From 1b5afb45838e603fa6780762eb8cc59246dc2d81 Mon Sep 17 00:00:00 2001
From: IlyaOvodov <b@ovdv.ru>
Date: Tue, 08 May 2018 11:09:35 +0000
Subject: [PATCH] Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount
---
src/region_layer.c | 125 ++++++++++++++++++++++++++++++++++++++++-
1 files changed, 121 insertions(+), 4 deletions(-)
diff --git a/src/region_layer.c b/src/region_layer.c
index 9ca71c6..62c8b34 100644
--- a/src/region_layer.c
+++ b/src/region_layer.c
@@ -130,12 +130,15 @@
} else {
// Focal loss
if (focal_loss) {
- // Focal Loss for Dense Object Detection: http://blog.csdn.net/linmingan/article/details/77885832
+ // 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 grad = -2 * (1 - output[ti])*logf(fmaxf(output[ti], 0.0000001))*output[ti] + (1 - output[ti])*(1 - output[ti]);
+ 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]);
@@ -165,6 +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)
{
@@ -434,7 +444,7 @@
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;
@@ -444,7 +454,7 @@
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);
}
@@ -454,3 +464,110 @@
}
#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