Model architectures 🏛
Metrics 📊
Solvers / Optimizers 🧮
Scheduler ⏰
Training parameters
Augmentations
DEPLOYMENT
Random
A type of data split strategy
In this type of split, the input data in randomly assigned to the test, train and validation set according to the given sizes.
The split is done without replacement, which means that the validation, test and training set doesn't contain the same data.
Random split is the simplest split strategy and is effective in most of the cases.
Last modified 5mo ago
Copy link