From d7d7da2653ff4f79a275529b0ac3fec438880083 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 27 Mar 2015 02:13:59 +0000
Subject: [PATCH] Fixed im2col mistake >< face#palm
---
src/detection_layer.c | 139 ++++++++++++++++++++++++++++++++++++----------
1 files changed, 108 insertions(+), 31 deletions(-)
diff --git a/src/detection_layer.c b/src/detection_layer.c
index 68d151a..73b2862 100644
--- a/src/detection_layer.c
+++ b/src/detection_layer.c
@@ -8,23 +8,25 @@
int get_detection_layer_locations(detection_layer layer)
{
- return layer.inputs / (layer.classes+layer.coords+layer.rescore);
+ return layer.inputs / (layer.classes+layer.coords+layer.rescore+layer.background);
}
int get_detection_layer_output_size(detection_layer layer)
{
- return get_detection_layer_locations(layer)*(layer.classes+layer.coords);
+ return get_detection_layer_locations(layer)*(layer.background + layer.classes + layer.coords);
}
-detection_layer *make_detection_layer(int batch, int inputs, int classes, int coords, int rescore)
+detection_layer *make_detection_layer(int batch, int inputs, int classes, int coords, int rescore, int background, int nuisance)
{
detection_layer *layer = calloc(1, sizeof(detection_layer));
-
+
layer->batch = batch;
layer->inputs = inputs;
layer->classes = classes;
layer->coords = coords;
layer->rescore = rescore;
+ layer->nuisance = nuisance;
+ layer->background = background;
int outputs = get_detection_layer_output_size(*layer);
layer->output = calloc(batch*outputs, sizeof(float));
layer->delta = calloc(batch*outputs, sizeof(float));
@@ -39,28 +41,85 @@
return layer;
}
-void forward_detection_layer(const detection_layer layer, float *in, float *truth)
+void dark_zone(detection_layer layer, int class, int start, network_state state)
+{
+ int index = start+layer.background+class;
+ int size = layer.classes+layer.coords+layer.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;
+ layer.output[index + di] = 0;
+ //if(!state.truth[start+di]) continue;
+ //layer.output[start + di] = 1;
+ }
+ }
+}
+
+void forward_detection_layer(const detection_layer layer, network_state state)
{
int in_i = 0;
int out_i = 0;
int locations = get_detection_layer_locations(layer);
int i,j;
for(i = 0; i < layer.batch*locations; ++i){
- int mask = (!truth || !truth[out_i + layer.classes - 1]);
+ int mask = (!state.truth || state.truth[out_i + layer.background + layer.classes + 2]);
float scale = 1;
- if(layer.rescore) scale = in[in_i++];
- for(j = 0; j < layer.classes; ++j){
- layer.output[out_i++] = scale*in[in_i++];
+ if(layer.rescore) scale = state.input[in_i++];
+ else if(layer.nuisance){
+ layer.output[out_i++] = 1-state.input[in_i++];
+ scale = mask;
}
- softmax_array(layer.output + out_i - layer.classes, layer.classes, layer.output + out_i - layer.classes);
- activate_array(in+in_i, layer.coords, LOGISTIC);
+ else if(layer.background) layer.output[out_i++] = scale*state.input[in_i++];
+
+ for(j = 0; j < layer.classes; ++j){
+ layer.output[out_i++] = scale*state.input[in_i++];
+ }
+ if(layer.nuisance){
+
+ }else if(layer.background){
+ softmax_array(layer.output + out_i - layer.classes-layer.background, layer.classes+layer.background, layer.output + out_i - layer.classes-layer.background);
+ activate_array(state.input+in_i, layer.coords, LOGISTIC);
+ }
for(j = 0; j < layer.coords; ++j){
- layer.output[out_i++] = mask*in[in_i++];
+ layer.output[out_i++] = mask*state.input[in_i++];
}
}
+ /*
+ int count = 0;
+ for(i = 0; i < layer.batch*locations; ++i){
+ for(j = 0; j < layer.classes+layer.background; ++j){
+ printf("%f, ", layer.output[count++]);
+ }
+ printf("\n");
+ for(j = 0; j < layer.coords; ++j){
+ printf("%f, ", layer.output[count++]);
+ }
+ printf("\n");
+ }
+ */
+ /*
