hookeai.model_architectures.rnn_base_model.train.training¶

Training of recurrent neural network model.

Classes¶

Functions

`data_scaler_transform`(model, tensor, ...[, mode])	Perform data scaling operation on features PyTorch tensor.
`fit_data_scalers`(model, dataset[, ...])	Fit model data scalers.
`get_learning_rate_scheduler`(optimizer, ...)	Get PyTorch optimizer learning rate scheduler.
`get_model_summary`(model[, input_data, ...])	Get summary of PyTorch model.
`get_pytorch_loss`(loss_type, **kwargs)	Get PyTorch-based loss function.
`get_pytorch_optimizer`(algorithm, params, ...)	Get PyTorch optimizer.
`get_time_series_data_loader`(dataset[, ...])	Get time series data set data loader.
`load_model_state`(model[, model_load_state, ...])	Load model state from file.
`predict`(dataset, model_directory[, model, ...])	Make predictions with recurrent neural network model for given dataset.
`save_loss_history`(model, n_max_epochs, ...)	Save training process loss history record.
`save_model_state`(model[, state_type, epoch, ...])	Save model state to file.
`save_training_state`(model, optimizer, state_type)	Save model and optimizer states at given training epoch.
`seed_worker`(worker_id)	Set workers seed in PyTorch data loaders to preserve reproducibility.
`train_model`(n_max_epochs, dataset, ...[, ...])	Training of recurrent neural network model.
`write_training_summary_file`(device_type, ...)	Write summary data file for model training process.

Classes

`EarlyStopper`(validation_dataset[, ...])	Early stopping procedure (implicit regularizaton).
`GRURNNModel`(n_features_in, n_features_out, ...)	Multi-layer gated recurrent unit (GRU) recurrent neural network model.