From b8e6e80c6d411d05a9e09f1e3676eb9a7f3ea0e8 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Fri, 03 Aug 2018 11:35:03 +0000
Subject: [PATCH] Added spatial Yolo v3 yolov3-spp.cfg
---
src/yolo_layer.c | 125 +++++++++++++++++++++++++++++------------
1 files changed, 87 insertions(+), 38 deletions(-)
diff --git a/src/yolo_layer.c b/src/yolo_layer.c
index c8e2ff5..f0bc073 100644
--- a/src/yolo_layer.c
+++ b/src/yolo_layer.c
@@ -10,7 +10,7 @@
#include <string.h>
#include <stdlib.h>
-layer make_yolo_layer(int batch, int w, int h, int n, int total, int *mask, int classes)
+layer make_yolo_layer(int batch, int w, int h, int n, int total, int *mask, int classes, int max_boxes)
{
int i;
layer l = {0};
@@ -38,7 +38,8 @@
l.bias_updates = calloc(n*2, sizeof(float));
l.outputs = h*w*n*(classes + 4 + 1);
l.inputs = l.outputs;
- l.truths = 90*(4 + 1);
+ l.max_boxes = max_boxes;
+ l.truths = l.max_boxes*(4 + 1); // 90*(4 + 1);
l.delta = calloc(batch*l.outputs, sizeof(float));
l.output = calloc(batch*l.outputs, sizeof(float));
for(i = 0; i < total*2; ++i){
@@ -54,7 +55,7 @@
l.delta_gpu = cuda_make_array(l.delta, batch*l.outputs);
#endif
- fprintf(stderr, "detection\n");
+ fprintf(stderr, "yolo\n");
srand(0);
return l;
@@ -108,17 +109,40 @@
}
-void delta_yolo_class(float *output, float *delta, int index, int class, int classes, int stride, float *avg_cat)
+void delta_yolo_class(float *output, float *delta, int index, int class_id, int classes, int stride, float *avg_cat, int focal_loss)
{
int n;
- if (delta[index]){
- delta[index + stride*class] = 1 - output[index + stride*class];
- if(avg_cat) *avg_cat += output[index + stride*class];
+ if (delta[index + stride*class_id]){
+ delta[index + stride*class_id] = 1 - output[index + stride*class_id];
+ if(avg_cat) *avg_cat += output[index + stride*class_id];
return;
}
- for(n = 0; n < classes; ++n){
- delta[index + stride*n] = ((n == class)?1 : 0) - output[index + stride*n];
- if(n == class && avg_cat) *avg_cat += output[index + stride*n];
+ // Focal loss
+ if (focal_loss) {
+ // Focal Loss
+ float alpha = 0.5; // 0.25 or 0.5
+ //float gamma = 2; // hardcoded in many places of the grad-formula
+
+ int ti = index + stride*class_id;
+ float pt = output[ti] + 0.000000000000001F;
+ // http://fooplot.com/#W3sidHlwZSI6MCwiZXEiOiItKDEteCkqKDIqeCpsb2coeCkreC0xKSIsImNvbG9yIjoiIzAwMDAwMCJ9LHsidHlwZSI6MTAwMH1d
+ float grad = -(1 - pt) * (2 * pt*logf(pt) + pt - 1); // http://blog.csdn.net/linmingan/article/details/77885832
+ //float grad = (1 - pt) * (2 * pt*logf(pt) + pt - 1); // https://github.com/unsky/focal-loss
+
+ for (n = 0; n < classes; ++n) {
+ delta[index + stride*n] = (((n == class_id) ? 1 : 0) - output[index + stride*n]);
+
+ delta[index + stride*n] *= alpha*grad;
+
+ if (n == class_id) *avg_cat += output[index + stride*n];
+ }
+ }
+ else {
+ // default
+ for (n = 0; n < classes; ++n) {
+ delta[index + stride*n] = ((n == class_id) ? 1 : 0) - output[index + stride*n];
+ if (n == class_id && avg_cat) *avg_cat += output[index + stride*n];
+ }
}
}
@@ -131,12 +155,12 @@
static box float_to_box_stride(float *f, int stride)
{
- box b = { 0 };
- b.x = f[0];
- b.y = f[1 * stride];
- b.w = f[2 * stride];
- b.h = f[3 * stride];
- return b;
+ box b = { 0 };
+ b.x = f[0];
+ b.y = f[1 * stride];
+ b.w = f[2 * stride];
+ b.h = f[3 * stride];
+ return b;
}
void forward_yolo_layer(const layer l, network_state state)
@@ -176,6 +200,12 @@
int best_t = 0;
for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box_stride(state.truth + t*(4 + 1) + b*l.truths, 1);
+ int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
