294 src/detection_layer.c
View file
@@ -6,42 +6,32 @@
#include "cuda.h"
#include "utils.h"
#include <stdio.h>
#include <assert.h>
#include <string.h>
#include <stdlib.h>

int get_detection_layer_locations(detection_layer l)
{
return l.inputs / (l.classes+l.coords+l.joint+(l.background || l.objectness));
}

int get_detection_layer_output_size(detection_layer l)
{
return get_detection_layer_locations(l)*((l.background || l.objectness) + l.classes + l.coords);
}

detection_layer make_detection_layer(int batch, int inputs, int classes, int coords, int joint, int rescore, int background, int objectness)
detection_layer make_detection_layer(int batch, int inputs, int n, int side, int classes, int coords, int rescore)
{
detection_layer l = {0};
l.type = DETECTION;


l.n = n;
l.batch = batch;
l.inputs = inputs;
l.classes = classes;
l.coords = coords;
l.rescore = rescore;
l.objectness = objectness;
l.background = background;
l.joint = joint;
l.side = side;
assert(side*side*((1 + l.coords)*l.n + l.classes) == inputs);
l.cost = calloc(1, sizeof(float));
l.does_cost=1;
int outputs = get_detection_layer_output_size(l);
l.outputs = outputs;
l.output = calloc(batch*outputs, sizeof(float));
l.delta = calloc(batch*outputs, sizeof(float));
#ifdef GPU
l.output_gpu = cuda_make_array(l.output, batch*outputs);
l.delta_gpu = cuda_make_array(l.delta, batch*outputs);
#endif
l.outputs = l.inputs;
l.truths = l.side*l.side*(1+l.coords+l.classes);
l.output = calloc(batch*l.outputs, sizeof(float));
l.delta = calloc(batch*l.outputs, sizeof(float));
#ifdef GPU
l.output_gpu = cuda_make_array(l.output, batch*l.outputs);
l.delta_gpu = cuda_make_array(l.delta, batch*l.outputs);
#endif

fprintf(stderr, "Detection Layer\n");
srand(0);
@@ -51,163 +41,181 @@ detection_layer make_detection_layer(int batch, int inputs, int classes, int coo

void forward_detection_layer(const detection_layer l, network_state state)
{
int in_i = 0;
int out_i = 0;
int locations = get_detection_layer_locations(l);
int locations = l.side*l.side;
int i,j;
for(i = 0; i < l.batch*locations; ++i){
int mask = (!state.truth || state.truth[out_i + (l.background || l.objectness) + l.classes + 2]);
float scale = 1;
if(l.joint) scale = state.input[in_i++];
else if(l.objectness){
l.output[out_i++] = 1-state.input[in_i++];
scale = mask;
}
else if(l.background) l.output[out_i++] = scale*state.input[in_i++];

for(j = 0; j < l.classes; ++j){
l.output[out_i++] = scale*state.input[in_i++];
}
if(l.objectness){

}else if(l.background){
softmax_array(l.output + out_i - l.classes-l.background, l.classes+l.background, l.output + out_i - l.classes-l.background);
activate_array(state.input+in_i, l.coords, LOGISTIC);
}
for(j = 0; j < l.coords; ++j){
l.output[out_i++] = mask*state.input[in_i++];
memcpy(l.output, state.input, l.outputs*l.batch*sizeof(float));
int b;
if (l.softmax){
for(b = 0; b < l.batch; ++b){
int index = b*l.inputs;
for (i = 0; i < locations; ++i) {
int offset = i*l.classes;
softmax_array(l.output + index + offset, l.classes,
l.output + index + offset);
}
int offset = locations*l.classes;
activate_array(l.output + index + offset, locations*l.n*(1+l.coords), LOGISTIC);
}
}
float avg_iou = 0;
int count = 0;
if(l.does_cost && state.train){
if(state.train){
float avg_iou = 0;
float avg_cat = 0;
float avg_allcat = 0;
float avg_obj = 0;
float avg_anyobj = 0;
int count = 0;
*(l.cost) = 0;
int size = get_detection_layer_output_size(l) * l.batch;
int size = l.inputs * l.batch;
memset(l.delta, 0, size * sizeof(float));
for (i = 0; i < l.batch*locations; ++i) {
int classes = (l.objectness || l.background)+l.classes;
int offset = i*(classes+l.coords);
for (j = offset; j < offset+classes; ++j) {
*(l.cost) += pow(state.truth[j] - l.output[j], 2);
l.delta[j] = state.truth[j] - l.output[j];
if(l.background && j == offset) l.delta[j] *= .1;
}
for (b = 0; b < l.batch; ++b){
int index = b*l.inputs;
for (i = 0; i < locations; ++i) {
int truth_index = (b*locations + i)*(1+l.coords+l.classes);
int is_obj = state.truth[truth_index];
for (j = 0; j < l.n; ++j) {
int p_index = index + locations*l.classes + i*l.n + j;
l.delta[p_index] = l.noobject_scale*(0 - l.output[p_index]);
*(l.cost) += l.noobject_scale*pow(l.output[p_index], 2);
avg_anyobj += l.output[p_index];
}

