From 408bde78ffd5c9512ee09adcd2faba21c875d676 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Fri, 13 Apr 2018 14:32:10 +0000
Subject: [PATCH] Fixed darknet.py for Linux
---
src/detection_layer.c | 647 ++++++++++++++++++++++------------------------------------
1 files changed, 245 insertions(+), 402 deletions(-)
diff --git a/src/detection_layer.c b/src/detection_layer.c
index af137c6..0a1c107 100644
--- a/src/detection_layer.c
+++ b/src/detection_layer.c
@@ -2,44 +2,43 @@
#include "activations.h"
#include "softmax_layer.h"
#include "blas.h"
+#include "box.h"
#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.rescore+l.background);
-}
-
-int get_detection_layer_output_size(detection_layer l)
-{
- return get_detection_layer_locations(l)*(l.background + l.classes + l.coords);
-}
-
-detection_layer make_detection_layer(int batch, int inputs, int classes, int coords, int rescore, int background, int nuisance)
+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.nuisance = nuisance;
+ l.side = side;
+ l.w = side;
+ l.h = side;
+ assert(side*side*((1 + l.coords)*l.n + l.classes) == inputs);
l.cost = calloc(1, sizeof(float));
- l.does_cost=1;
- l.background = background;
- 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(0, batch*outputs);
- l.delta_gpu = cuda_make_array(0, 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));
+
+ l.forward = forward_detection_layer;
+ l.backward = backward_detection_layer;
+#ifdef GPU
+ l.forward_gpu = forward_detection_layer_gpu;
+ l.backward_gpu = backward_detection_layer_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);
@@ -47,376 +46,207 @@
return l;
}
-void dark_zone(detection_layer l, int class, int start, network_state state)
-{
- int index = start+l.background+class;
- int size = l.classes+l.coords+l.background;
- int location = (index%(7*7*size)) / size ;
- int r = location / 7;
- int c = location % 7;
- int dr, dc;
- for(dr = -1; dr <= 1; ++dr){
- for(dc = -1; dc <= 1; ++dc){
- if(!(dr || dc)) continue;
- if((r + dr) > 6 || (r + dr) < 0) continue;
- if((c + dc) > 6 || (c + dc) < 0) continue;
- int di = (dr*7 + dc) * size;
- if(state.truth[index+di]) continue;
- l.output[index + di] = 0;
- //if(!state.truth[start+di]) continue;
- //l.output[start + di] = 1;
- }
- }
-}
-
-typedef struct{
- float dx, dy, dw, dh;
-} dbox;
-
-dbox derivative(box a, box b)
-{
- dbox d;
- d.dx = 0;
- d.dw = 0;
- float l1 = a.x - a.w/2;
- float l2 = b.x - b.w/2;
- if (l1 > l2){
- d.dx -= 1;
- d.dw += .5;
- }
- float r1 = a.x + a.w/2;
- float r2 = b.x + b.w/2;
- if(r1 < r2){
- d.dx += 1;
- d.dw += .5;
- }
- if (l1 > r2) {
- d.dx = -1;
- d.dw = 0;
- }
- if (r1 < l2){
- d.dx = 1;
- d.dw = 0;
- }
-
- d.dy = 0;
- d.dh = 0;
- float t1 = a.y - a.h/2;
- float t2 = b.y - b.h/2;
- if (t1 > t2){
- d.dy -= 1;
- d.dh += .5;
- }
- float b1 = a.y + a.h/2;
- float b2 = b.y + b.h/2;
- if(b1 < b2){
- d.dy += 1;
- d.dh += .5;
- }
- if (t1 > b2) {
- d.dy = -1;
- d.dh = 0;
- }
- if (b1 < t2){
- d.dy = 1;
- d.dh = 0;
- }
- return d;
-}
-
-float overlap(float x1, float w1, float x2, float w2)
-{
- float l1 = x1 - w1/2;
- float l2 = x2 - w2/2;
- float left = l1 > l2 ? l1 : l2;
- float r1 = x1 + w1/2;
