From 5b6be00d4b1ffd671c20c4c72d2239c924eaa3d4 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Thu, 23 Aug 2018 12:28:34 +0000
Subject: [PATCH] Added yolov3-tiny_xnor.cfg
---
src/region_layer.c | 222 ++++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 185 insertions(+), 37 deletions(-)
diff --git a/src/region_layer.c b/src/region_layer.c
index 7772bc3..ada5f8e 100644
--- a/src/region_layer.c
+++ b/src/region_layer.c
@@ -11,7 +11,7 @@
#define DOABS 1
-region_layer make_region_layer(int batch, int w, int h, int n, int classes, int coords)
+region_layer make_region_layer(int batch, int w, int h, int n, int classes, int coords, int max_boxes)
{
region_layer l = {0};
l.type = REGION;
@@ -27,7 +27,8 @@
l.bias_updates = calloc(n*2, sizeof(float));
l.outputs = h*w*n*(classes + coords + 1);
l.inputs = l.outputs;
- l.truths = 30*(5);
+ l.max_boxes = max_boxes;
+ l.truths = max_boxes*(5);
l.delta = calloc(batch*l.outputs, sizeof(float));
l.output = calloc(batch*l.outputs, sizeof(float));
int i;
@@ -52,6 +53,8 @@
void resize_region_layer(layer *l, int w, int h)
{
+ int old_w = l->w;
+ int old_h = l->h;
l->w = w;
l->h = h;
@@ -62,11 +65,13 @@
l->delta = realloc(l->delta, l->batch*l->outputs*sizeof(float));
#ifdef GPU
- cuda_free(l->delta_gpu);
- cuda_free(l->output_gpu);
+ if (old_w < w || old_h < h) {
+ cuda_free(l->delta_gpu);
+ cuda_free(l->output_gpu);
- l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs);
- l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs);
+ l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs);
+ l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs);
+ }
#endif
}
@@ -105,27 +110,50 @@
return iou;
}
-void delta_region_class(float *output, float *delta, int index, int class, int classes, tree *hier, float scale, float *avg_cat)
+void delta_region_class(float *output, float *delta, int index, int class_id, int classes, tree *hier, float scale, float *avg_cat, int focal_loss)
{
int i, n;
if(hier){
float pred = 1;
- while(class >= 0){
- pred *= output[index + class];
- int g = hier->group[class];
+ while(class_id >= 0){
+ pred *= output[index + class_id];
+ int g = hier->group[class_id];
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]);
+ delta[index + class_id] = scale * (1 - output[index + class_id]);
- class = hier->parent[class];
+ class_id = hier->parent[class_id];
}
*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];
+ // 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 + 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 + n] = scale * (((n == class_id) ? 1 : 0) - output[index + n]);
+
+ delta[index + n] *= alpha*grad;
+
+ if (n == class_id) *avg_cat += output[index + n];
+ }
+ }
+ else {
+ // default
+ for (n = 0; n < classes; ++n) {
+ delta[index + n] = scale * (((n == class_id) ? 1 : 0) - output[index + n]);
+ if (n == class_id) *avg_cat += output[index + n];
+ }
}
}
}
@@ -140,6 +168,13 @@
return (x != x);
}
+static int entry_index(layer l, int batch, int location, int entry)
+{
+ int n = location / (l.w*l.h);
+ int loc = location % (l.w*l.h);
+ return batch*l.outputs + n*l.w*l.h*(l.coords + l.classes + 1) + entry*l.w*l.h + loc;
+}
+
void softmax_tree(float *input, int batch, int inputs, float temp, tree *hierarchy, float *output);
void forward_region_layer(const region_layer l, network_state state)
{
@@ -169,7 +204,7 @@
for (b = 0; b < l.batch; ++b){
for(i = 0; i < l.h*l.w*l.n; ++i){
