From 0f645836f193e75c4c3b718369e6fab15b5d19c5 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 11 Feb 2015 03:41:03 +0000
Subject: [PATCH] Detection is back, baby\!
---
src/cost_layer.c | 54 +++++++++++++++++++++++++++++++++++++++++++++---------
1 files changed, 45 insertions(+), 9 deletions(-)
diff --git a/src/cost_layer.c b/src/cost_layer.c
index 66ce349..a08562b 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -1,19 +1,42 @@
#include "cost_layer.h"
-#include "mini_blas.h"
+#include "utils.h"
+#include "cuda.h"
+#include "blas.h"
#include <math.h>
+#include <string.h>
#include <stdlib.h>
#include <stdio.h>
-cost_layer *make_cost_layer(int batch, int inputs)
+COST_TYPE get_cost_type(char *s)
+{
+ if (strcmp(s, "sse")==0) return SSE;
+ if (strcmp(s, "detection")==0) return DETECTION;
+ fprintf(stderr, "Couldn't find activation function %s, going with SSE\n", s);
+ return SSE;
+}
+
+char *get_cost_string(COST_TYPE a)
+{
+ switch(a){
+ case SSE:
+ return "sse";
+ case DETECTION:
+ return "detection";
+ }
+ return "sse";
+}
+
+cost_layer *make_cost_layer(int batch, int inputs, COST_TYPE type)
{
fprintf(stderr, "Cost Layer: %d inputs\n", inputs);
cost_layer *layer = calloc(1, sizeof(cost_layer));
layer->batch = batch;
layer->inputs = inputs;
+ layer->type = type;
layer->delta = calloc(inputs*batch, sizeof(float));
layer->output = calloc(1, sizeof(float));
#ifdef GPU
- layer->delta_cl = cl_make_array(layer->delta, inputs*batch);
+ layer->delta_gpu = cuda_make_array(layer->delta, inputs*batch);
#endif
return layer;
}
@@ -23,7 +46,14 @@
if (!truth) return;
copy_cpu(layer.batch*layer.inputs, truth, 1, layer.delta, 1);
axpy_cpu(layer.batch*layer.inputs, -1, input, 1, layer.delta, 1);
+ if(layer.type == DETECTION){
+ int i;
+ for(i = 0; i < layer.batch*layer.inputs; ++i){
+ if((i%5) && !truth[(i/5)*5]) layer.delta[i] = 0;
+ }
+ }
*(layer.output) = dot_cpu(layer.batch*layer.inputs, layer.delta, 1, layer.delta, 1);
+ //printf("cost: %f\n", *layer.output);
}
void backward_cost_layer(const cost_layer layer, float *input, float *delta)
@@ -32,20 +62,26 @@
}
#ifdef GPU
-void forward_cost_layer_gpu(cost_layer layer, cl_mem input, cl_mem truth)
+
+void forward_cost_layer_gpu(cost_layer layer, float * input, float * truth)
{
if (!truth) return;
+ copy_ongpu(layer.batch*layer.inputs, truth, 1, layer.delta_gpu, 1);
+ axpy_ongpu(layer.batch*layer.inputs, -1, input, 1, layer.delta_gpu, 1);
- copy_ongpu(layer.batch*layer.inputs, truth, 1, layer.delta_cl, 1);
- axpy_ongpu(layer.batch*layer.inputs, -1, input, 1, layer.delta_cl, 1);
- cl_read_array(layer.delta_cl, layer.delta, layer.batch*layer.inputs);
+ if(layer.type==DETECTION){
+ mask_ongpu(layer.inputs*layer.batch, layer.delta_gpu, truth, 5);
+ }
+
+ cuda_pull_array(layer.delta_gpu, layer.delta, layer.batch*layer.inputs);
*(layer.output) = dot_cpu(layer.batch*layer.inputs, layer.delta, 1, layer.delta, 1);
+ //printf("cost: %f\n", *layer.output);
}
-void backward_cost_layer_gpu(const cost_layer layer, cl_mem input, cl_mem delta)
+void backward_cost_layer_gpu(const cost_layer layer, float * input, float * delta)
{
- copy_ongpu(layer.batch*layer.inputs, layer.delta_cl, 1, delta, 1);
+ copy_ongpu(layer.batch*layer.inputs, layer.delta_gpu, 1, delta, 1);
}
#endif
--
Gitblit v1.10.0