From ed44d5b283e48b8d5c8a36f1b1cc788159d3f256 Mon Sep 17 00:00:00 2001 From: RobinMeersman Date: Tue, 25 Nov 2025 20:20:34 +0100 Subject: [PATCH] feat: datasets package --- CNN-model/datasets/EnWik9.py | 11 +++++++++++ 1 file changed, 11 insertions(+) create mode 100644 CNN-model/datasets/EnWik9.py diff --git a/CNN-model/datasets/EnWik9.py b/CNN-model/datasets/EnWik9.py new file mode 100644 index 0000000..6d56f52 --- /dev/null +++ b/CNN-model/datasets/EnWik9.py @@ -0,0 +1,11 @@ +from datasets import load_dataset +from os.path import curdir, join + +class EnWik9DataSet: + def __init__(self): + path = join(curdir, "data") + self.data = load_dataset("haukur/enwik9", cache_dir=path, split="train") + + + def __len__(self): + return len(self.data) \ No newline at end of file