+ if (class_id >= l.classes) {
+ printf(" Warning: in txt-labels class_id=%d >= classes=%d in cfg-file. In txt-labels class_id should be [from 0 to %d] \n", class_id, l.classes, l.classes - 1);
+ getchar();
+ continue; // if label contains class_id more than number of classes in the cfg-file
+ }
if(!truth.x) break;
float iou = box_iou(pred, truth);
if (iou > best_iou) {
@@ -192,10 +222,10 @@
if (best_iou > l.truth_thresh) {
l.delta[obj_index] = 1 - l.output[obj_index];
- int class = state.truth[best_t*(4 + 1) + b*l.truths + 4];
- if (l.map) class = l.map[class];
+ int class_id = state.truth[best_t*(4 + 1) + b*l.truths + 4];
+ if (l.map) class_id = l.map[class_id];
int class_index = entry_index(l, b, n*l.w*l.h + j*l.w + i, 4 + 1);
- delta_yolo_class(l.output, l.delta, class_index, class, l.classes, l.w*l.h, 0);
+ delta_yolo_class(l.output, l.delta, class_index, class_id, l.classes, l.w*l.h, 0, l.focal_loss);
box truth = float_to_box_stride(state.truth + best_t*(4 + 1) + b*l.truths, 1);
delta_yolo_box(truth, l.output, l.biases, l.mask[n], box_index, i, j, l.w, l.h, state.net.w, state.net.h, l.delta, (2-truth.w*truth.h), l.w*l.h);
}
@@ -204,6 +234,8 @@
}
for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box_stride(state.truth + t*(4 + 1) + b*l.truths, 1);
+ int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
+ if (class_id >= l.classes) continue; // if label contains class_id more than number of classes in the cfg-file
if(!truth.x) break;
float best_iou = 0;
@@ -232,10 +264,10 @@
avg_obj += l.output[obj_index];
l.delta[obj_index] = 1 - l.output[obj_index];
- int class = state.truth[t*(4 + 1) + b*l.truths + 4];
- if (l.map) class = l.map[class];
+ int class_id = state.truth[t*(4 + 1) + b*l.truths + 4];
+ if (l.map) class_id = l.map[class_id];
int class_index = entry_index(l, b, mask_n*l.w*l.h + j*l.w + i, 4 + 1);
- delta_yolo_class(l.output, l.delta, class_index, class, l.classes, l.w*l.h, &avg_cat);
+ delta_yolo_class(l.output, l.delta, class_index, class_id, l.classes, l.w*l.h, &avg_cat, l.focal_loss);
++count;
++class_count;
@@ -259,20 +291,20 @@
int i;
int new_w=0;
int new_h=0;
- if (letter) {
- if (((float)netw / w) < ((float)neth / h)) {
- new_w = netw;
- new_h = (h * netw) / w;
- }
- else {
- new_h = neth;
- new_w = (w * neth) / h;
- }
- }
- else {
- new_w = netw;
- new_h = neth;
- }
+ if (letter) {
+ if (((float)netw / w) < ((float)neth / h)) {
+ new_w = netw;
+ new_h = (h * netw) / w;
+ }
+ else {
+ new_h = neth;
+ new_w = (w * neth) / h;
+ }
+ }
+ else {
+ new_w = netw;
+ new_h = neth;
+ }
for (i = 0; i < n; ++i){
box b = dets[i].bbox;
b.x = (b.x - (netw - new_w)/2./netw) / ((float)new_w/netw);
@@ -378,9 +410,26 @@
return;
}
- cuda_pull_array(l.output_gpu, state.input, l.batch*l.inputs);
- forward_yolo_layer(l, state);
+ //cuda_pull_array(l.output_gpu, state.input, l.batch*l.inputs);
+ float *in_cpu = calloc(l.batch*l.inputs, sizeof(float));
+ cuda_pull_array(l.output_gpu, in_cpu, l.batch*l.inputs);
+ float *truth_cpu = 0;
+ if (state.truth) {
+ int num_truth = l.batch*l.truths;
+ truth_cpu = calloc(num_truth, sizeof(float));
+ cuda_pull_array(state.truth, truth_cpu, num_truth);
+ }
+ network_state cpu_state = state;
+ cpu_state.net = state.net;
+ cpu_state.index = state.index;
+ cpu_state.train = state.train;
+ cpu_state.truth = truth_cpu;
+ cpu_state.input = in_cpu;
+ forward_yolo_layer(l, cpu_state);
+ //forward_yolo_layer(l, state);
cuda_push_array(l.delta_gpu, l.delta, l.batch*l.outputs);
+ free(in_cpu);
+ if (cpu_state.truth) free(cpu_state.truth);
}
void backward_yolo_layer_gpu(const layer l, network_state state)
--
Gitblit v1.10.0