February 2018
Intermediate to advanced
262 pages
6h 59m
English
Content preview from Deep Learning with PyTorch
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
Start your free trial
Data redundancy
Duplicates are common in data. Care should be taken so that the data present in the training, validation, and test sets are unique. If there are duplicates, then the model may not generalize well on unseen data.