From 352ae7e65b6a74bcd768aa88b866a44c713284c8 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 26 Oct 2016 15:35:44 +0000
Subject: [PATCH] ADAM
---
src/parser.c | 23 ++++++++++++++++++++---
1 files changed, 20 insertions(+), 3 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index a27d245..44ba1c4 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -111,6 +111,7 @@
int c;
int index;
int time_steps;
+ network net;
} size_params;
local_layer parse_local(list *options, size_params params)
@@ -156,9 +157,14 @@
int binary = option_find_int_quiet(options, "binary", 0);
int xnor = option_find_int_quiet(options, "xnor", 0);
- convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,padding,activation, batch_normalize, binary, xnor);
+ convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,padding,activation, batch_normalize, binary, xnor, params.net.adam);
layer.flipped = option_find_int_quiet(options, "flipped", 0);
layer.dot = option_find_float_quiet(options, "dot", 0);
+ if(params.net.adam){
+ layer.B1 = params.net.B1;
+ layer.B2 = params.net.B2;
+ layer.eps = params.net.eps;
+ }
return layer;
}
@@ -221,6 +227,8 @@
int groups = option_find_int_quiet(options, "groups",1);
softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
layer.temperature = option_find_float_quiet(options, "temperature", 1);
+ char *tree_file = option_find_str(options, "tree", 0);
+ if (tree_file) layer.softmax_tree = read_tree(tree_file);
return layer;
}
@@ -480,6 +488,13 @@
net->batch *= net->time_steps;
net->subdivisions = subdivs;
+ net->adam = option_find_int_quiet(options, "adam", 0);
+ if(net->adam){
+ net->B1 = option_find_float(options, "B1", .9);
+ net->B2 = option_find_float(options, "B2", .999);
+ net->eps = option_find_float(options, "eps", .000001);
+ }
+
net->h = option_find_int_quiet(options, "height",0);
net->w = option_find_int_quiet(options, "width",0);
net->c = option_find_int_quiet(options, "channels",0);
@@ -562,6 +577,7 @@
params.inputs = net.inputs;
params.batch = net.batch;
params.time_steps = net.time_steps;
+ params.net = net;
size_t workspace_size = 0;
n = n->next;
@@ -598,6 +614,7 @@
l = parse_detection(options, params);
}else if(lt == SOFTMAX){
l = parse_softmax(options, params);
+ net.hierarchy = l.softmax_tree;
}else if(lt == NORMALIZATION){
l = parse_normalization(options, params);
}else if(lt == BATCHNORM){
@@ -776,7 +793,7 @@
{
#ifdef GPU
if(net.gpu_index >= 0){
- cuda_set_device(net.gpu_index);
+ cuda_set_device(net.gpu_index);
}
#endif
fprintf(stderr, "Saving weights to %s\n", filename);
@@ -944,7 +961,7 @@
{
#ifdef GPU
if(net->gpu_index >= 0){
- cuda_set_device(net->gpu_index);
+ cuda_set_device(net->gpu_index);
}
#endif
fprintf(stderr, "Loading weights from %s...", filename);
--
Gitblit v1.10.0