 @@
}
#include "convolutional_layer.h"
-void rgbgr_filters(convolutional_layer l);
+void rescale_net(char *cfgfile, char *weightfile, char *outfile)
+{
+ gpu_index = -1;
+ network net = parse_network_cfg(cfgfile);
+ if(weightfile){
+ load_weights(&net, weightfile);
+ }
+ int i;
+ for(i = 0; i < net.n; ++i){
+ layer l = net.layers[i];
+ if(l.type == CONVOLUTIONAL){
+ rescale_filters(l, 2, -.5);
+ break;
+ }
+ }
+ save_weights(net, outfile);
+}
+
void rgbgr_net(char *cfgfile, char *weightfile, char *outfile)
{
gpu_index = -1;
@@ -95,6 +113,8 @@
run_imagenet(argc, argv);
} else if (0 == strcmp(argv[1], "detection")){
run_detection(argc, argv);
+ } else if (0 == strcmp(argv[1], "coco")){
+ run_coco(argc, argv);
} else if (0 == strcmp(argv[1], "writing")){
run_writing(argc, argv);
} else if (0 == strcmp(argv[1], "test")){
@@ -107,6 +127,8 @@
change_rate(argv[2], atof(argv[3]), (argc > 4) ? atof(argv[4]) : 0);
} else if (0 == strcmp(argv[1], "rgbgr")){
rgbgr_net(argv[2], argv[3], argv[4]);
+ } else if (0 == strcmp(argv[1], "rescale")){
+ rescale_net(argv[2], argv[3], argv[4]);
} else if (0 == strcmp(argv[1], "partial")){
partial(argv[2], argv[3], argv[4], atoi(argv[5]));
} else if (0 == strcmp(argv[1], "visualize")){
diff --git a/src/detection.c b/src/detection.c
index 615ad6d..55c75de 100644
--- a/src/detection.c
+++ b/src/detection.c
@@ -143,26 +143,6 @@
}
}
-void do_nms(box *boxes, float **probs, int num_boxes, int classes, float thresh)
-{
- int i, j, k;
- for(i = 0; i < num_boxes*num_boxes; ++i){
- int any = 0;
- for(k = 0; k < classes; ++k) any = any || (probs[i][k] > 0);
- if(!any) {
- continue;
- }
- for(j = i+1; j < num_boxes*num_boxes; ++j){
- if (box_iou(boxes[i], boxes[j]) > thresh){
- for(k = 0; k < classes; ++k){
- if (probs[i][k] < probs[j][k]) probs[i][k] = 0;
- else probs[j][k] = 0;
- }
- }
- }
- }
-}
-
void print_detections(FILE **fps, char *id, box *boxes, float **probs, int num_boxes, int classes, int w, int h)
{
int i, j;
diff --git a/src/detection_layer.c b/src/detection_layer.c
index 6a25819..e48b8b3 100644
--- a/src/detection_layer.c
+++ b/src/detection_layer.c
@@ -204,6 +204,7 @@
backward_detection_layer(l, cpu_state);
cuda_push_array(state.delta, delta_cpu, l.batch*l.inputs);
+ if (truth_cpu) free(truth_cpu);
free(in_cpu);
free(delta_cpu);
}
diff --git a/src/image.c b/src/image.c
index 5db93f1..92c9066 100644
--- a/src/image.c
+++ b/src/image.c
@@ -249,6 +249,7 @@
}
}
int success = stbi_write_png(buff, im.w, im.h, im.c, data, im.w*im.c);
+ free(data);
if(!success) fprintf(stderr, "Failed to write image %s\n", buff);
}
--
Gitblit v1.10.0