preparingToSave: Prepare 'DigitalDLSorter' object to be saved as an RDA file

In digitalDLSorteR: Deconvolution of Bulk RNA-Seq Data Based on Deep Learning

Prepare DigitalDLSorter object to be saved as an RDA file

Description

Prepare a DigitalDLSorter object that has a DigitalDLSorterDNN object with a trained DNN model. keras models cannot be stored natively as R objects (e.g. RData or RDS files). By saving the structure as a JSON-like character object and the weights as a list, it is possible to retrieve the model and make predictions. Note: with this option, the state of optimizer is not saved, only the architecture and weights.

Usage

preparingToSave(object)

Arguments

object

DigitalDLSorter object with the trained.data slot.

Details

It is possible to save the entire model as an HDF5 file with the saveTrainedModelAsH5 function and to load it into a DigitalDLSorter object with the loadTrainedModelFromH5 function.

It is also possible to save a DigitalDLSorter object as an RDS file with the saveRDS function without any preparation.

Value

A DigitalDLSorter or DigitalDLSorterDNN object with its trained keras model transformed from a keras.engine.sequential.Sequential class into a list with the architecture as a JSON-like character object and the weights as a list.

See Also

saveRDS saveTrainedModelAsH5

digitalDLSorteR documentation built on Sept. 13, 2024, 5:06 p.m.