google_ml: Deep Learning Classification with Google Hyper-parameter...

In tianwei-zhang/easyAI: Democratize AI

Usage

google_ml(x, y, num_layer, max_units, start_unit, max_dropout, min_dropout,
  max_lr, min_lr, validation_split, num_epoch, num_patience, machine_type,
  target_type)

Arguments

x	training feature matrix
y	target matrix
num_layer	a vector of integers indicating the number of hidden layers to test. Default to seq(1,5,1)
max_units	the maximum number of hidden units in a layer. Default to an optimized value based on data
start_unit	the minimum number of hiddent units in a layer. Default to 5
max_dropout	A number between 0 and 1 indicating the maximum dropoff rate in a layer. Default to 0.2
min_dropout	A number between 0 and 1 indicating the minimum dropoff rate in a layer. Default to 0
max_lr	maximum learning rate in a run. Default to 0.2
min_lr	minimum learning rate in a run. Default to 0.001
validation_split	\item num_epochnumber of epoches to go through during training \item num_patiencenumber of patience in early stopping criteria \item machine_typetype of server to use. Could be standard, standard_gpu, standard_p100. For more visit https://cloud.google.com/ml-engine/docs/training-overview#machine_type_table \item target_typeeither classification or regression

returns a list object with two values: train_performance: A table with parameters and model performance metrics best_model: a keras_model object with the optimal parameters Deep Learning Classification with Google Hyper-parameter Tuning

tianwei-zhang/easyAI documentation built on May 14, 2019, 12:48 p.m.