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/connected_layer.c | 31 +++++++++++++++++++++++++++++--
1 files changed, 29 insertions(+), 2 deletions(-)
diff --git a/src/connected_layer.c b/src/connected_layer.c
index e7784ea..2694229 100644
--- a/src/connected_layer.c
+++ b/src/connected_layer.c
@@ -36,6 +36,10 @@
l.weights = calloc(outputs*inputs, sizeof(float));
l.biases = calloc(outputs, sizeof(float));
+ l.forward = forward_connected_layer;
+ l.backward = backward_connected_layer;
+ l.update = update_connected_layer;
+
//float scale = 1./sqrt(inputs);
float scale = sqrt(2./inputs);
for(i = 0; i < outputs*inputs; ++i){
@@ -66,6 +70,10 @@
}
#ifdef GPU
+ l.forward_gpu = forward_connected_layer_gpu;
+ l.backward_gpu = backward_connected_layer_gpu;
+ l.update_gpu = update_connected_layer_gpu;
+
l.weights_gpu = cuda_make_array(l.weights, outputs*inputs);
l.biases_gpu = cuda_make_array(l.biases, outputs);
@@ -187,7 +195,7 @@
{
int i, j;
for(i = 0; i < l.outputs; ++i){
- float scale = l.scales[i]/sqrt(l.rolling_variance[i] + .00001);
+ float scale = l.scales[i]/sqrt(l.rolling_variance[i] + .000001);
for(j = 0; j < l.inputs; ++j){
l.weights[i*l.inputs + j] *= scale;
}
@@ -198,6 +206,25 @@
}
}
+
+void statistics_connected_layer(layer l)
+{
+ if(l.batch_normalize){
+ printf("Scales ");
+ print_statistics(l.scales, l.outputs);
+ /*
+ printf("Rolling Mean ");
+ print_statistics(l.rolling_mean, l.outputs);
+ printf("Rolling Variance ");
+ print_statistics(l.rolling_variance, l.outputs);
+ */
+ }
+ printf("Biases ");
+ print_statistics(l.biases, l.outputs);
+ printf("Weights ");
+ print_statistics(l.weights, l.outputs);
+}
+
#ifdef GPU
void pull_connected_layer(connected_layer l)
@@ -265,7 +292,7 @@
void backward_connected_layer_gpu(connected_layer l, network_state state)
{
int i;
- constrain_ongpu(l.outputs*l.batch, 5, l.delta_gpu, 1);
+ constrain_ongpu(l.outputs*l.batch, 1, l.delta_gpu, 1);
gradient_array_ongpu(l.output_gpu, l.outputs*l.batch, l.activation, l.delta_gpu);
for(i = 0; i < l.batch; ++i){
axpy_ongpu(l.outputs, 1, l.delta_gpu + i*l.outputs, 1, l.bias_updates_gpu, 1);
--
Gitblit v1.10.0