graphorge.gnn_base_model.predict.prediction

Prediction of Graph Neural Network model.

Functions

predict

Make predictions with Graph Neural Network model for given dataset.

make_predictions_subdir

Create model predictions subdirectory.

save_sample_predictions

Save model prediction results for given sample.

load_sample_predictions

Load model prediction results for given sample.

compute_sample_prediction_loss

Compute loss of sample output features prediction.

seed_worker

Set workers seed in PyTorch data loaders to preserve reproducibility.

write_prediction_summary_file

Write summary data file for model prediction process.

Functions

compute_sample_prediction_loss(model, ...[, ...])	Compute loss of sample output features prediction.
get_pytorch_loss(loss_type, **kwargs)	Get PyTorch loss function.
load_sample_predictions(sample_prediction_path)	Load model prediction results for given sample.
make_directory(directory[, is_overwrite])	Create a directory.
make_predictions_subdir(predict_directory)	Create model predictions subdirectory.
predict(dataset, model_directory[, model, ...])	Make predictions with Graph Neural Network model for given dataset.
save_sample_predictions(predictions_dir, ...)	Save model prediction results for given sample.
seed_worker(worker_id)	Set workers seed in PyTorch data loaders to preserve reproducibility.
write_prediction_summary_file(...)	Write summary data file for model prediction process.
write_summary_file(summary_directory[, ...])	Write summary data file with provided keyword-based parameters.

Classes

GNNEPDBaseModel(n_node_in, n_node_out, ...)

GNN Encoder-Processor-Decoder base model.