From b77a8f39874c05a1ed0cabd8d85134126ac2da47 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 28 Nov 2014 18:38:26 +0000
Subject: [PATCH] stable
---
src/cost_layer.c | 65 ++++++++++++++++++++++++++++++++
1 files changed, 64 insertions(+), 1 deletions(-)
diff --git a/src/cost_layer.c b/src/cost_layer.c
index 1df0ed4..6614b94 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -2,15 +2,36 @@
#include "utils.h"
#include "mini_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
@@ -24,6 +45,12 @@
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);
}
@@ -33,6 +60,38 @@
}
#ifdef GPU
+
+cl_kernel get_mask_kernel()
+{
+ static int init = 0;
+ static cl_kernel kernel;
+ if(!init){
+ kernel = get_kernel("src/axpy.cl", "mask", 0);
+ init = 1;
+ }
+ return kernel;
+}
+
+void mask_ongpu(int n, cl_mem x, cl_mem mask, int mod)
+{
+ cl_setup();
+ cl_kernel kernel = get_mask_kernel();
+ cl_command_queue queue = cl.queue;
+
+ cl_uint i = 0;
+ cl.error = clSetKernelArg(kernel, i++, sizeof(n), (void*) &n);
+ cl.error = clSetKernelArg(kernel, i++, sizeof(x), (void*) &x);
+ cl.error = clSetKernelArg(kernel, i++, sizeof(mask), (void*) &mask);
+ cl.error = clSetKernelArg(kernel, i++, sizeof(mod), (void*) &mod);
+ check_error(cl);
+
+ const size_t global_size[] = {n};
+
+ cl.error = clEnqueueNDRangeKernel(queue, kernel, 1, 0, global_size, 0, 0, 0, 0);
+ check_error(cl);
+
+}
+
void forward_cost_layer_gpu(cost_layer layer, cl_mem input, cl_mem truth)
{
if (!truth) return;
@@ -40,6 +99,10 @@
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);
+ if(layer.type==DETECTION){
+ mask_ongpu(layer.inputs*layer.batch, layer.delta_cl, truth, 5);
+ }
+
cl_read_array(layer.delta_cl, layer.delta, layer.batch*layer.inputs);
*(layer.output) = dot_cpu(layer.batch*layer.inputs, layer.delta, 1, layer.delta, 1);
//printf("%f\n", *layer.output);
--
Gitblit v1.10.0