From 68213b835b9f15cb449ad2037a8b51c17a3de07b Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 14 Mar 2016 22:10:14 +0000
Subject: [PATCH] Makefile
---
src/cost_layer.c | 26 ++++++++++++++------------
1 files changed, 14 insertions(+), 12 deletions(-)
diff --git a/src/cost_layer.c b/src/cost_layer.c
index 39ae809..fdba777 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -41,9 +41,11 @@
l.outputs = inputs;
l.cost_type = cost_type;
l.delta = calloc(inputs*batch, sizeof(float));
- l.output = calloc(1, sizeof(float));
+ l.output = calloc(inputs*batch, sizeof(float));
+ l.cost = calloc(1, sizeof(float));
#ifdef GPU
- l.delta_gpu = cuda_make_array(l.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 l;
}
@@ -53,9 +55,12 @@
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
}
@@ -69,13 +74,11 @@
}
}
if(l.cost_type == SMOOTH){
- smooth_l1_cpu(l.batch*l.inputs, state.input, state.truth, l.delta);
+ smooth_l1_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
} else {
- copy_cpu(l.batch*l.inputs, state.truth, 1, l.delta, 1);
- axpy_cpu(l.batch*l.inputs, -1, state.input, 1, l.delta, 1);
+ l2_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
}
- *(l.output) = dot_cpu(l.batch*l.inputs, l.delta, 1, l.delta, 1);
- //printf("cost: %f\n", *l.output);
+ l.cost[0] = sum_array(l.output, l.batch*l.inputs);
}
void backward_cost_layer(const cost_layer l, network_state state)
@@ -103,14 +106,13 @@
}
if(l.cost_type == SMOOTH){
- smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu);
+ smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
} else {
- copy_ongpu(l.batch*l.inputs, state.truth, 1, l.delta_gpu, 1);
- axpy_ongpu(l.batch*l.inputs, -1, state.input, 1, l.delta_gpu, 1);
+ l2_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
}
- cuda_pull_array(l.delta_gpu, l.delta, l.batch*l.inputs);
- *(l.output) = dot_cpu(l.batch*l.inputs, l.delta, 1, l.delta, 1);
+ 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)
--
Gitblit v1.10.0