Semantic Segmentation Hyperparameters

The following tables list the hyperparameters supported by the Amazon SageMaker semantic segmentation algorithm for network architecture, data inputs, and training. You specify Semantic Segmentation for training in the AlgorithmName of the CreateTrainingJob request.

Network Architecture Hyperparameters

Parameter Name	Description
backbone	The backbone to use for the algorithm’s encoder component. Optional Valid values: `resnet-50`, `resnet-101` Default value: `resnet-50`
use_pretrained_model	Whether a pretrained model is to be used for the backbone. Optional Valid values: `True`, `False` Default value: `True`
algorithm	The algorithm to use for semantic segmentation. Optional Valid values: [See the AWS documentation website for more details] Default value: `fcn`

Data Hyperparameters

Parameter Name	Description
num_classes	The number of classes to segment. Required Valid values: 2 ≤ positive integer ≤ 254
num_training_samples	The number of samples in the training data. The algorithm uses this value to set up the learning rate scheduler. Required Valid values: positive integer
crop_size	The image size for input images. We rescale the input image to a square image to this `crop_size`. We do this by rescaling the shorter side to match this parameter while maintaining the aspect ratio, and then take a random crop along the longer side. Optional Valid values: positive integer > 16 Default value: 480

Training Hyperparameters

Parameter Name	Description
early_stopping	Whether to use early stopping logic during training. Optional Valid values: `True`, `False` Default value: `False`
early_stopping_min_epochs	The minimum number of epochs that must be run. Optional Valid values: integer Default value: 5
early_stopping_patience	The number of epochs that meet the tolerance for lower performance before the algorithm enforces an early stop. Optional Valid values: integer Default value: 4
early_stopping_tolerance	If the relative improvement of the score of the training job, the mIOU, is smaller than this value, early stopping considers the epoch as not improved. This is used only when `early_stopping` = `True`. Optional Valid values: 0 ≤ float ≤ 1 Default value: 0.0
epochs	The number of epochs with which to train. Optional Valid values: positive integer Default value: 30
gamma1	The decay factor for the moving average of the squared gradient for `rmsprop`. Used only for `rmsprop`. Optional Valid values: 0 ≤ float ≤ 1 Default value: 0.9
gamma2	The momentum factor for `rmsprop`. Optional Valid values: 0 ≤ float ≤ 1 Default value: 0.9
learning_rate	The initial learning rate. Optional Valid values: 0 < float ≤ 1 Default value: 0.001
lr_scheduler	The shape of the learning rate schedule that controls its decrease over time. Optional Valid values: [See the AWS documentation website for more details] Default value: `poly`
mini_batch_size	The batch size for training. Using a large `mini_batch_size` usually results in faster training, but it might cause you to run out of memory. Memory usage is affected by the values of the `mini_batch_size` and `image_shape` parameters, and the backbone architecture. Optional Valid values: positive integer Default value: 4
momentum	The momentum for the `sgd` optimizer. When you use other optimizers, the semantic segmentation algorithm ignores this parameter. Optional Valid values: 0 < float ≤ 1 Default value: 0.9
optimizer	The type of optimizer. For more information about an optimizer, choose the appropriate link: [See the AWS documentation website for more details] Optional Valid values: `adam`, `adagrad`, `nag`, `rmsprop`, `sgd` Default value: `sgd`
validation_mini_batch_size	The batch size for validation. A large `mini_batch_size` usually results in faster training, but it might cause you to run out of memory. Memory usage is affected by the values of the `mini_batch_size` and `image_shape` parameters, and the backbone architecture. [See the AWS documentation website for more details] Optional Valid values: positive integer Default value: 4
weight_decay	The weight decay coefficient for the `sgd` optimizer. When you use other optimizers, the algorithm ignores this parameter. Optional Valid values: 0 < float < 1 Default value: 0.0001