- float r2 = x2 + w2/2;
- float right = r1 < r2 ? r1 : r2;
- return right - left;
-}
-
-float box_intersection(box a, box b)
-{
- float w = overlap(a.x, a.w, b.x, b.w);
- float h = overlap(a.y, a.h, b.y, b.h);
- if(w < 0 || h < 0) return 0;
- float area = w*h;
- return area;
-}
-
-float box_union(box a, box b)
-{
- float i = box_intersection(a, b);
- float u = a.w*a.h + b.w*b.h - i;
- return u;
-}
-
-float box_iou(box a, box b)
-{
- return box_intersection(a, b)/box_union(a, b);
-}
-
-dbox dintersect(box a, box b)
-{
- float w = overlap(a.x, a.w, b.x, b.w);
- float h = overlap(a.y, a.h, b.y, b.h);
- dbox dover = derivative(a, b);
- dbox di;
-
- di.dw = dover.dw*h;
- di.dx = dover.dx*h;
- di.dh = dover.dh*w;
- di.dy = dover.dy*w;
-
- return di;
-}
-
-dbox dunion(box a, box b)
-{
- dbox du;
-
- dbox di = dintersect(a, b);
- du.dw = a.h - di.dw;
- du.dh = a.w - di.dh;
- du.dx = -di.dx;
- du.dy = -di.dy;
-
- return du;
-}
-
-dbox diou(box a, box b);
-
-void test_dunion()
-{
- box a = {0, 0, 1, 1};
- box dxa= {0+.0001, 0, 1, 1};
- box dya= {0, 0+.0001, 1, 1};
- box dwa= {0, 0, 1+.0001, 1};
- box dha= {0, 0, 1, 1+.0001};
-
- box b = {.5, .5, .2, .2};
- dbox di = dunion(a,b);
- printf("Union: %f %f %f %f\n", di.dx, di.dy, di.dw, di.dh);
- float inter = box_union(a, b);
- float xinter = box_union(dxa, b);
- float yinter = box_union(dya, b);
- float winter = box_union(dwa, b);
- float hinter = box_union(dha, b);
- xinter = (xinter - inter)/(.0001);
- yinter = (yinter - inter)/(.0001);
- winter = (winter - inter)/(.0001);
- hinter = (hinter - inter)/(.0001);
- printf("Union Manual %f %f %f %f\n", xinter, yinter, winter, hinter);
-}
-void test_dintersect()
-{
- box a = {0, 0, 1, 1};
- box dxa= {0+.0001, 0, 1, 1};
- box dya= {0, 0+.0001, 1, 1};
- box dwa= {0, 0, 1+.0001, 1};
- box dha= {0, 0, 1, 1+.0001};
-
- box b = {.5, .5, .2, .2};
- dbox di = dintersect(a,b);
- printf("Inter: %f %f %f %f\n", di.dx, di.dy, di.dw, di.dh);
- float inter = box_intersection(a, b);
- float xinter = box_intersection(dxa, b);
- float yinter = box_intersection(dya, b);
- float winter = box_intersection(dwa, b);
- float hinter = box_intersection(dha, b);
- xinter = (xinter - inter)/(.0001);
- yinter = (yinter - inter)/(.0001);
- winter = (winter - inter)/(.0001);
- hinter = (hinter - inter)/(.0001);
- printf("Inter Manual %f %f %f %f\n", xinter, yinter, winter, hinter);
-}
-
-void test_box()
-{
- test_dintersect();
- test_dunion();
- box a = {0, 0, 1, 1};
- box dxa= {0+.00001, 0, 1, 1};
- box dya= {0, 0+.00001, 1, 1};
- box dwa= {0, 0, 1+.00001, 1};
- box dha= {0, 0, 1, 1+.00001};
-
- box b = {.5, 0, .2, .2};
-
- float iou = box_iou(a,b);
- iou = (1-iou)*(1-iou);
- printf("%f\n", iou);
- dbox d = diou(a, b);
- printf("%f %f %f %f\n", d.dx, d.dy, d.dw, d.dh);
-
- float xiou = box_iou(dxa, b);
- float yiou = box_iou(dya, b);
- float wiou = box_iou(dwa, b);
- float hiou = box_iou(dha, b);
- xiou = ((1-xiou)*(1-xiou) - iou)/(.00001);
- yiou = ((1-yiou)*(1-yiou) - iou)/(.00001);
- wiou = ((1-wiou)*(1-wiou) - iou)/(.00001);
- hiou = ((1-hiou)*(1-hiou) - iou)/(.00001);
- printf("manual %f %f %f %f\n", xiou, yiou, wiou, hiou);
- /*
-
