par_list={"dataset_name": dataset_name,
"n_fold": n_folds,
"learning_rate": lr,
"drop_prob": drop_prob,
"weight_decay": weight_decay,
"batch_size": batch_size,
"n_hidden": n_units,
"test_epoch": test_epoch,
"output": output,
"max_k": max_k})
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
criterion = torch.nn.NLLLoss()
dataset_cv_splits = getcross_validation_split(dataset_path, dataset_name, n_folds, batch_size)
for split_id, split in enumerate(dataset_cv_splits):
loader_train = split[0]
loader_test = split[1]
loader_valid = split[2]
model = PGC_GNN(loader_train.dataset.num_features, n_units, n_units,
n_classes, drop_prob, k=max_k,
output=output).to(device)
model_impl = modelImplementation_GraphBinClassifier(model, lr, criterion,
device).to(device)
model_impl.set_optimizer(weight_decay=weight_decay)
model_impl.train_test_model(split_id, loader_train, loader_test, loader_valid,
"batch_size": batch_size,
"n_hidden": n_units,
"test_epoch": test_epoch,
"output": output,
"max_k": max_k
})
device = torch.device(
'cuda' if torch.cuda.is_available(
) else 'cpu')
criterion = torch.nn.NLLLoss()
dataset_cv_splits = getcross_validation_split(
dataset_path,
dataset_name,
n_folds,
batch_size,
use_node_attr=True)
for split_id, split in enumerate(
dataset_cv_splits):
loader_train = split[0]
loader_test = split[1]
loader_valid = split[2]
model = PGC_GNN(
loader_train.dataset.num_features,
n_units,
n_units,
n_classes,
drop_prob,
k=max_k,
