From 481b57a96a9ef29b112caec1bb3e17ffb043ceae Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sun, 25 Sep 2016 06:12:54 +0000
Subject: [PATCH] So I have this new programming paradigm.......
---
src/route_layer.c | 32 +++++++++++++++++++-------------
1 files changed, 19 insertions(+), 13 deletions(-)
diff --git a/src/route_layer.c b/src/route_layer.c
index e3802b7..47e3d70 100644
--- a/src/route_layer.c
+++ b/src/route_layer.c
@@ -21,22 +21,28 @@
fprintf(stderr, "\n");
l.outputs = outputs;
l.inputs = outputs;
- l.delta = calloc(outputs*batch, sizeof(float));
+ l.delta = calloc(outputs*batch, sizeof(float));
l.output = calloc(outputs*batch, sizeof(float));;
+
+ l.forward = forward_route_layer;
+ l.backward = backward_route_layer;
#ifdef GPU
- l.delta_gpu = cuda_make_array(0, outputs*batch);
- l.output_gpu = cuda_make_array(0, outputs*batch);
+ l.forward_gpu = forward_route_layer_gpu;
+ l.backward_gpu = backward_route_layer_gpu;
+
+ l.delta_gpu = cuda_make_array(l.delta, outputs*batch);
+ l.output_gpu = cuda_make_array(l.output, outputs*batch);
#endif
return l;
}
-void forward_route_layer(const route_layer l, network net)
+void forward_route_layer(const route_layer l, network_state state)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
- float *input = net.layers[index].output;
+ float *input = state.net.layers[index].output;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
copy_cpu(input_size, input + j*input_size, 1, l.output + offset + j*l.outputs, 1);
@@ -45,29 +51,29 @@
}
}
-void backward_route_layer(const route_layer l, network net)
+void backward_route_layer(const route_layer l, network_state state)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
- float *delta = net.layers[index].delta;
+ float *delta = state.net.layers[index].delta;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
- copy_cpu(input_size, l.delta + offset + j*l.outputs, 1, delta + j*input_size, 1);
+ axpy_cpu(input_size, 1, l.delta + offset + j*l.outputs, 1, delta + j*input_size, 1);
}
offset += input_size;
}
}
#ifdef GPU
-void forward_route_layer_gpu(const route_layer l, network net)
+void forward_route_layer_gpu(const route_layer l, network_state state)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
- float *input = net.layers[index].output_gpu;
+ float *input = state.net.layers[index].output_gpu;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
copy_ongpu(input_size, input + j*input_size, 1, l.output_gpu + offset + j*l.outputs, 1);
@@ -76,16 +82,16 @@
}
}
-void backward_route_layer_gpu(const route_layer l, network net)
+void backward_route_layer_gpu(const route_layer l, network_state state)
{
int i, j;
int offset = 0;
for(i = 0; i < l.n; ++i){
int index = l.input_layers[i];
- float *delta = net.layers[index].delta_gpu;
+ float *delta = state.net.layers[index].delta_gpu;
int input_size = l.input_sizes[i];
for(j = 0; j < l.batch; ++j){
- copy_ongpu(input_size, l.delta_gpu + offset + j*l.outputs, 1, delta + j*input_size, 1);
+ axpy_ongpu(input_size, 1, l.delta_gpu + offset + j*l.outputs, 1, delta + j*input_size, 1);
}
offset += input_size;
}
--
Gitblit v1.10.0