int index = size*i + b*l.outputs;
- softmax(l.output + index + 5, l.classes, 1, l.output + index + 5);
+ softmax(l.output + index + 5, l.classes, 1, l.output + index + 5, 1);
}
}
}
@@ -186,31 +221,31 @@
*(l.cost) = 0;
for (b = 0; b < l.batch; ++b) {
if(l.softmax_tree){
- int onlyclass = 0;
- for(t = 0; t < 30; ++t){
+ int onlyclass_id = 0;
+ for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box(state.truth + t*5 + b*l.truths);
- if(!truth.x) break;
- int class = state.truth[t*5 + b*l.truths + 4];
+ if(!truth.x) break; // continue;
+ int class_id = state.truth[t*5 + b*l.truths + 4];
float maxp = 0;
int maxi = 0;
if(truth.x > 100000 && truth.y > 100000){
for(n = 0; n < l.n*l.w*l.h; ++n){
int index = size*n + b*l.outputs + 5;
float scale = l.output[index-1];
- float p = scale*get_hierarchy_probability(l.output + index, l.softmax_tree, class);
+ float p = scale*get_hierarchy_probability(l.output + index, l.softmax_tree, class_id);
if(p > maxp){
maxp = p;
maxi = n;
}
}
int index = size*maxi + b*l.outputs + 5;
- delta_region_class(l.output, l.delta, index, class, l.classes, l.softmax_tree, l.class_scale, &avg_cat);
+ delta_region_class(l.output, l.delta, index, class_id, l.classes, l.softmax_tree, l.class_scale, &avg_cat, l.focal_loss);
++class_count;
- onlyclass = 1;
+ onlyclass_id = 1;
break;
}
}
- if(onlyclass) continue;
+ if(onlyclass_id) continue;
}
for (j = 0; j < l.h; ++j) {
for (i = 0; i < l.w; ++i) {
@@ -218,13 +253,15 @@
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){
+ int best_class_id = -1;
+ for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box(state.truth + t*5 + b*l.truths);
- if(!truth.x) break;
+ int class_id = state.truth[t * 5 + 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; // continue;
float iou = box_iou(pred, truth);
if (iou > best_iou) {
- best_class = state.truth[t*5 + b*l.truths + 4];
+ best_class_id = state.truth[t*5 + b*l.truths + 4];
best_iou = iou;
}
}
@@ -235,7 +272,7 @@
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);
+ delta_region_class(l.output, l.delta, index + 5, best_class_id, l.classes, l.softmax_tree, l.class_scale*(l.classfix == 2 ? l.output[index + 4] : 1), &avg_cat, l.focal_loss);
++class_count;
}
}
@@ -256,10 +293,16 @@
}
}
}
- for(t = 0; t < 30; ++t){
+ for(t = 0; t < l.max_boxes; ++t){
box truth = float_to_box(state.truth + t*5 + b*l.truths);
+ int class_id = state.truth[t * 5 + 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;
+ if(!truth.x) break; // continue;
float best_iou = 0;
int best_index = 0;
int best_n = 0;
@@ -304,10 +347,8 @@
l.delta[best_index + 4] = l.object_scale * (iou - l.output[best_index + 4]) * logistic_gradient(l.output[best_index + 4]);
}
-
- int class = state.truth[t*5 + b*l.truths + 4];
- if (l.map) class = l.map[class];
- delta_region_class(l.output, l.delta, best_index + 5, class, l.classes, l.softmax_tree, l.class_scale, &avg_cat);
+ if (l.map) class_id = l.map[class_id];
+ delta_region_class(l.output, l.delta, best_index + 5, class_id, l.classes, l.softmax_tree, l.class_scale, &avg_cat, l.focal_loss);
++count;
++class_count;
}
@@ -409,7 +450,7 @@
cuda_pull_array(state.truth, truth_cpu, num_truth);
}
cuda_pull_array(l.output_gpu, in_cpu, l.batch*l.inputs);
- cudaStreamSynchronize(get_cuda_stream());
+ //cudaStreamSynchronize(get_cuda_stream());
network_state cpu_state = state;
cpu_state.train = state.train;
