OrgLion-ML
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Releases Wiki Activity

Minor cleanup

This commit is contained in:
Davis King 2017-02-09 12:38:39 -05:00
parent 57ca3e5459
commit 45d047de80
1 changed files with 7 additions and 6 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
examples/dnn_metric_learning_on_images_ex.cpp
View File

@ -14,9 +14,10 @@
space it's very easy to do face recognition with some kind of k-nearest
neighbor classifier.
In this example we will use the ResNet-34 network from the dnn_imagenet_ex.cpp
example to learn to map images into some vector space where pictures of
the same person are close and pictures of different people are far apart.
In this example we will use a version of the ResNet network from the
dnn_imagenet_ex.cpp example to learn to map images into some vector space where
pictures of the same person are close and pictures of different people are far
apart.
You might want to read the simpler introduction to the deep metric learning
API, dnn_metric_learning_ex.cpp, before reading this example. You should
@ -112,7 +113,7 @@ void load_mini_batch (
}
}
// You might want to do some data augmentation at this point. Here we so some simple
// You might want to do some data augmentation at this point. Here we do some simple
// color augmentation.
for (auto&& crop : images)
disturb_colors(crop,rnd);
@ -173,7 +174,7 @@ using net_type = loss_metric<fc_no_bias<128,avg_pool_everything<
level3<
level4<
max_pool<3,3,2,2,relu<bn_con<con<32,7,7,2,2,
input_rgb_image_sized<150>
input_rgb_image
>>>>>>>>>>>>;
// testing network type (replaced batch normalization with fixed affine transforms)
@ -184,7 +185,7 @@ using anet_type = loss_metric<fc_no_bias<128,avg_pool_everything<
alevel3<
alevel4<
max_pool<3,3,2,2,relu<affine<con<32,7,7,2,2,
input_rgb_image_sized<150>
input_rgb_image
>>>>>>>>>>>>;
// ----------------------------------------------------------------------------------------