From a99050f0c8cb0315fa31e3d1fa3e38594fe5e40a Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 08 Dec 2014 04:16:21 +0000
Subject: [PATCH] Some fixes to momentum
---
src/convolutional_layer.c | 8 ++++----
1 files changed, 4 insertions(+), 4 deletions(-)
diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
index 4ca6104..5b4e0b5 100644
--- a/src/convolutional_layer.c
+++ b/src/convolutional_layer.c
@@ -64,10 +64,10 @@
layer->bias_updates = calloc(n, sizeof(float));
float scale = 1./(size*size*c);
scale = .01;
- for(i = 0; i < c*n*size*size; ++i) layer->filters[i] = scale*2*(rand_uniform()-.5);
+ for(i = 0; i < c*n*size*size; ++i) layer->filters[i] = scale*rand_normal();
for(i = 0; i < n; ++i){
//layer->biases[i] = rand_normal()*scale + scale;
- layer->biases[i] = .5;
+ layer->biases[i] = .01;
}
int out_h = convolutional_out_height(*layer);
int out_w = convolutional_out_width(*layer);
@@ -204,7 +204,7 @@
axpy_cpu(layer.n, layer.learning_rate, layer.bias_updates, 1, layer.biases, 1);
scal_cpu(layer.n, layer.momentum, layer.bias_updates, 1);
- scal_cpu(size, 1.-layer.learning_rate*layer.decay, layer.filters, 1);
+ axpy_cpu(size, -layer.decay, layer.filters, 1, layer.filter_updates, 1);
axpy_cpu(size, layer.learning_rate, layer.filter_updates, 1, layer.filters, 1);
scal_cpu(size, layer.momentum, layer.filter_updates, 1);
}
@@ -409,7 +409,7 @@
axpy_ongpu(layer.n, layer.learning_rate, layer.bias_updates_cl, 1, layer.biases_cl, 1);
scal_ongpu(layer.n,layer.momentum, layer.bias_updates_cl, 1);
- scal_ongpu(size, 1.-layer.learning_rate*layer.decay, layer.filters_cl, 1);
+ axpy_ongpu(size, -layer.decay, layer.filters_cl, 1, layer.filter_updates_cl, 1);
axpy_ongpu(size, layer.learning_rate, layer.filter_updates_cl, 1, layer.filters_cl, 1);
scal_ongpu(size, layer.momentum, layer.filter_updates_cl, 1);
pull_convolutional_layer(layer);
--
Gitblit v1.10.0