From 252e3b1916cfaca0783c9e90efaa55eb07b1a8cd Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Sun, 06 Nov 2016 00:27:31 +0000
Subject: [PATCH] :charizard: :charizard: :charizard:
---
src/convolutional_layer.c | 32 +++++++++++++++++++++++++++-----
1 files changed, 27 insertions(+), 5 deletions(-)
diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
index 299af75..1d93b3f 100644
--- a/src/convolutional_layer.c
+++ b/src/convolutional_layer.c
@@ -171,7 +171,7 @@
#endif
#endif
-convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int padding, ACTIVATION activation, int batch_normalize, int binary, int xnor)
+convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int padding, ACTIVATION activation, int batch_normalize, int binary, int xnor, int adam)
{
int i;
convolutional_layer l = {0};
@@ -209,6 +209,9 @@
l.output = calloc(l.batch*out_h * out_w * n, sizeof(float));
l.delta = calloc(l.batch*out_h * out_w * n, sizeof(float));
+ l.forward = forward_convolutional_layer;
+ l.backward = backward_convolutional_layer;
+ l.update = update_convolutional_layer;
if(binary){
l.binary_weights = calloc(c*n*size*size, sizeof(float));
l.cweights = calloc(c*n*size*size, sizeof(char));
@@ -232,18 +235,29 @@
l.rolling_mean = calloc(n, sizeof(float));
l.rolling_variance = calloc(n, sizeof(float));
}
+ if(adam){
+ l.adam = 1;
+ l.m = calloc(c*n*size*size, sizeof(float));
+ l.v = calloc(c*n*size*size, sizeof(float));
+ }
#ifdef GPU
+ l.forward_gpu = forward_convolutional_layer_gpu;
+ l.backward_gpu = backward_convolutional_layer_gpu;
+ l.update_gpu = update_convolutional_layer_gpu;
+
if(gpu_index >= 0){
+ if (adam) {
+ l.m_gpu = cuda_make_array(l.m, c*n*size*size);
+ l.v_gpu = cuda_make_array(l.v, c*n*size*size);
+ }
+
l.weights_gpu = cuda_make_array(l.weights, c*n*size*size);
l.weight_updates_gpu = cuda_make_array(l.weight_updates, c*n*size*size);
l.biases_gpu = cuda_make_array(l.biases, n);
l.bias_updates_gpu = cuda_make_array(l.bias_updates, n);
- l.scales_gpu = cuda_make_array(l.scales, n);
- l.scale_updates_gpu = cuda_make_array(l.scale_updates, n);
-
l.delta_gpu = cuda_make_array(l.delta, l.batch*out_h*out_w*n);
l.output_gpu = cuda_make_array(l.output, l.batch*out_h*out_w*n);
@@ -265,6 +279,9 @@
l.mean_delta_gpu = cuda_make_array(l.mean, n);
l.variance_delta_gpu = cuda_make_array(l.variance, n);
+ l.scales_gpu = cuda_make_array(l.scales, n);
+ l.scale_updates_gpu = cuda_make_array(l.scale_updates, n);
+
l.x_gpu = cuda_make_array(l.output, l.batch*out_h*out_w*n);
l.x_norm_gpu = cuda_make_array(l.output, l.batch*out_h*out_w*n);
}
@@ -305,7 +322,7 @@
void test_convolutional_layer()
{
- convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1, 0, 0);
+ convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1, 0, 0, 0);
l.batch_normalize = 1;
float data[] = {1,1,1,1,1,
1,1,1,1,1,
@@ -511,6 +528,11 @@
axpy_cpu(l.n, learning_rate/batch, l.bias_updates, 1, l.biases, 1);
scal_cpu(l.n, momentum, l.bias_updates, 1);
+ if(l.scales){
+ axpy_cpu(l.n, learning_rate/batch, l.scale_updates, 1, l.scales, 1);
+ scal_cpu(l.n, momentum, l.scale_updates, 1);
+ }
+
axpy_cpu(size, -decay*batch, l.weights, 1, l.weight_updates, 1);
axpy_cpu(size, learning_rate/batch, l.weight_updates, 1, l.weights, 1);
scal_cpu(size, momentum, l.weight_updates, 1);
--
Gitblit v1.10.0