Training Parameters

Training Parameters allow customization of the basic parameters of your training. All of the parameters below are supported for both TensorFlow and PyTorch.

1. Epochs

An epoch is a measure of the number of times the entire dataset is passed through the model during training. The number of epochs you should use depends on the complexity of your model and the size of your dataset. Here, the default number of epochs is 10, but you can change it to any number you like by using the following code:

trainingObject.epochs(100)

2. Cycles

A cycle is a complete pass through the training and validation datasets. The number of cycles you use will depend on the size of your dataset and the number of epochs. An experiment is finished when all of the cycles have completed. Here, the default number of cycles is 1, but you can change it to any number you like by using the following code:

trainingObject.cycles(10)

3. Batch Size

The batch size is the number of samples that are passed through the model at one time. The batch size is used to determine the number of times the model's weights are updated. The default batch size is based on the size of the dataset and the number of classes. If the batch size is too small or too large, an error message will be displayed.

trainingObject.batchSize(16)

4. Validation Split

The validation split is the percentage of the dataset that is set aside for use as a validation set during training. The validation set is used to evaluate the model's performance after each cycle. The default validation split is based on the size of the dataset and the number of classes, but it can be changed to any value between 0 and 1. If the value is too small or too large, an error message will be displayed.

trainingObject.validation_split(0.2)