- while(count++ < 300){
- dbox d = diou(a, b);
- printf("%f %f %f %f\n", a.x, a.y, a.w, a.h);
- a.x += .1*d.dx;
- a.w += .1*d.dw;
- a.y += .1*d.dy;
- a.h += .1*d.dh;
- printf("inter: %f\n", box_intersection(a, b));
- printf("union: %f\n", box_union(a, b));
- printf("IOU: %f\n", box_iou(a, b));
- if(d.dx==0 && d.dw==0 && d.dy==0 && d.dh==0) {
- printf("break!!!\n");
- break;
- }
- }
- */
-}
-
-dbox diou(box a, box b)
-{
- float u = box_union(a,b);
- float i = box_intersection(a,b);
- dbox di = dintersect(a,b);
- dbox du = dunion(a,b);
- dbox dd = {0,0,0,0};
-
- if(i <= 0 || 1) {
- dd.dx = b.x - a.x;
- dd.dy = b.y - a.y;
- dd.dw = b.w - a.w;
- dd.dh = b.h - a.h;
- return dd;
- }
-
- dd.dx = 2*pow((1-(i/u)),1)*(di.dx*u - du.dx*i)/(u*u);
- dd.dy = 2*pow((1-(i/u)),1)*(di.dy*u - du.dy*i)/(u*u);
- dd.dw = 2*pow((1-(i/u)),1)*(di.dw*u - du.dw*i)/(u*u);
- dd.dh = 2*pow((1-(i/u)),1)*(di.dh*u - du.dh*i)/(u*u);
- return dd;
-}
-
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.classes + 2]);
- float scale = 1;
- if(l.rescore) scale = state.input[in_i++];
- else if(l.nuisance){
- 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.nuisance){
-
- }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));
+ //if(l.reorg) reorg(l.output, l.w*l.h, size*l.n, l.batch, 1);
+ 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(l.output + index + offset, l.classes, 1,
+ l.output + index + offset, 1);
+ }
}
}
- 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.nuisance+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];
+ 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;
+
+ 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;
+ }
+ }
+ }
+
+ if(l.forced){
+ if(truth.w*truth.h < .1){
+ best_index = 1;
+ }else{
+ best_index = 0;
+ }
+ }
+ if(l.random && *(state.net.seen) < 64000){
+ best_index = rand()%l.n;
+ }
+
+ 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;
}
+ }
- 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;
- dbox delta = diou(out, truth);
-
- l.delta[j+0] = 10 * delta.dx/7;
- l.delta[j+1] = 10 * delta.dy/7;
- l.delta[j+2] = 10 * delta.dw * 2 * sqrt(out.w);
- l.delta[j+3] = 10 * delta.dh * 2 * sqrt(out.h);
-
-
- *(l.cost) += pow((1-iou), 2);
- if(0){
- l.delta[j+0] = (state.truth[j+0] - l.output[j+0]);
- l.delta[j+1] = (state.truth[j+1] - l.output[j+1]);
- l.delta[j+2] = (state.truth[j+2] - l.output[j+2]);
- l.delta[j+3] = (state.truth[j+3] - l.output[j+3]);
- }else{
- l.delta[j+0] = 4 * (state.truth[j+0] - l.output[j+0]) / 7;
- l.delta[j+1] = 4 * (state.truth[j+1] - l.output[j+1]) / 7;
- 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(0){
- 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(0){
+ float *costs = calloc(l.batch*locations*l.n, sizeof(float));
+ for (b = 0; b < l.batch; ++b) {
+ int index = b*l.inputs;
+ for (i = 0; i < locations; ++i) {
+ for (j = 0; j < l.n; ++j) {
+ int p_index = index + locations*l.classes + i*l.n + j;
+ costs[b*locations*l.n + i*l.n + j] = l.delta[p_index]*l.delta[p_index];
+ }
}
}
-
- /*
- */
+ int indexes[100];
+ top_k(costs, l.batch*locations*l.n, 100, indexes);
+ float cutoff = costs[indexes[99]];
+ for (b = 0; b < l.batch; ++b) {
+ int index = b*l.inputs;