int best_index = -1;
float best_iou = 0;
float best_rmse = 20;

if (!is_obj){
continue;
}

int class_index = index + i*l.classes;
for(j = 0; j < l.classes; ++j) {
l.delta[class_index+j] = l.class_scale * (state.truth[truth_index+1+j] - l.output[class_index+j]);
*(l.cost) += l.class_scale * pow(state.truth[truth_index+1+j] - l.output[class_index+j], 2);
if(state.truth[truth_index + 1 + j]) avg_cat += l.output[class_index+j];
avg_allcat += l.output[class_index+j];
}

box truth = float_to_box(state.truth + truth_index + 1 + l.classes);
truth.x /= l.side;
truth.y /= l.side;

box truth;
truth.x = state.truth[j+0]/7;
truth.y = state.truth[j+1]/7;
truth.w = pow(state.truth[j+2], 2);
truth.h = pow(state.truth[j+3], 2);

box out;
out.x = l.output[j+0]/7;
out.y = l.output[j+1]/7;
out.w = pow(l.output[j+2], 2);
out.h = pow(l.output[j+3], 2);

if(!(truth.w*truth.h)) continue;
float iou = box_iou(out, truth);
avg_iou += iou;
++count;

*(l.cost) += pow((1-iou), 2);
l.delta[j+0] = 4 * (state.truth[j+0] - l.output[j+0]);
l.delta[j+1] = 4 * (state.truth[j+1] - l.output[j+1]);
l.delta[j+2] = 4 * (state.truth[j+2] - l.output[j+2]);
l.delta[j+3] = 4 * (state.truth[j+3] - l.output[j+3]);
if(l.rescore){
if(l.objectness){
state.truth[offset] = iou;
l.delta[offset] = state.truth[offset] - l.output[offset];
for(j = 0; j < l.n; ++j){
int box_index = index + locations*(l.classes + l.n) + (i*l.n + j) * l.coords;
box out = float_to_box(l.output + box_index);
out.x /= l.side;
out.y /= l.side;

if (l.sqrt){
out.w = out.w*out.w;
out.h = out.h*out.h;
}

float iou = box_iou(out, truth);
//iou = 0;
float rmse = box_rmse(out, truth);
if(best_iou > 0 || iou > 0){
if(iou > best_iou){
best_iou = iou;
best_index = j;
}
}else{
if(rmse < best_rmse){
best_rmse = rmse;
best_index = j;
}
}
}
else{
for (j = offset; j < offset+classes; ++j) {
if(state.truth[j]) state.truth[j] = iou;
l.delta[j] = state.truth[j] - l.output[j];

if(l.forced){
if(truth.w*truth.h < .1){
best_index = 1;
}else{
best_index = 0;
}
}

int box_index = index + locations*(l.classes + l.n) + (i*l.n + best_index) * l.coords;
int tbox_index = truth_index + 1 + l.classes;

box out = float_to_box(l.output + box_index);
out.x /= l.side;
out.y /= l.side;
if (l.sqrt) {
out.w = out.w*out.w;
out.h = out.h*out.h;
}
float iou = box_iou(out, truth);

