Segmentation YAML References

Segmentation training jobs use the keys listed in the table below.

dataset

The following parameters can be used to load datasets.

train_split_key

• Type: String
• Default: Train
• Choices: train/test/dev
• Description: The name given to the data split that will be used for training.

test_split_key

• Type: String
• Default: dev
• Choices: train/test/dev
• Description: The name given to the data split that will be used for testing.

val_split_key

• Type: String
• Default: dev
• Choices: train/test/dev
• Description: The name given to the data split that will be used for validation.

train

The following parameters can be used to define model hyperparameters.

batch_size

• Type: Integer
• Default: 8
• Value Range: 1 <= batch_size
• Description: Number of examples/images in each training batch. The minimum batch size is 1.

epoch

• Type: Integer
• Default: 200
• Value Range: 1 <= epoch <=1000
• Description: The number of epochs to train the model. If you turn on early stopping, the actual training epoch may be smaller.

learning_rate

• Type: Float
• Default: 0.0001
• Value Range: 0 < learning_rate < 1.0
• Description: The learning rate used to update the weights.

validation_run_freq

• Type: Integer
• Default: 1
• ValueRange: 1 <= validation_run_freq
• Description: Number of epochs between validation runs.

early_stop

• Type: Object
• Description: Configuration for stopping training when a monitored metric has stopped improving.
• Properties:
  • min_delta
    • Type: Float
    • Default: 0.01
    • Description: Minimum change in the monitored quantity to qualify as an improvement.
  • min_epochs
    • Type: Integer
    • Default: 40
    • Description: Number of epochs with no improvement after which training will be stopped.

auto_tuning

• Type: Object
• Description: Configuration for automated hyperparameter tuning.
• Properties:
  • class_weights
    • Type: Boolean
    • Default: True
    • Description: Whether to use automated class weight tuning with pixel counts in the train and valid splits.
  • class_weights_method
    • Type: Integer
    • Default: 0
    • Choices: 0, 1, 2
    • Description: Which method to use to tune class weights
      debug
    • Type: Boolean
    • Default: False
    • Description: Whether to turn on the debug mode of auto-tuning process.

model

The following parameters can be used to specify which Segmentation model to use.

avi

• Type: Object
• Description: Specifies the python library from where the model is implemented.
• Properties:
  • Unet:
    • Type: Object
    • Description: The UNet parser class.
  • Properties:
    • backbone_name
      • Type: string
        • Default: ResNet34
      • Choices:
        • ResNet18
          • ResNet34
          • ResNet50
        • Description: The backbone to use in RetinaNet.
    • output_depth
      • Type: integer
      • Value Range: 1 <= output_depth
      • Description: The number of classes. Number of defective class plus OK class.
    • input_shape
      • Type: Array
      • Description: Shape of the images.
    • Items:
      • item_1
        • Default: 512
          • Value Range: 1 <= item_1 <= 1024
          • Multiply of: 32
          • Description: Height of the image.
      • item_2
        • Default: 512
          • ValueRange: 1 <= item_2 <= 1024
          • Multiply of: 32
          • Description: Width of the image.
      • item_3
        • Default: 3
          • Value Range: 1 <= item_3 <= 4
          • Description: This is the channels of the image (1 for grayscale, 2 for grayscale + alpha, 3 for RGB, 4 for RGB + alpha).
      • activation
        • Type: String
        • Default: Softmax
        • Choices:
          • Softmax
          • Sigmoid
        • ValueRange: 0 <= nms_threshold <= 1
        • Description: Last layer activation function.
      • encoder_weights
        • Type: String | Null
        • Default: Imagenet
        • Choices:
          • null
          • imagenet
        • Description: Load imagenet pre-trained weights to the backbone or randomly
          decoder_block_type.
        • Type: String
        • Default: Transpose
        • Choices:
          • Transpose
          • Upsampling
        • Descriptions: Type of the decoder block type in segmentation models repo.

loss

The following parameters specify the loss functions to use for the Classification and regression head of the model.

CategoricalCrossEntropy

• Type: Object
• Description: CategoricalCrossEntropy
• Properties:
  • weights
    • Type: Union[float, array[float]]
    • Default: 7.0
    • Value Range: 0 <= weights
    • Description: Weights to apply to each label in the loss function.
    • Item Type: float
  • from_logits
    • Type: Boolean
    • Default: false
    • Description: Whether the loss is computed from the logits of the network or from sigmoid activations.

BinaryCrossEntropy

• Type: Object
• Description: CategoricalCrossEntropy
• Properties:
  • weights
    • Type: Union[float, array[float]]
    • Default: 7.0
    • Value Range: 0 <= weights
    • Description: Weights to apply to each label in the loss function.
    • Item Type: float
  • from_logits
    • Type: Boolean
    • Default: False
    • Description: Whether the loss is computed from the logits of the network or from sigmoid activations.

eval

The following parameters can be used in the evaluation phase:

postprocessing

• Type: Object
• Description: The configuration for post-processing steps.
• Properties:
  • output_type
    • Type: String
    • Default: Segmentation
    • Choices:
      • Classification
      • Segmentation
    • Description: The kind of output after preprocessing
  • iou_threshold
    • Type: float
    • Default: 0.5
    • Value Range: 0 <= iou_threshold <= 1
    • Description: The IoU threshold to determine True Positive and False Positive.
  • transforms
    • Type: array | null
    • Items:
      • Type: Post-processing transforms
    • Description: The transformations to apply in post-processing steps to both ground truth and prediction.
  • gt_transforms
    • Type: array | null
    • Items:
      • Type: Post-processing transforms
    • Description: The transformations to apply in post-processing steps to ground truth only.
      pred_transforms
    • Type: array | null
    • Items:
      • Type: Post-processing transforms
      • Description: The transformations to apply in post-processing steps to prediction only.