From c7b10ceadb1a78e7480d281444a31ae2a7dc1b05 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 06 May 2016 23:25:16 +0000
Subject: [PATCH] so much need to commit
---
src/cost_layer.c | 122 ++++++++++++++++++++++++++++++++--------
1 files changed, 98 insertions(+), 24 deletions(-)
diff --git a/src/cost_layer.c b/src/cost_layer.c
index dd0ff90..fdba777 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -1,49 +1,123 @@
#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, "masked")==0) return MASKED;
+ if (strcmp(s, "smooth")==0) return SMOOTH;
+ fprintf(stderr, "Couldn't find cost type %s, going with SSE\n", s);
+ return SSE;
+}
+
+char *get_cost_string(COST_TYPE a)
+{
+ switch(a){
+ case SSE:
+ return "sse";
+ case MASKED:
+ return "masked";
+ case SMOOTH:
+ return "smooth";
+ }
+ return "sse";
+}
+
+cost_layer make_cost_layer(int batch, int inputs, COST_TYPE cost_type, float scale)
{
fprintf(stderr, "Cost Layer: %d inputs\n", inputs);
- cost_layer *layer = calloc(1, sizeof(cost_layer));
- layer->batch = batch;
- layer->inputs = inputs;
- layer->delta = calloc(inputs*batch, sizeof(float));
- layer->output = calloc(1, sizeof(float));
+ cost_layer l = {0};
+ l.type = COST;
+
+ l.scale = scale;
+ l.batch = batch;
+ l.inputs = inputs;
+ l.outputs = inputs;
+ l.cost_type = cost_type;
+ l.delta = calloc(inputs*batch, sizeof(float));
+ l.output = calloc(inputs*batch, sizeof(float));
+ l.cost = calloc(1, sizeof(float));
#ifdef GPU
- layer->delta_cl = cl_make_array(layer->delta, inputs*batch);
+ l.delta_gpu = cuda_make_array(l.output, inputs*batch);
+ l.output_gpu = cuda_make_array(l.delta, inputs*batch);
#endif
- return layer;
+ return l;
}
-void forward_cost_layer(cost_layer layer, float *input, float *truth)
+void resize_cost_layer(cost_layer *l, int inputs)
{
- 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);
+ l->inputs = inputs;
+ l->outputs = inputs;
+ l->delta = realloc(l->delta, inputs*l->batch*sizeof(float));
+ l->output = realloc(l->output, inputs*l->batch*sizeof(float));
+#ifdef GPU
+ cuda_free(l->delta_gpu);
+ cuda_free(l->output_gpu);
+ l->delta_gpu = cuda_make_array(l->delta, inputs*l->batch);
+ l->output_gpu = cuda_make_array(l->output, inputs*l->batch);
+#endif
}
-void backward_cost_layer(const cost_layer layer, float *input, float *delta)
+void forward_cost_layer(cost_layer l, network_state state)
{
- copy_cpu(layer.batch*layer.inputs, layer.delta, 1, delta, 1);
+ if (!state.truth) return;
+ if(l.cost_type == MASKED){
+ int i;
+ for(i = 0; i < l.batch*l.inputs; ++i){
+ if(state.truth[i] == SECRET_NUM) state.input[i] = SECRET_NUM;
+ }
+ }
+ if(l.cost_type == SMOOTH){
+ smooth_l1_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
+ } else {
+ l2_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
+ }
+ l.cost[0] = sum_array(l.output, l.batch*l.inputs);
+}
+
+void backward_cost_layer(const cost_layer l, network_state state)
+{
+ axpy_cpu(l.batch*l.inputs, l.scale, l.delta, 1, state.delta, 1);
}
#ifdef GPU
-void forward_cost_layer_gpu(cost_layer layer, cl_mem input, cl_mem truth)
+
+void pull_cost_layer(cost_layer l)
{
- if (!truth) return;
- 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);
- *(layer.output) = dot_cpu(layer.batch*layer.inputs, layer.delta, 1, layer.delta, 1);
+ cuda_pull_array(l.delta_gpu, l.delta, l.batch*l.inputs);
}
-void backward_cost_layer_gpu(const cost_layer layer, cl_mem input, cl_mem delta)
+void push_cost_layer(cost_layer l)
{
- copy_ongpu(layer.batch*layer.inputs, layer.delta_cl, 1, delta, 1);
+ cuda_push_array(l.delta_gpu, l.delta, l.batch*l.inputs);
+}
+
+void forward_cost_layer_gpu(cost_layer l, network_state state)
+{
+ if (!state.truth) return;
+ if (l.cost_type == MASKED) {
+ mask_ongpu(l.batch*l.inputs, state.input, SECRET_NUM, state.truth);
+ }
+
+ if(l.cost_type == SMOOTH){
+ smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
+ } else {
+ l2_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
+ }
+
+ cuda_pull_array(l.output_gpu, l.output, l.batch*l.inputs);
+ l.cost[0] = sum_array(l.output, l.batch*l.inputs);
+}
+
+void backward_cost_layer_gpu(const cost_layer l, network_state state)
+{
+ axpy_ongpu(l.batch*l.inputs, l.scale, l.delta_gpu, 1, state.delta, 1);
}
#endif
--
Gitblit v1.10.0