//printf("%d", best_index);
int p_index = index + locations*l.classes + i*l.n + best_index;
*(l.cost) -= l.noobject_scale * pow(l.output[p_index], 2);
*(l.cost) += l.object_scale * pow(1-l.output[p_index], 2);
avg_obj += l.output[p_index];
l.delta[p_index] = l.object_scale * (1.-l.output[p_index]);

if(l.rescore){
l.delta[p_index] = l.object_scale * (iou - l.output[p_index]);
}

l.delta[box_index+0] = l.coord_scale*(state.truth[tbox_index + 0] - l.output[box_index + 0]);
l.delta[box_index+1] = l.coord_scale*(state.truth[tbox_index + 1] - l.output[box_index + 1]);
l.delta[box_index+2] = l.coord_scale*(state.truth[tbox_index + 2] - l.output[box_index + 2]);
l.delta[box_index+3] = l.coord_scale*(state.truth[tbox_index + 3] - l.output[box_index + 3]);
if(l.sqrt){
l.delta[box_index+2] = l.coord_scale*(sqrt(state.truth[tbox_index + 2]) - l.output[box_index + 2]);
l.delta[box_index+3] = l.coord_scale*(sqrt(state.truth[tbox_index + 3]) - l.output[box_index + 3]);
}

*(l.cost) += pow(1-iou, 2);
avg_iou += iou;
++count;
}
if(l.softmax){
gradient_array(l.output + index + locations*l.classes, locations*l.n*(1+l.coords),
LOGISTIC, l.delta + index + locations*l.classes);
}
}
printf("Avg IOU: %f\n", avg_iou/count);
printf("Detection Avg IOU: %f, Pos Cat: %f, All Cat: %f, Pos Obj: %f, Any Obj: %f, count: %d\n", avg_iou/count, avg_cat/count, avg_allcat/(count*l.classes), avg_obj/count, avg_anyobj/(l.batch*locations*l.n), count);
}
}

void backward_detection_layer(const detection_layer l, network_state state)
{
int locations = get_detection_layer_locations(l);
int i,j;
int in_i = 0;
int out_i = 0;
for(i = 0; i < l.batch*locations; ++i){
float scale = 1;
float latent_delta = 0;
if(l.joint) scale = state.input[in_i++];
else if (l.objectness) state.delta[in_i++] += -l.delta[out_i++];
else if (l.background) state.delta[in_i++] += scale*l.delta[out_i++];
for(j = 0; j < l.classes; ++j){
latent_delta += state.input[in_i]*l.delta[out_i];
state.delta[in_i++] += scale*l.delta[out_i++];
}

if (l.objectness) {

}else if (l.background) gradient_array(l.output + out_i, l.coords, LOGISTIC, l.delta + out_i);
for (j = 0; j < l.coords; ++j){
state.delta[in_i++] += l.delta[out_i++];
}
if(l.joint) state.delta[in_i-l.coords-l.classes-l.joint] += latent_delta;
}
axpy_cpu(l.batch*l.inputs, 1, l.delta, 1, state.delta, 1);
}

#ifdef GPU

void forward_detection_layer_gpu(const detection_layer l, network_state state)
{
int outputs = get_detection_layer_output_size(l);
if(!state.train){
copy_ongpu(l.batch*l.inputs, state.input, 1, l.output_gpu, 1);
return;
}

float *in_cpu = calloc(l.batch*l.inputs, sizeof(float));
float *truth_cpu = 0;
if(state.truth){
truth_cpu = calloc(l.batch*outputs, sizeof(float));
cuda_pull_array(state.truth, truth_cpu, l.batch*outputs);
int num_truth = l.batch*l.side*l.side*(1+l.coords+l.classes);
truth_cpu = calloc(num_truth, sizeof(float));
cuda_pull_array(state.truth, truth_cpu, num_truth);
}
cuda_pull_array(state.input, in_cpu, l.batch*l.inputs);
network_state cpu_state;
cpu_state.train = state.train;
cpu_state.truth = truth_cpu;
cpu_state.input = in_cpu;
forward_detection_layer(l, cpu_state);
cuda_push_array(l.output_gpu, l.output, l.batch*outputs);
cuda_push_array(l.delta_gpu, l.delta, l.batch*outputs);
cuda_push_array(l.output_gpu, l.output, l.batch*l.outputs);
cuda_push_array(l.delta_gpu, l.delta, l.batch*l.inputs);
free(cpu_state.input);
if(cpu_state.truth) free(cpu_state.truth);
}

