Semantic training rfcr

operators.ml3d.semantic_training_rfcr(client, data_in_path='/data/files/', out_model_parameters_path='trained_model/model_1', class_names='1,2,3,4,5,6,7,8', feature_names='red,green,blue', point_names='x,y,z', label_name='classification', resolution=0.06, max_epochs=500, learning_rate=0.01, batch_size=10, learning_rate_decay=0.1, learning_momentum=0.98, learning_gradient_clip_norm=100, first_features_dim=128, instance_type='x2large')

semantic_training_rfcr( client,

data_in_path=’/data/files/’,

out_model_parameters_path=’trained_model/model_1’,

class_names=’1,2,3,4,5,6,7,8’,

feature_names=’red,green,blue’,

point_names=’x,y,z’,

label_name=’classification’,

resolution=0.06,

max_epochs=500,

learning_rate=0.01,

batch_size=10,

learning_rate_decay=0.1,

learning_momentum=0.98,

learning_gradient_clip_norm=100,

first_features_dim=128,

instance_type=’x2large’ )

Parameters:

• data_in_path – path to folder that contains the training data

• out_model_parameters_path – path to model

• class_names – comma separated list of class names. Class 0 is always given and is used to denote unlabeled points.

• feature_names – comma separated list of features that are provided

• point_names – comma separated list of point identifiers in (las/laz)

• label_name – label name for (las/laz)

• resolution – resolution of the subsampled point cloud

• max_epochs – maximum number of epochs

• learning_rate – learning rate

• batch_size – batch size

• learning_rate_decay – learning rate decay

• learning_momentum – learning momentum

• learning_gradient_clip_norm – learning gradient clip threshold

• first_features_dim – dimension of the first feature maps

• instance_type – type of cloud instance used for processing