Create validation sets by splitting your custom PyTorch datasets easily

splitting-datasets.py

import string
from torch.utils.data import DataLoader, random_split
from datasets import TESNamesDataset

data_root = '/home/syafiq/Data/tes-names/'
charset = string.ascii_letters + "-' "
length = 30

dataset = TESNamesDataset(data_root, charset, length)
trainset, valset = random_split(dataset, [15593, 3898])

train_loader = DataLoader(trainset, batch_size=10, shuffle=True, num_workers=2)
val_loader = DataLoader(valset, batch_size=10, shuffle=True, num_workers=2)

for i, batch in enumerate(train_loader):
    print(i, batch)

for i, batch in enumerate(val_loader):
    print(i, batch)