void backward_detection_layer_gpu(detection_layer l, network_state state)
{
int outputs = get_detection_layer_output_size(l);

float *in_cpu = calloc(l.batch*l.inputs, sizeof(float));
float *delta_cpu = calloc(l.batch*l.inputs, sizeof(float));
float *truth_cpu = 0;
if(state.truth){
truth_cpu = calloc(l.batch*outputs, sizeof(float));
cuda_pull_array(state.truth, truth_cpu, l.batch*outputs);
}
network_state cpu_state;
cpu_state.train = state.train;
cpu_state.input = in_cpu;
cpu_state.truth = truth_cpu;
cpu_state.delta = delta_cpu;

cuda_pull_array(state.input, in_cpu, l.batch*l.inputs);
cuda_pull_array(state.delta, delta_cpu, l.batch*l.inputs);
cuda_pull_array(l.delta_gpu, l.delta, l.batch*outputs);
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);
axpy_ongpu(l.batch*l.inputs, 1, l.delta_gpu, 1, state.delta, 1);
//copy_ongpu(l.batch*l.inputs, l.delta_gpu, 1, state.delta, 1);
}
#endif

8 src/detection_layer.h
View file
@@ -1,16 +1,14 @@
#ifndef DETECTION_LAYER_H
#define DETECTION_LAYER_H
#ifndef REGION_LAYER_H
#define REGION_LAYER_H

#include "params.h"
#include "layer.h"

typedef layer detection_layer;

detection_layer make_detection_layer(int batch, int inputs, int classes, int coords, int joint, int rescore, int background, int objectness);
detection_layer make_detection_layer(int batch, int inputs, int n, int size, int classes, int coords, int rescore);
void forward_detection_layer(const detection_layer l, network_state state);
void backward_detection_layer(const detection_layer l, network_state state);
int get_detection_layer_output_size(detection_layer l);
int get_detection_layer_locations(detection_layer l);

#ifdef GPU
void forward_detection_layer_gpu(const detection_layer l, network_state state);
4 src/layer.h
View file
@@ -15,7 +15,6 @@ typedef enum {
ROUTE,
COST,
NORMALIZATION,
REGION,
AVGPOOL
} LAYER_TYPE;

@@ -30,9 +29,6 @@ typedef struct {
int batch_normalize;
int batch;
int forced;
int object_logistic;
int class_logistic;
int coord_logistic;
int inputs;
int outputs;
int truths;
11 src/network.c
View file
@@ -11,7 +11,6 @@
#include "convolutional_layer.h"
#include "deconvolutional_layer.h"
#include "detection_layer.h"
#include "region_layer.h"
#include "normalization_layer.h"
#include "maxpool_layer.h"
#include "avgpool_layer.h"
@@ -72,8 +71,6 @@ char *get_layer_string(LAYER_TYPE a)
return "softmax";
case DETECTION:
return "detection";
case REGION:
return "region";
case DROPOUT:
return "dropout";
case CROP:
@@ -119,8 +116,6 @@ void forward_network(network net, network_state state)
forward_normalization_layer(l, state);
} else if(l.type == DETECTION){
forward_detection_layer(l, state);
} else if(l.type == REGION){
forward_region_layer(l, state);
} else if(l.type == CONNECTED){
forward_connected_layer(l, state);
} else if(l.type == CROP){
@@ -180,10 +175,6 @@ float get_network_cost(network net)
sum += net.layers[i].cost[0];
++count;
}
if(net.layers[i].type == REGION){
sum += net.layers[i].cost[0];
++count;
}
}
return sum/count;
}
@@ -224,8 +215,6 @@ void backward_network(network net, network_state state)
backward_dropout_layer(l, state);
} else if(l.type == DETECTION){
backward_detection_layer(l, state);
} else if(l.type == REGION){
backward_region_layer(l, state);
} else if(l.type == SOFTMAX){
if(i != 0) backward_softmax_layer(l, state);
} else if(l.type == CONNECTED){
1 src/network.h
View file
@@ -89,7 +89,6 @@ int resize_network(network *net, int w, int h);
void set_batch_network(network *net, int b);
int get_network_input_size(network net);
float get_network_cost(network net);
detection_layer get_network_detection_layer(network net);