cpu_state.truth = truth_cpu;
@@ -419,7 +460,7 @@
free(cpu_state.input);
if(!state.train) return;
cuda_push_array(l.delta_gpu, l.delta, l.batch*l.outputs);
- cudaStreamSynchronize(get_cuda_stream());
+ //cudaStreamSynchronize(get_cuda_stream());
if(cpu_state.truth) free(cpu_state.truth);
}
@@ -429,3 +470,110 @@
}
#endif
+
+void correct_region_boxes(detection *dets, int n, int w, int h, int netw, int neth, int relative)
+{
+ int i;
+ int new_w = 0;
+ int new_h = 0;
+ if (((float)netw / w) < ((float)neth / h)) {
+ new_w = netw;
+ new_h = (h * netw) / w;
+ }
+ else {
+ new_h = neth;
+ new_w = (w * neth) / h;
+ }
+ for (i = 0; i < n; ++i) {
+ box b = dets[i].bbox;
+ b.x = (b.x - (netw - new_w) / 2. / netw) / ((float)new_w / netw);
+ b.y = (b.y - (neth - new_h) / 2. / neth) / ((float)new_h / neth);
+ b.w *= (float)netw / new_w;
+ b.h *= (float)neth / new_h;
+ if (!relative) {
+ b.x *= w;
+ b.w *= w;
+ b.y *= h;
+ b.h *= h;
+ }
+ dets[i].bbox = b;
+ }
+}
+
+
+void get_region_detections(layer l, int w, int h, int netw, int neth, float thresh, int *map, float tree_thresh, int relative, detection *dets)
+{
+ int i, j, n, z;
+ float *predictions = l.output;
+ if (l.batch == 2) {
+ float *flip = l.output + l.outputs;
+ for (j = 0; j < l.h; ++j) {
+ for (i = 0; i < l.w / 2; ++i) {
+ for (n = 0; n < l.n; ++n) {
+ for (z = 0; z < l.classes + l.coords + 1; ++z) {
+ int i1 = z*l.w*l.h*l.n + n*l.w*l.h + j*l.w + i;
+ int i2 = z*l.w*l.h*l.n + n*l.w*l.h + j*l.w + (l.w - i - 1);
+ float swap = flip[i1];
+ flip[i1] = flip[i2];
+ flip[i2] = swap;
+ if (z == 0) {
+ flip[i1] = -flip[i1];
+ flip[i2] = -flip[i2];
+ }
+ }
+ }
+ }
+ }
+ for (i = 0; i < l.outputs; ++i) {
+ l.output[i] = (l.output[i] + flip[i]) / 2.;
+ }
+ }
+ for (i = 0; i < l.w*l.h; ++i) {
+ int row = i / l.w;
+ int col = i % l.w;
+ for (n = 0; n < l.n; ++n) {
+ int index = n*l.w*l.h + i;
+ for (j = 0; j < l.classes; ++j) {
+ dets[index].prob[j] = 0;
+ }
+ int obj_index = entry_index(l, 0, n*l.w*l.h + i, l.coords);
+ int box_index = entry_index(l, 0, n*l.w*l.h + i, 0);
+ int mask_index = entry_index(l, 0, n*l.w*l.h + i, 4);
+ float scale = l.background ? 1 : predictions[obj_index];
+ dets[index].bbox = get_region_box(predictions, l.biases, n, box_index, col, row, l.w, l.h);// , l.w*l.h);
+ dets[index].objectness = scale > thresh ? scale : 0;
+ if (dets[index].mask) {
+ for (j = 0; j < l.coords - 4; ++j) {
+ dets[index].mask[j] = l.output[mask_index + j*l.w*l.h];
+ }
+ }
+
+ int class_index = entry_index(l, 0, n*l.w*l.h + i, l.coords + !l.background);
+ if (l.softmax_tree) {
+
+ hierarchy_predictions(predictions + class_index, l.classes, l.softmax_tree, 0);// , l.w*l.h);
+ if (map) {
+ for (j = 0; j < 200; ++j) {
+ int class_index = entry_index(l, 0, n*l.w*l.h + i, l.coords + 1 + map[j]);
+ float prob = scale*predictions[class_index];
+ dets[index].prob[j] = (prob > thresh) ? prob : 0;
+ }
+ }
+ else {
+ int j = hierarchy_top_prediction(predictions + class_index, l.softmax_tree, tree_thresh, l.w*l.h);
+ dets[index].prob[j] = (scale > thresh) ? scale : 0;
+ }
+ }
+ else {
+ if (dets[index].objectness) {
+ for (j = 0; j < l.classes; ++j) {
+ int class_index = entry_index(l, 0, n*l.w*l.h + i, l.coords + 1 + j);
+ float prob = scale*predictions[class_index];
+ dets[index].prob[j] = (prob > thresh) ? prob : 0;
+ }
+ }
+ }
+ }
+ }
+ correct_region_boxes(dets, l.w*l.h*l.n, w, h, netw, neth, relative);
+}
--
Gitblit v1.10.0