NextCloud
/
dlib
mirror of https://github.com/davisking/dlib.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

Updated comments to reflect recent API changes.

Browse Source
pull/919/head
Davis King 7 years ago
parent 895d7874d3
commit 50de3da992
2 changed files with 6 additions and 6 deletions
Show Stats Download Patch File Download Diff File

6
examples/dnn_mmod_dog_hipsterizer.cpp
Unescape View File

@ -24,16 +24,16 @@
Additionally, the following training parameters were different during Additionally, the following training parameters were different during
training: The following lines in dnn_mmod_ex.cpp were changed from training: The following lines in dnn_mmod_ex.cpp were changed from
mmod_options options(face_boxes_train, 40*40); mmod_options options(face_boxes_train, 40,40);
trainer.set_iterations_without_progress_threshold(300); trainer.set_iterations_without_progress_threshold(300);
to the following when training the model used in this example: to the following when training the model used in this example:
mmod_options options(face_boxes_train, 80*80); mmod_options options(face_boxes_train, 80,80);
trainer.set_iterations_without_progress_threshold(8000); trainer.set_iterations_without_progress_threshold(8000);
Also, the random_cropper was left at its default settings, So we didn't Also, the random_cropper was left at its default settings, So we didn't
call these functions: call these functions:
cropper.set_chip_dims(200, 200); cropper.set_chip_dims(200, 200);
cropper.set_min_object_height(0.2); cropper.set_min_object_size(40,40);
The training data used to create the model is also available at The training data used to create the model is also available at
http://dlib.net/files/data/CU_dogs_fully_labeled.tar.gz http://dlib.net/files/data/CU_dogs_fully_labeled.tar.gz

6
examples/dnn_mmod_face_detection_ex.cpp
Unescape View File

@ -26,16 +26,16 @@
Additionally, the following training parameters were different during Additionally, the following training parameters were different during
training: The following lines in dnn_mmod_ex.cpp were changed from training: The following lines in dnn_mmod_ex.cpp were changed from
mmod_options options(face_boxes_train, 40*40); mmod_options options(face_boxes_train, 40,40);
trainer.set_iterations_without_progress_threshold(300); trainer.set_iterations_without_progress_threshold(300);
to the following when training the model used in this example: to the following when training the model used in this example:
mmod_options options(face_boxes_train, 80*80); mmod_options options(face_boxes_train, 80,80);
trainer.set_iterations_without_progress_threshold(8000); trainer.set_iterations_without_progress_threshold(8000);
Also, the random_cropper was left at its default settings, So we didn't Also, the random_cropper was left at its default settings, So we didn't
call these functions: call these functions:
cropper.set_chip_dims(200, 200); cropper.set_chip_dims(200, 200);
cropper.set_min_object_height(0.2); cropper.set_min_object_size(40,40);
The training data used to create the model is also available at The training data used to create the model is also available at
http://dlib.net/files/data/dlib_face_detection_dataset-2016-09-30.tar.gz http://dlib.net/files/data/dlib_face_detection_dataset-2016-09-30.tar.gz

Write Preview
Loading…
Cancel
Save