int get_network_nuisance(network net);
int get_network_background(network net);
7 src/network_kernels.cu
View file
@@ -13,7 +13,6 @@ extern "C" {
#include "crop_layer.h"
#include "connected_layer.h"
#include "detection_layer.h"
#include "region_layer.h"
#include "convolutional_layer.h"
#include "deconvolutional_layer.h"
#include "maxpool_layer.h"
@@ -44,8 +43,6 @@ void forward_network_gpu(network net, network_state state)
forward_deconvolutional_layer_gpu(l, state);
} else if(l.type == DETECTION){
forward_detection_layer_gpu(l, state);
} else if(l.type == REGION){
forward_region_layer_gpu(l, state);
} else if(l.type == CONNECTED){
forward_connected_layer_gpu(l, state);
} else if(l.type == CROP){
@@ -96,8 +93,6 @@ void backward_network_gpu(network net, network_state state)
backward_dropout_layer_gpu(l, state);
} else if(l.type == DETECTION){
backward_detection_layer_gpu(l, state);
} else if(l.type == REGION){
backward_region_layer_gpu(l, state);
} else if(l.type == NORMALIZATION){
backward_normalization_layer_gpu(l, state);
} else if(l.type == SOFTMAX){
@@ -134,7 +129,7 @@ float train_network_datum_gpu(network net, float *x, float *y)
network_state state;
int x_size = get_network_input_size(net)*net.batch;
int y_size = get_network_output_size(net)*net.batch;
if(net.layers[net.n-1].type == REGION) y_size = net.layers[net.n-1].truths*net.batch;
if(net.layers[net.n-1].type == DETECTION) y_size = net.layers[net.n-1].truths*net.batch;
if(!*net.input_gpu){
*net.input_gpu = cuda_make_array(x, x_size);
*net.truth_gpu = cuda_make_array(y, y_size);
607 src/old.c
View file

This file was deleted.

28 src/parser.c
View file
@@ -14,7 +14,6 @@
#include "softmax_layer.h"
#include "dropout_layer.h"
#include "detection_layer.h"
#include "region_layer.h"
#include "avgpool_layer.h"
#include "route_layer.h"
#include "list.h"
@@ -38,7 +37,6 @@ int is_normalization(section *s);
int is_crop(section *s);
int is_cost(section *s);
int is_detection(section *s);
int is_region(section *s);
int is_route(section *s);
list *read_cfg(char *filename);

@@ -164,39 +162,23 @@ softmax_layer parse_softmax(list *options, size_params params)
}

detection_layer parse_detection(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 1);
int classes = option_find_int(options, "classes", 1);
int rescore = option_find_int(options, "rescore", 0);
int joint = option_find_int(options, "joint", 0);
int objectness = option_find_int(options, "objectness", 0);
int background = option_find_int(options, "background", 0);
detection_layer layer = make_detection_layer(params.batch, params.inputs, classes, coords, joint, rescore, background, objectness);
return layer;
}

region_layer parse_region(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 1);
int classes = option_find_int(options, "classes", 1);
int rescore = option_find_int(options, "rescore", 0);
int num = option_find_int(options, "num", 1);
int side = option_find_int(options, "side", 7);
region_layer layer = make_region_layer(params.batch, params.inputs, num, side, classes, coords, rescore);
detection_layer layer = make_detection_layer(params.batch, params.inputs, num, side, classes, coords, rescore);

