PatientLevelPrediction (version 4.3.10)

setCNNTorch: Create setting for CNN model with python

Description

Create setting for CNN model with python

Usage

setCNNTorch(
  nbfilters = c(16, 32),
  epochs = c(20, 50),
  seed = 0,
  class_weight = 0,
  type = "CNN"
)

Arguments

nbfilters

The number of filters

epochs

The number of epochs

seed

A seed for the model

class_weight

The class weight used for imbalanced data: 0: Inverse ratio between positives and negatives -1: Focal loss

type

It can be normal 'CNN', 'CNN_LSTM', CNN_MLF' with multiple kernels with different kernel size, 'CNN_MIX', 'ResNet' and 'CNN_MULTI'

Examples

# NOT RUN {
model.cnnTorch <- setCNNTorch()
# }