+ for (i = 0; i < locations; ++i) {
+ for (j = 0; j < l.n; ++j) {
+ int p_index = index + locations*l.classes + i*l.n + j;
+ if (l.delta[p_index]*l.delta[p_index] < cutoff) l.delta[p_index] = 0;
+ }
+ }
+ }
+ free(costs);
}
- printf("Avg IOU: %f\n", avg_iou/count);
+
+
+ *(l.cost) = pow(mag_array(l.delta, l.outputs * l.batch), 2);
+
+
+ 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);
+ //if(l.reorg) reorg(l.delta, l.w*l.h, size*l.n, l.batch, 0);
}
}
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.rescore) scale = state.input[in_i++];
- else if (l.nuisance) 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++];
- }
+ axpy_cpu(l.batch*l.inputs, 1, l.delta, 1, state.delta, 1);
+}
- if (l.nuisance) {
-
- }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++];
+void get_detection_boxes(layer l, int w, int h, float thresh, float **probs, box *boxes, int only_objectness)
+{
+ int i,j,n;
+ float *predictions = l.output;
+ //int per_cell = 5*num+classes;
+ for (i = 0; i < l.side*l.side; ++i){
+ int row = i / l.side;
+ int col = i % l.side;
+ for(n = 0; n < l.n; ++n){
+ int index = i*l.n + n;
+ int p_index = l.side*l.side*l.classes + i*l.n + n;
+ float scale = predictions[p_index];
+ int box_index = l.side*l.side*(l.classes + l.n) + (i*l.n + n)*4;
+ boxes[index].x = (predictions[box_index + 0] + col) / l.side * w;
+ boxes[index].y = (predictions[box_index + 1] + row) / l.side * h;
+ boxes[index].w = pow(predictions[box_index + 2], (l.sqrt?2:1)) * w;
+ boxes[index].h = pow(predictions[box_index + 3], (l.sqrt?2:1)) * h;
+ for(j = 0; j < l.classes; ++j){
+ int class_index = i*l.classes;
+ float prob = scale*predictions[class_index+j];
+ probs[index][j] = (prob > thresh) ? prob : 0;
+ }
+ if(only_objectness){
+ probs[index][0] = scale;
+ }
}
- if(l.rescore) state.delta[in_i-l.coords-l.classes-l.rescore-l.background] = latent_delta;
}
}
@@ -424,49 +254,62 @@
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;
+ network_state cpu_state = 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(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);
-
- 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
+void get_detection_detections(layer l, int w, int h, float thresh, detection *dets)
+{
+ int i, j, n;
+ float *predictions = l.output;
+ //int per_cell = 5*num+classes;
+ for (i = 0; i < l.side*l.side; ++i) {
+ int row = i / l.side;
+ int col = i % l.side;
+ for (n = 0; n < l.n; ++n) {
+ int index = i*l.n + n;
+ int p_index = l.side*l.side*l.classes + i*l.n + n;
+ float scale = predictions[p_index];
+ int box_index = l.side*l.side*(l.classes + l.n) + (i*l.n + n) * 4;
+ box b;
+ b.x = (predictions[box_index + 0] + col) / l.side * w;
+ b.y = (predictions[box_index + 1] + row) / l.side * h;
+ b.w = pow(predictions[box_index + 2], (l.sqrt ? 2 : 1)) * w;
+ b.h = pow(predictions[box_index + 3], (l.sqrt ? 2 : 1)) * h;
+ dets[index].bbox = b;
+ dets[index].objectness = scale;
+ for (j = 0; j < l.classes; ++j) {
+ int class_index = i*l.classes;
+ float prob = scale*predictions[class_index + j];
+ dets[index].prob[j] = (prob > thresh) ? prob : 0;
+ }
+ }
+ }
+}
\ No newline at end of file
--
Gitblit v1.10.0