layer.softmax = option_find_int(options, "softmax", 0);
layer.sqrt = option_find_int(options, "sqrt", 0);

layer.object_logistic = option_find_int(options, "object_logistic", 0);
layer.class_logistic = option_find_int(options, "class_logistic", 0);
layer.coord_logistic = option_find_int(options, "coord_logistic", 0);

layer.coord_scale = option_find_float(options, "coord_scale", 1);
layer.forced = option_find_int(options, "forced", 0);
layer.object_scale = option_find_float(options, "object_scale", 1);
layer.noobject_scale = option_find_float(options, "noobject_scale", 1);
layer.class_scale = option_find_float(options, "class_scale", 1);
layer.jitter = option_find_float(options, "jitter", .1);
layer.jitter = option_find_float(options, "jitter", .2);
return layer;
}

@@ -430,8 +412,6 @@ network parse_network_cfg(char *filename)
l = parse_cost(options, params);
}else if(is_detection(s)){
l = parse_detection(options, params);
}else if(is_region(s)){
l = parse_region(options, params);
}else if(is_softmax(s)){
l = parse_softmax(options, params);
}else if(is_normalization(s)){
@@ -485,10 +465,6 @@ int is_detection(section *s)
{
return (strcmp(s->type, "[detection]")==0);
}
int is_region(section *s)
{
return (strcmp(s->type, "[region]")==0);
}
int is_deconvolutional(section *s)
{
return (strcmp(s->type, "[deconv]")==0
259 src/region_layer.c
View file

This file was deleted.

18 src/region_layer.h
View file

This file was deleted.

460 src/swag.c
View file

This file was deleted.

356 src/yolo.c
View file

Large diffs are not rendered by default.

15 src/swag_kernels.cu → src/yolo_kernels.cu
View file
@@ -1,6 +1,5 @@
extern "C" {
#include "network.h"
#include "region_layer.h"
#include "detection_layer.h"
#include "cost_layer.h"
#include "utils.h"
@@ -13,16 +12,16 @@ extern "C" {
#include "opencv2/highgui/highgui.hpp"
#include "opencv2/imgproc/imgproc.hpp"
extern "C" image ipl_to_image(IplImage* src);
extern "C" void convert_swag_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
extern "C" void draw_swag(image im, int num, float thresh, box *boxes, float **probs, char *label);
extern "C" void convert_yolo_detections(float *predictions, int classes, int num, int square, int side, int w, int h, float thresh, float **probs, box *boxes, int only_objectness);
extern "C" void draw_yolo(image im, int num, float thresh, box *boxes, float **probs, char *label);

extern "C" void demo_swag(char *cfgfile, char *weightfile, float thresh)
extern "C" void demo_yolo(char *cfgfile, char *weightfile, float thresh)
{
network net = parse_network_cfg(cfgfile);
if(weightfile){
load_weights(&net, weightfile);
}
region_layer l = net.layers[net.n-1];
detection_layer l = net.layers[net.n-1];
cv::VideoCapture cap(0);

set_batch_network(&net, 1);
@@ -43,19 +42,19 @@ extern "C" void demo_swag(char *cfgfile, char *weightfile, float thresh)
image sized = resize_image(im, net.w, net.h);
float *X = sized.data;
float *predictions = network_predict(net, X);
convert_swag_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
convert_yolo_detections(predictions, l.classes, l.n, l.sqrt, l.side, 1, 1, thresh, probs, boxes, 0);
if (nms > 0) do_nms(boxes, probs, l.side*l.side*l.n, l.classes, nms);
printf("\033[2J");
printf("\033[1;1H");
printf("\nObjects:\n\n");
draw_swag(im, l.side*l.side*l.n, thresh, boxes, probs, "predictions");
draw_yolo(im, l.side*l.side*l.n, thresh, boxes, probs, "predictions");

free_image(im);
free_image(sized);
cvWaitKey(1);
}
}
#else
extern "C" void demo_swag(char *cfgfile, char *weightfile, float thresh){}
extern "C" void demo_yolo(char *cfgfile, char *weightfile, float thresh){}
#endif