mirror/darknet
1
0
Fork 0
mirror of https://github.com/pjreddie/darknet.git synced 2023-08-10 21:13:14 +03:00
Code Issues Projects Releases Wiki Activity

stuff and things

Browse Source
This commit is contained in:
Joseph Redmon 2016-11-07 23:42:19 -08:00
parent 252e3b1916
commit 4b60afcc64
5 changed files with 76 additions and 39 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
src/layer.h
View File

@ -67,6 +67,7 @@ struct layer{
int size;
int side;
int stride;
int reverse;
int pad;
int sqrt;
int flip;
@ -118,6 +119,7 @@ struct layer{
int bias_match;
int random;
float thresh;
int classfix;
int dontload;
int dontloadscales;

4
src/parser.c
View File

@ -268,6 +268,7 @@ layer parse_region(list *options, size_params params)
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.coord_scale = option_find_float(options, "coord_scale", 1);
l.object_scale = option_find_float(options, "object_scale", 1);
@ -357,6 +358,7 @@ crop_layer parse_crop(list *options, size_params params)
layer parse_reorg(list *options, size_params params)
{
int stride = option_find_int(options, "stride",1);
int reverse = option_find_int_quiet(options, "reverse",0);
int batch,h,w,c;
h = params.h;
@ -365,7 +367,7 @@ layer parse_reorg(list *options, size_params params)
batch=params.batch;
if(!(h && w && c)) error("Layer before reorg layer must output image.");
layer layer = make_reorg_layer(batch,w,h,c,stride);
layer layer = make_reorg_layer(batch,w,h,c,stride,reverse);
return layer;
}

73
src/region_layer.c
View File

@ -89,6 +89,31 @@ float delta_region_box(box truth, float *x, float *biases, int n, int index, int
return iou;
}
void delta_region_class(float *output, float *delta, int index, int class, int classes, tree *hier, float scale, float *avg_cat)
{
int i, n;
if(hier){
float pred = 1;
while(class >= 0){
pred *= output[index + class];
int g = hier->group[class];
int offset = hier->group_offset[g];
for(i = 0; i < hier->group_size[g]; ++i){
delta[index + offset + i] = scale * (0 - output[index + offset + i]);
}
delta[index + class] = scale * (1 - output[index + class]);
class = hier->parent[class];
}
*avg_cat += pred;
} else {
for(n = 0; n < classes; ++n){
delta[index + n] = scale * (((n == class)?1 : 0) - output[index + n]);
if(n == class) *avg_cat += output[index + n];
}
}
}
float logit(float x)
{
return log(x/(1.-x));
@ -125,6 +150,7 @@ void forward_region_layer(const region_layer l, network_state state)
float avg_obj = 0;
float avg_anyobj = 0;
int count = 0;
int class_count = 0;
*(l.cost) = 0;
for (b = 0; b < l.batch; ++b) {
for (j = 0; j < l.h; ++j) {
@ -133,15 +159,28 @@ void forward_region_layer(const region_layer l, network_state state)
int index = size*(j*l.w*l.n + i*l.n + n) + b*l.outputs;
box pred = get_region_box(l.output, l.biases, n, index, i, j, l.w, l.h);
float best_iou = 0;
int best_class = -1;
for(t = 0; t < 30; ++t){
box truth = float_to_box(state.truth + t*5 + b*l.truths);
if(!truth.x) break;
float iou = box_iou(pred, truth);
if (iou > best_iou) best_iou = iou;
if (iou > best_iou) {
best_class = state.truth[t*5 + b*l.truths + 4];
best_iou = iou;
}
}
avg_anyobj += l.output[index + 4];
l.delta[index + 4] = l.noobject_scale * ((0 - l.output[index + 4]) * logistic_gradient(l.output[index + 4]));
if(best_iou > l.thresh) l.delta[index + 4] = 0;
if(l.classfix == -1) l.delta[index + 4] = l.noobject_scale * ((best_iou - l.output[index + 4]) * logistic_gradient(l.output[index + 4]));
else{
if (best_iou > l.thresh) {
l.delta[index + 4] = 0;
if(l.classfix > 0){
delta_region_class(l.output, l.delta, index + 5, best_class, l.classes, l.softmax_tree, l.class_scale*(l.classfix == 2 ? l.output[index + 4] : 1), &avg_cat);
++class_count;
}
}
}
if(*(state.net.seen) < 12800){
box truth = {0};
@ -205,35 +244,15 @@ void forward_region_layer(const region_layer l, network_state state)
int class = state.truth[t*5 + b*l.truths + 4];
if (l.map) class = l.map[class];
if(l.softmax_tree){
float pred = 1;
while(class >= 0){
pred *= l.output[best_index + 5 + class];
int g = l.softmax_tree->group[class];
int i;
int offset = l.softmax_tree->group_offset[g];
for(i = 0; i < l.softmax_tree->group_size[g]; ++i){
int index = best_index + 5 + offset + i;
l.delta[index] = l.class_scale * (0 - l.output[index]);
}
l.delta[best_index + 5 + class] = l.class_scale * (1 - l.output[best_index + 5 + class]);
class = l.softmax_tree->parent[class];
}
avg_cat += pred;
} else {
for(n = 0; n < l.classes; ++n){
l.delta[best_index + 5 + n] = l.class_scale * (((n == class)?1 : 0) - l.output[best_index + 5 + n]);
if(n == class) avg_cat += l.output[best_index + 5 + n];
}
}
delta_region_class(l.output, l.delta, best_index + 5, class, l.classes, l.softmax_tree, l.class_scale, &avg_cat);
++count;
++class_count;
}
}
//printf("\n");
reorg(l.delta, l.w*l.h, size*l.n, l.batch, 0);
*(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
printf("Region Avg IOU: %f, Class: %f, Obj: %f, No Obj: %f, Avg Recall: %f, count: %d\n", avg_iou/count, avg_cat/count, avg_obj/count, avg_anyobj/(l.w*l.h*l.n*l.batch), recall/count, count);
printf("Region Avg IOU: %f, Class: %f, Obj: %f, No Obj: %f, Avg Recall: %f, count: %d\n", avg_iou/count, avg_cat/class_count, avg_obj/count, avg_anyobj/(l.w*l.h*l.n*l.batch), recall/count, count);
}
void backward_region_layer(const region_layer l, network_state state)
@ -245,7 +264,6 @@ void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *b
{
int i,j,n;
float *predictions = l.output;
//int per_cell = 5*num+classes;
for (i = 0; i < l.w*l.h; ++i){
int row = i / l.w;
int col = i % l.w;
@ -253,6 +271,7 @@ void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *b
int index = i*l.n + n;
int p_index = index * (l.classes + 5) + 4;
float scale = predictions[p_index];
if(l.classfix == -1 && scale < .5) scale = 0;
int box_index = index * (l.classes + 5);
boxes[index] = get_region_box(predictions, l.biases, n, box_index, col, row, l.w, l.h);
boxes[index].x *= w;
@ -262,7 +281,7 @@ void get_region_boxes(layer l, int w, int h, float thresh, float **probs, box *b
int class_index = index * (l.classes + 5) + 5;
if(l.softmax_tree){
hierarchy_predictions(predictions + class_index, l.classes, l.softmax_tree, 0);
int found = 0;
for(j = l.classes - 1; j >= 0; --j){

