From f1ad9a0487dc60c01e56bacb2a67de1e1006b4b7 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Thu, 05 Apr 2018 22:31:04 +0000
Subject: [PATCH] Compile fix
---
src/route_layer.c | 68 +++++++++++++++++++++++++++-------
1 files changed, 54 insertions(+), 14 deletions(-)
diff --git a/src/route_layer.c b/src/route_layer.c
index e3802b7..dce7118 100644
--- a/src/route_layer.c
+++ b/src/route_layer.c
@@ -5,7 +5,7 @@
route_layer make_route_layer(int batch, int n, int *input_layers, int *input_sizes)
{
- fprintf(stderr,"Route Layer:");
+ fprintf(stderr,"route ");
route_layer l = {0};
l.type = ROUTE;
l.batch = batch;
@@ -21,22 +21,62 @@
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 resize_route_layer(route_layer *l, network *net)
+{
+ int i;
+ layer first = net->layers[l->input_layers[0]];
+ l->out_w = first.out_w;
+ l->out_h = first.out_h;
+ l->out_c = first.out_c;
+ l->outputs = first.outputs;
+ l->input_sizes[0] = first.outputs;
+ for(i = 1; i < l->n; ++i){
+ int index = l->input_layers[i];
+ layer next = net->layers[index];
+ l->outputs += next.outputs;
+ l->input_sizes[i] = next.outputs;
+ if(next.out_w == first.out_w && next.out_h == first.out_h){
+ l->out_c += next.out_c;
+ }else{
+ printf("%d %d, %d %d\n", next.out_w, next.out_h, first.out_w, first.out_h);
+ l->out_h = l->out_w = l->out_c = 0;
+ }
+ }
+ l->inputs = l->outputs;
+ l->delta = realloc(l->delta, l->outputs*l->batch*sizeof(float));
+ l->output = realloc(l->output, l->outputs*l->batch*sizeof(float));
+
+#ifdef GPU
+ cuda_free(l->output_gpu);
+ cuda_free(l->delta_gpu);
+ l->output_gpu = cuda_make_array(l->output, l->outputs*l->batch);
+ l->delta_gpu = cuda_make_array(l->delta, l->outputs*l->batch);
+#endif
+
+}
+
+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 +85,29 @@
}
}
-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 +116,16 @@
}
}
-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