In NLP, batches often need sequences of equal length. Given a list of token ID sequences (lists of ints), pad them with a special pad_value to match the length of the longest sequence.
Input: seqs = [[1, 2], [3, 4, 5], [6]], pad_value = 0, max_len = None
Output: [[1, 2, 0], [3, 4, 5], [6, 0, 0]]
Explanation: The longest sequence has length 3, so shorter sequences are padded on the right.
Input: seqs = [[1, 2, 3], [4]], pad_value = -1, max_len = None
Output: [[1, 2, 3], [4, -1, -1]]
When max_len is None, derive it from the longest sequence and use zero for an empty collection.
Initialize the output with np.full, then copy each truncated sequence into its row.
Accepts: array
Accepts: number
Accepts: any
In NLP, batches often need sequences of equal length. Given a list of token ID sequences (lists of ints), pad them with a special pad_value to match the length of the longest sequence.
Input: seqs = [[1, 2], [3, 4, 5], [6]], pad_value = 0, max_len = None
Output: [[1, 2, 0], [3, 4, 5], [6, 0, 0]]
Explanation: The longest sequence has length 3, so shorter sequences are padded on the right.
Input: seqs = [[1, 2, 3], [4]], pad_value = -1, max_len = None
Output: [[1, 2, 3], [4, -1, -1]]
When max_len is None, derive it from the longest sequence and use zero for an empty collection.
Initialize the output with np.full, then copy each truncated sequence into its row.
Accepts: array
Accepts: number
Accepts: any