turi::style_transfer::Checkpoint Class Reference

#include <toolkits/style_transfer/st_model_trainer.hpp>

Public Member Functions
virtual std::unique_ptr< ModelTrainer >	CreateModelTrainer () const =0
virtual neural_net::model_spec	ExportToCoreML () const =0

Detailed Description

A representation of all the parameters needed to reconstruct a model.

Definition at line 166 of file st_model_trainer.hpp.

Member Function Documentation

CreateModelTrainer()

virtual std::unique_ptr<ModelTrainer> turi::style_transfer::Checkpoint::CreateModelTrainer ( ) const

pure virtual

Loads the checkpoint into an active ModelTrainer instance.

Implemented in turi::style_transfer::ResNet16Checkpoint.

ExportToCoreML()

virtual neural_net::model_spec turi::style_transfer::Checkpoint::ExportToCoreML ( ) const

pure virtual

Returns the CoreML spec corresponding to the current model.

The first layer of the model should have a single input: the image to stylize. The last layer of the model should have a single output: the stylized image.

Implemented in turi::style_transfer::ResNet16Checkpoint.

---

The documentation for this class was generated from the following file:

• toolkits/style_transfer/st_model_trainer.hpp