1234567891011121314151617181920 |
- <?xml version="1.0"?>
- <!-- cascade_depth stores the depth of cascade of regressors used for training.
- tree_depth stores the depth of trees created as weak learners during gradient boosting.
- num_trees_per_cascade_level stores number of trees required per cascade level.
- learning_rate stores the learning rate for gradient boosting.This is required to prevent overfitting using shrinkage.
- oversampling_amount stores the oversampling amount for the samples.
- num_test_coordinates stores number of test coordinates to be generated as samples to decide for making the split.
- lambda stores the value used for calculating the probabilty which helps to select closer pixels for making the split.
- num_test_splits stores the number of test splits to be generated before making the best split.
- -->
- <opencv_storage>
- <cascade_depth>15</cascade_depth>
- <tree_depth>4</tree_depth>
- <num_trees_per_cascade_level>500</num_trees_per_cascade_level>
- <learning_rate>1.0000000149011612e-01</learning_rate>
- <oversampling_amount>20</oversampling_amount>
- <num_test_coordinates>400</num_test_coordinates>
- <lambda>1.0000000149011612e-01</lambda>
- <num_test_splits>20</num_test_splits>
- </opencv_storage>
|