You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Hi! I have some graphs and I want to put some of them into training set and some into test set at runtime.
Now I create two datasets, one for training and one for testing. train_dataset = MyOwnDataset('dataset_train') test_dataset = MyOwnDataset('dataset_test')
But these requires building dataset everytime I change the train and test split.
Is there any way to put all graphs into one dataset and obtain training set and test set at runtime?
P.S. train_dataset= dataset[0:10] + dataset[20:30] is not a good choice because this will make train_dataset a ConcatDataset object and can not directly access the properties of Pyg datasets like dataset.x
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
-
Hi! I have some graphs and I want to put some of them into training set and some into test set at runtime.
Now I create two datasets, one for training and one for testing.
train_dataset = MyOwnDataset('dataset_train')
test_dataset = MyOwnDataset('dataset_test')
But these requires building dataset everytime I change the train and test split.
Is there any way to put all graphs into one dataset and obtain training set and test set at runtime?
P.S. train_dataset= dataset[0:10] + dataset[20:30] is not a good choice because this will make train_dataset a ConcatDataset object and can not directly access the properties of Pyg datasets like dataset.x
Beta Was this translation helpful? Give feedback.
All reactions