From f047cfff99e00e28c02eb59b6d32386c122f9af6 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sun, 08 Mar 2015 18:31:12 +0000
Subject: [PATCH] renamed sigmoid to logistic
---
src/cost_layer.c | 61 ++++++++++++++++++++++++++----
1 files changed, 52 insertions(+), 9 deletions(-)
diff --git a/src/cost_layer.c b/src/cost_layer.c
index 66ce349..8158275 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -1,29 +1,59 @@
#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;
+ 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";
+ }
+ 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;
}
+void pull_cost_layer(cost_layer layer)
+{
+ cuda_pull_array(layer.delta_gpu, layer.delta, layer.batch*layer.inputs);
+}
+void push_cost_layer(cost_layer layer)
+{
+ cuda_push_array(layer.delta_gpu, layer.delta, layer.batch*layer.inputs);
+}
+
void forward_cost_layer(cost_layer layer, float *input, float *truth)
{
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);
*(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 +62,33 @@
}
#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;
+
+ /*
+ float *in = calloc(layer.inputs*layer.batch, sizeof(float));
+ float *t = calloc(layer.inputs*layer.batch, sizeof(float));
+ cuda_pull_array(input, in, layer.batch*layer.inputs);
+ cuda_pull_array(truth, t, layer.batch*layer.inputs);
+ forward_cost_layer(layer, in, t);
+ cuda_push_array(layer.delta_gpu, layer.delta, layer.batch*layer.inputs);
+ free(in);
+ free(t);
+ */
+ 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);
+ 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