From 6d56c38e8bcb9041335b03f27c192c24dfaedb1c Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Wed, 28 Mar 2018 23:39:28 +0000
Subject: [PATCH] Merge branch 'master' of github.com:AlexeyAB/darknet
---
src/network.c | 152 ++++++++++++++++++++++++++++++++++++++++++++++++--
1 files changed, 145 insertions(+), 7 deletions(-)
diff --git a/src/network.c b/src/network.c
index 0c1b9af..51d290c 100644
--- a/src/network.c
+++ b/src/network.c
@@ -27,6 +27,7 @@
#include "dropout_layer.h"
#include "route_layer.h"
#include "shortcut_layer.h"
+#include "yolo_layer.h"
int get_current_batch(network net)
{
@@ -140,6 +141,11 @@
#ifdef GPU
net.input_gpu = calloc(1, sizeof(float *));
net.truth_gpu = calloc(1, sizeof(float *));
+
+ net.input16_gpu = calloc(1, sizeof(float *));
+ net.output16_gpu = calloc(1, sizeof(float *));
+ net.max_input16_size = calloc(1, sizeof(size_t));
+ net.max_output16_size = calloc(1, sizeof(size_t));
#endif
return net;
}
@@ -316,7 +322,20 @@
net->layers[i].batch = b;
#ifdef CUDNN
if(net->layers[i].type == CONVOLUTIONAL){
- cudnn_convolutional_setup(net->layers + i);
+ cudnn_convolutional_setup(net->layers + i, cudnn_fastest);
+ /*
+ layer *l = net->layers + i;
+ cudnn_convolutional_setup(l, cudnn_fastest);
+ // check for excessive memory consumption
+ size_t free_byte;
+ size_t total_byte;
+ check_error(cudaMemGetInfo(&free_byte, &total_byte));
+ if (l->workspace_size > free_byte || l->workspace_size >= total_byte / 2) {
+ printf(" used slow CUDNN algo without Workspace! \n");
+ cudnn_convolutional_setup(l, cudnn_smallest);
+ l->workspace_size = get_workspace_size(*l);
+ }
+ */
}
#endif
}
@@ -328,6 +347,12 @@
cuda_set_device(net->gpu_index);
if(gpu_index >= 0){
cuda_free(net->workspace);
+ if (net->input_gpu) {
+ cuda_free(*net->input_gpu);
+ *net->input_gpu = 0;
+ cuda_free(*net->truth_gpu);
+ *net->truth_gpu = 0;
+ }
}
#endif
int i;
@@ -340,6 +365,7 @@
//fflush(stderr);
for (i = 0; i < net->n; ++i){
layer l = net->layers[i];
+ //printf(" %d: layer = %d,", i, l.type);
if(l.type == CONVOLUTIONAL){
resize_convolutional_layer(&l, w, h);
}else if(l.type == CROP){
@@ -348,8 +374,14 @@
resize_maxpool_layer(&l, w, h);
}else if(l.type == REGION){
resize_region_layer(&l, w, h);
+ }else if (l.type == YOLO) {
+ resize_yolo_layer(&l, w, h);
}else if(l.type == ROUTE){
resize_route_layer(&l, net);
+ }else if (l.type == SHORTCUT) {
+ resize_shortcut_layer(&l, w, h);
+ }else if (l.type == UPSAMPLE) {
+ resize_upsample_layer(&l, w, h);
}else if(l.type == REORG){
resize_reorg_layer(&l, w, h);
}else if(l.type == AVGPOOL){
@@ -371,13 +403,9 @@
}
#ifdef GPU
if(gpu_index >= 0){
- if(net->input_gpu) {
- cuda_free(*net->input_gpu);
- *net->input_gpu = 0;
- cuda_free(*net->truth_gpu);
- *net->truth_gpu = 0;
- }
+ printf(" try to allocate workspace = %zu * sizeof(float), ", (workspace_size - 1) / sizeof(float) + 1);
net->workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
+ printf(" CUDA allocate done! \n");
}else {
free(net->workspace);
net->workspace = calloc(1, workspace_size);
@@ -476,6 +504,109 @@
return out;
}
+int num_detections(network *net, float thresh)
+{
+ int i;
+ int s = 0;
+ for (i = 0; i < net->n; ++i) {
+ layer l = net->layers[i];
+ if (l.type == YOLO) {
+ s += yolo_num_detections(l, thresh);
+ }
