Split

Split Dataset¶

After you import your dataset, you can split it into train, validation and test sets.

Load Dataset¶

In [1]:

from waffle_hub.dataset import Dataset

dataset = Dataset.load(name="mnist_coco")

from waffle_hub.dataset import Dataset dataset = Dataset.load(name="mnist_coco")

/home/lhj/anaconda3/envs/waffle/lib/python3.9/site-packages/tqdm/auto.py:21: TqdmWarning: IProgress not found. Please update jupyter and ipywidgets. See https://ipywidgets.readthedocs.io/en/stable/user_install.html
  from .autonotebook import tqdm as notebook_tqdm

Split Dataset¶

In [3]:

dataset.split(train_ratio=0.8, val_ratio=0.2)
train_ids, val_ids, test_ids, unlabeled_ids = dataset.get_split_ids()

dataset.split(train_ratio=0.8, val_ratio=0.2) train_ids, val_ids, test_ids, unlabeled_ids = dataset.get_split_ids()

In [4]:

len(train_ids), len(val_ids), len(test_ids), len(unlabeled_ids)

len(train_ids), len(val_ids), len(test_ids), len(unlabeled_ids)

Out[4]:

(79, 21, 21, 0)