34
src/reorg_layer.c
View File

@ -4,7 +4,7 @@
#include <stdio.h>
layer make_reorg_layer(int batch, int h, int w, int c, int stride)
layer make_reorg_layer(int batch, int h, int w, int c, int stride, int reverse)
{
layer l = {0};
l.type = REORG;
@ -13,9 +13,15 @@ layer make_reorg_layer(int batch, int h, int w, int c, int stride)
l.h = h;
l.w = w;
l.c = c;
l.out_w = w*stride;
l.out_h = h*stride;
l.out_c = c/(stride*stride);
if(reverse){
l.out_w = w*stride;
l.out_h = h*stride;
l.out_c = c/(stride*stride);
}else{
l.out_w = w/stride;
l.out_h = h/stride;
l.out_c = c*(stride*stride);
}
fprintf(stderr, "Reorg Layer: %d x %d x %d image -> %d x %d x %d image, \n", w,h,c,l.out_w, l.out_h, l.out_c);
l.outputs = l.out_h * l.out_w * l.out_c;
l.inputs = h*w*c;
@ -25,13 +31,13 @@ layer make_reorg_layer(int batch, int h, int w, int c, int stride)
l.forward = forward_reorg_layer;
l.backward = backward_reorg_layer;
#ifdef GPU
#ifdef GPU
l.forward_gpu = forward_reorg_layer_gpu;
l.backward_gpu = backward_reorg_layer_gpu;
l.output_gpu = cuda_make_array(l.output, output_size);
l.delta_gpu = cuda_make_array(l.delta, output_size);
#endif
#endif
return l;
}
@ -52,12 +58,12 @@ void resize_reorg_layer(layer *l, int w, int h)
l->output = realloc(l->output, output_size * sizeof(float));
l->delta = realloc(l->delta, output_size * sizeof(float));
#ifdef GPU
#ifdef GPU
cuda_free(l->output_gpu);
cuda_free(l->delta_gpu);
l->output_gpu = cuda_make_array(l->output, output_size);
l->delta_gpu = cuda_make_array(l->delta, output_size);
#endif
#endif
}
void forward_reorg_layer(const layer l, network_state state)
@ -107,11 +113,19 @@ void backward_reorg_layer(const layer l, network_state state)
#ifdef GPU
void forward_reorg_layer_gpu(layer l, network_state state)
{
reorg_ongpu(state.input, l.w, l.h, l.c, l.batch, l.stride, 1, l.output_gpu);
if(l.reverse){
reorg_ongpu(state.input, l.w, l.h, l.c, l.batch, l.stride, 1, l.output_gpu);
}else {
reorg_ongpu(state.input, l.w, l.h, l.c, l.batch, l.stride, 0, l.output_gpu);
}
}
void backward_reorg_layer_gpu(layer l, network_state state)
{
reorg_ongpu(l.delta_gpu, l.w, l.h, l.c, l.batch, l.stride, 0, state.delta);
if(l.reverse){
reorg_ongpu(l.delta_gpu, l.w, l.h, l.c, l.batch, l.stride, 0, state.delta);
}else{
reorg_ongpu(l.delta_gpu, l.w, l.h, l.c, l.batch, l.stride, 1, state.delta);
}
}
#endif

2
src/reorg_layer.h
View File

@ -6,7 +6,7 @@
#include "layer.h"
#include "network.h"
layer make_reorg_layer(int batch, int h, int w, int c, int stride);
layer make_reorg_layer(int batch, int h, int w, int c, int stride, int reverse);
void resize_reorg_layer(layer *l, int w, int h);
void forward_reorg_layer(const layer l, network_state state);
void backward_reorg_layer(const layer l, network_state state);