+ if(layer.background || 1){
+ for(i = 0; i < layer.batch*locations; ++i){
+ int index = i*(layer.classes+layer.coords+layer.background);
+ for(j= 0; j < layer.classes; ++j){
+ if(state.truth[index+j+layer.background]){
+ //dark_zone(layer, j, index, state);
+ }
+ }
+ }
+ }
+ */
}
-void backward_detection_layer(const detection_layer layer, float *in, float *delta)
+void backward_detection_layer(const detection_layer layer, network_state state)
{
int locations = get_detection_layer_locations(layer);
int i,j;
@@ -69,49 +128,67 @@
for(i = 0; i < layer.batch*locations; ++i){
float scale = 1;
float latent_delta = 0;
- if(layer.rescore) scale = in[in_i++];
+ if(layer.rescore) scale = state.input[in_i++];
+ else if (layer.nuisance) state.delta[in_i++] = -layer.delta[out_i++];
+ else if (layer.background) state.delta[in_i++] = scale*layer.delta[out_i++];
for(j = 0; j < layer.classes; ++j){
- latent_delta += in[in_i]*layer.delta[out_i];
- delta[in_i++] = scale*layer.delta[out_i++];
+ latent_delta += state.input[in_i]*layer.delta[out_i];
+ state.delta[in_i++] = scale*layer.delta[out_i++];
}
-
- gradient_array(layer.output + out_i, layer.coords, LOGISTIC, layer.delta + out_i);
+
+ if (layer.nuisance) {
+
+ }else if (layer.background) gradient_array(layer.output + out_i, layer.coords, LOGISTIC, layer.delta + out_i);
for(j = 0; j < layer.coords; ++j){
- delta[in_i++] = layer.delta[out_i++];
+ state.delta[in_i++] = layer.delta[out_i++];
}
- if(layer.rescore) delta[in_i-layer.coords-layer.classes-layer.rescore] = latent_delta;
+ if(layer.rescore) state.delta[in_i-layer.coords-layer.classes-layer.rescore-layer.background] = latent_delta;
}
}
#ifdef GPU
-void forward_detection_layer_gpu(const detection_layer layer, float *in, float *truth)
+void forward_detection_layer_gpu(const detection_layer layer, network_state state)
{
int outputs = get_detection_layer_output_size(layer);
float *in_cpu = calloc(layer.batch*layer.inputs, sizeof(float));
float *truth_cpu = 0;
- if(truth){
+ if(state.truth){
truth_cpu = calloc(layer.batch*outputs, sizeof(float));
- cuda_pull_array(truth, truth_cpu, layer.batch*outputs);
+ cuda_pull_array(state.truth, truth_cpu, layer.batch*outputs);
}
- cuda_pull_array(in, in_cpu, layer.batch*layer.inputs);
- forward_detection_layer(layer, in_cpu, truth_cpu);
+ cuda_pull_array(state.input, in_cpu, layer.batch*layer.inputs);
+ network_state cpu_state;
+ cpu_state.train = state.train;
+ cpu_state.truth = truth_cpu;
+ cpu_state.input = in_cpu;
+ forward_detection_layer(layer, cpu_state);
cuda_push_array(layer.output_gpu, layer.output, layer.batch*outputs);
- free(in_cpu);
- if(truth_cpu) free(truth_cpu);
+ free(cpu_state.input);
+ if(cpu_state.truth) free(cpu_state.truth);
}
-void backward_detection_layer_gpu(detection_layer layer, float *in, float *delta)
+void backward_detection_layer_gpu(detection_layer layer, network_state state)
{
int outputs = get_detection_layer_output_size(layer);
float *in_cpu = calloc(layer.batch*layer.inputs, sizeof(float));
float *delta_cpu = calloc(layer.batch*layer.inputs, sizeof(float));
+ float *truth_cpu = 0;
+ if(state.truth){
+ truth_cpu = calloc(layer.batch*outputs, sizeof(float));
+ cuda_pull_array(state.truth, truth_cpu, layer.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(in, in_cpu, layer.batch*layer.inputs);
+ cuda_pull_array(state.input, in_cpu, layer.batch*layer.inputs);
cuda_pull_array(layer.delta_gpu, layer.delta, layer.batch*outputs);
- backward_detection_layer(layer, in_cpu, delta_cpu);
- cuda_push_array(delta, delta_cpu, layer.batch*layer.inputs);
+ backward_detection_layer(layer, cpu_state);
+ cuda_push_array(state.delta, delta_cpu, layer.batch*layer.inputs);
free(in_cpu);
free(delta_cpu);
--
Gitblit v1.10.0