+ if (l.type == DETECTION || l.type == REGION) {
+ s += l.w*l.h*l.n;
+ }
+ }
+ return s;
+}
+
+detection *make_network_boxes(network *net, float thresh, int *num)
+{
+ layer l = net->layers[net->n - 1];
+ int i;
+ int nboxes = num_detections(net, thresh);
+ if (num) *num = nboxes;
+ detection *dets = calloc(nboxes, sizeof(detection));
+ for (i = 0; i < nboxes; ++i) {
+ dets[i].prob = calloc(l.classes, sizeof(float));
+ if (l.coords > 4) {
+ dets[i].mask = calloc(l.coords - 4, sizeof(float));
+ }
+ }
+ return dets;
+}
+
+
+void custom_get_region_detections(layer l, int w, int h, int net_w, int net_h, float thresh, int *map, float hier, int relative, detection *dets, int letter)
+{
+ box *boxes = calloc(l.w*l.h*l.n, sizeof(box));
+ float **probs = calloc(l.w*l.h*l.n, sizeof(float *));
+ int i, j;
+ for (j = 0; j < l.w*l.h*l.n; ++j) probs[j] = calloc(l.classes, sizeof(float *));
+ get_region_boxes(l, w, h, thresh, probs, boxes, 0, map);
+ for (j = 0; j < l.w*l.h*l.n; ++j) {
+ dets[j].classes = l.classes;
+ dets[j].bbox = boxes[j];
+ dets[j].objectness = 1;
+ for (i = 0; i < l.classes; ++i) {
+ dets[j].prob[i] = probs[j][i];
+ }
+ }
+
+ free(boxes);
+ free_ptrs((void **)probs, l.w*l.h*l.n);
+}
+
+void fill_network_boxes(network *net, int w, int h, float thresh, float hier, int *map, int relative, detection *dets, int letter)
+{
+ int j;
+ for (j = 0; j < net->n; ++j) {
+ layer l = net->layers[j];
+ if (l.type == YOLO) {
+ int count = get_yolo_detections(l, w, h, net->w, net->h, thresh, map, relative, dets, letter);
+ dets += count;
+ }
+ if (l.type == REGION) {
+ custom_get_region_detections(l, w, h, net->w, net->h, thresh, map, hier, relative, dets, letter);
+ //get_region_detections(l, w, h, net->w, net->h, thresh, map, hier, relative, dets);
+ dets += l.w*l.h*l.n;
+ }
+ if (l.type == DETECTION) {
+ get_detection_detections(l, w, h, thresh, dets);
+ dets += l.w*l.h*l.n;
+ }
+ }
+}
+
+detection *get_network_boxes(network *net, int w, int h, float thresh, float hier, int *map, int relative, int *num, int letter)
+{
+ detection *dets = make_network_boxes(net, thresh, num);
+ fill_network_boxes(net, w, h, thresh, hier, map, relative, dets, letter);
+ return dets;
+}
+
+void free_detections(detection *dets, int n)
+{
+ int i;
+ for (i = 0; i < n; ++i) {
+ free(dets[i].prob);
+ if (dets[i].mask) free(dets[i].mask);
+ }
+ free(dets);
+}
+
+float *network_predict_image(network *net, image im)
+{
+ image imr = letterbox_image(im, net->w, net->h);
+ set_batch_network(net, 1);
+ float *p = network_predict(*net, imr.data);
+ free_image(imr);
+ return p;
+}
+
+int network_width(network *net) { return net->w; }
+int network_height(network *net) { return net->h; }
+
matrix network_predict_data_multi(network net, data test, int n)
{
int i,j,b,m;
@@ -606,6 +737,13 @@
if (*net.truth_gpu) cuda_free(*net.truth_gpu);
if (net.input_gpu) free(net.input_gpu);
if (net.truth_gpu) free(net.truth_gpu);
+
+ if (*net.input16_gpu) cuda_free(*net.input16_gpu);
+ if (*net.output16_gpu) cuda_free(*net.output16_gpu);
+ if (net.input16_gpu) free(net.input16_gpu);
+ if (net.output16_gpu) free(net.output16_gpu);
+ if (net.max_input16_size) free(net.max_input16_size);
+ if (net.max_output16_size) free(net.max_output16_size);
#else
free(net.workspace);
#endif
--
Gitblit v1.10.0