pyabsa.tasks._Archive.ProteinRegression.instructor.proteinr_instructor

Module Contents

Classes

ProteinRTrainingInstructor

class pyabsa.tasks._Archive.ProteinRegression.instructor.proteinr_instructor.ProteinRTrainingInstructor(config)

Bases: pyabsa.framework.instructor_class.instructor_template.BaseTrainingInstructor

_init_misc()

Initialize miscellaneous settings specific to the subclass implementation. This method should be implemented in a subclass.

_cache_or_load_dataset()

Cache or load the dataset. This method should be implemented in a subclass.

_evaluate_acc_f1(test_dataloader)

Evaluate the accuracy and F1 score of the model. This method should be implemented in a subclass.

_load_dataset_and_prepare_dataloader()

Load the dataset and prepare the dataloader. This method should be implemented in a subclass.

reload_model(ckpt='./init_state_dict.bin')

_prepare_dataloader()

Prepares the data loaders for training, validation, and testing.

_train(criterion)

Train the model on a given criterion.

Parameters:

criterion – The loss function used to train the model.

Returns:

If there is only one validation dataloader, return the training results. If there are more than one validation dataloaders, perform k-fold cross-validation and return the results.

_train_and_evaluate(criterion)

Train and evaluate the model. This method should be implemented in a subclass.

_k_fold_train_and_evaluate(criterion)

Train and evaluate the model using k-fold cross validation. This method should be implemented in a subclass.

_evaluate_r2(test_dataloader, criterion)

run()