This repository has been archived on 2025-12-23. You can view files and clone it, but you cannot make any changes to it's state, such as pushing and creating new issues, pull requests or comments.
2025ML-project-neural_compr.../CNN-model/data_utils.py
2025-11-08 17:40:49 +01:00

11 lines
357 B
Python

import torch
from torch.utils.data import TensorDataset
def make_context_pairs(data: bytes, context_length: int) -> TensorDataset:
data = torch.tensor(list(data), dtype=torch.uint8)
sample_count = data.shape[0] - context_length
x = data.unfold(0, context_length, 1)[:sample_count]
y = data[context_length:]
return TensorDataset(x, y)