ImageModelSettingsObjectDetection Class

Definition

Settings used for training the model. For more information on the available settings please visit the official documentation: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-auto-train-image-models.

public class ImageModelSettingsObjectDetection : Azure.ResourceManager.MachineLearning.Models.ImageModelSettings, System.ClientModel.Primitives.IJsonModel<Azure.ResourceManager.MachineLearning.Models.ImageModelSettingsObjectDetection>, System.ClientModel.Primitives.IPersistableModel<Azure.ResourceManager.MachineLearning.Models.ImageModelSettingsObjectDetection>
public class ImageModelSettingsObjectDetection : Azure.ResourceManager.MachineLearning.Models.ImageModelSettings
type ImageModelSettingsObjectDetection = class
    inherit ImageModelSettings
    interface IJsonModel<ImageModelSettingsObjectDetection>
    interface IPersistableModel<ImageModelSettingsObjectDetection>
type ImageModelSettingsObjectDetection = class
    inherit ImageModelSettings
Public Class ImageModelSettingsObjectDetection
Inherits ImageModelSettings
Implements IJsonModel(Of ImageModelSettingsObjectDetection), IPersistableModel(Of ImageModelSettingsObjectDetection)
Public Class ImageModelSettingsObjectDetection
Inherits ImageModelSettings
Inheritance
ImageModelSettingsObjectDetection
Implements

Constructors

ImageModelSettingsObjectDetection()

Initializes a new instance of ImageModelSettingsObjectDetection.

Properties

AdvancedSettings

Settings for advanced scenarios.

(Inherited from ImageModelSettings)
AmsGradient

Enable AMSGrad when optimizer is 'adam' or 'adamw'.

(Inherited from ImageModelSettings)
Augmentations

Settings for using Augmentations.

(Inherited from ImageModelSettings)
Beta1

Value of 'beta1' when optimizer is 'adam' or 'adamw'. Must be a float in the range [0, 1].

(Inherited from ImageModelSettings)
Beta2

Value of 'beta2' when optimizer is 'adam' or 'adamw'. Must be a float in the range [0, 1].

(Inherited from ImageModelSettings)
BoxDetectionsPerImage

Maximum number of detections per image, for all classes. Must be a positive integer. Note: This settings is not supported for the 'yolov5' algorithm.

BoxScoreThreshold

During inference, only return proposals with a classification score greater than BoxScoreThreshold. Must be a float in the range[0, 1].

CheckpointFrequency

Frequency to store model checkpoints. Must be a positive integer.

(Inherited from ImageModelSettings)
CheckpointModel

The pretrained checkpoint model for incremental training.

(Inherited from ImageModelSettings)
CheckpointRunId

The id of a previous run that has a pretrained checkpoint for incremental training.

(Inherited from ImageModelSettings)
Distributed

Whether to use distributed training.

(Inherited from ImageModelSettings)
EarlyStopping

Enable early stopping logic during training.

(Inherited from ImageModelSettings)
EarlyStoppingDelay

Minimum number of epochs or validation evaluations to wait before primary metric improvement is tracked for early stopping. Must be a positive integer.

(Inherited from ImageModelSettings)
EarlyStoppingPatience

Minimum number of epochs or validation evaluations with no primary metric improvement before the run is stopped. Must be a positive integer.

(Inherited from ImageModelSettings)
EnableOnnxNormalization

Enable normalization when exporting ONNX model.

(Inherited from ImageModelSettings)
EvaluationFrequency

Frequency to evaluate validation dataset to get metric scores. Must be a positive integer.

(Inherited from ImageModelSettings)
GradientAccumulationStep

Gradient accumulation means running a configured number of "GradAccumulationStep" steps without updating the model weights while accumulating the gradients of those steps, and then using the accumulated gradients to compute the weight updates. Must be a positive integer.

(Inherited from ImageModelSettings)
ImageSize

Image size for train and validation. Must be a positive integer. Note: The training run may get into CUDA OOM if the size is too big. Note: This settings is only supported for the 'yolov5' algorithm.

LayersToFreeze

Number of layers to freeze for the model. Must be a positive integer. For instance, passing 2 as value for 'seresnext' means freezing layer0 and layer1. For a full list of models supported and details on layer freeze, please see: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-auto-train-image-models.

(Inherited from ImageModelSettings)
LearningRate

Initial learning rate. Must be a float in the range [0, 1].

(Inherited from ImageModelSettings)
LearningRateScheduler

Type of learning rate scheduler. Must be 'warmup_cosine' or 'step'.

(Inherited from ImageModelSettings)
LogTrainingMetrics

Enable computing and logging training metrics.

LogValidationLoss

Enable computing and logging validation loss.

MaxSize

Maximum size of the image to be rescaled before feeding it to the backbone. Must be a positive integer. Note: training run may get into CUDA OOM if the size is too big. Note: This settings is not supported for the 'yolov5' algorithm.

MinSize

Minimum size of the image to be rescaled before feeding it to the backbone. Must be a positive integer. Note: training run may get into CUDA OOM if the size is too big. Note: This settings is not supported for the 'yolov5' algorithm.

ModelName

Name of the model to use for training. For more information on the available models please visit the official documentation: https://docs.microsoft.com/en-us/azure/machine-learning/how-to-auto-train-image-models.

(Inherited from ImageModelSettings)
ModelSize

Model size. Must be 'small', 'medium', 'large', or 'xlarge'. Note: training run may get into CUDA OOM if the model size is too big. Note: This settings is only supported for the 'yolov5' algorithm.

Momentum

Value of momentum when optimizer is 'sgd'. Must be a float in the range [0, 1].

(Inherited from ImageModelSettings)
MultiScale

Enable multi-scale image by varying image size by +/- 50%. Note: training run may get into CUDA OOM if no sufficient GPU memory. Note: This settings is only supported for the 'yolov5' algorithm.

Nesterov

Enable nesterov when optimizer is 'sgd'.

(Inherited from ImageModelSettings)
NmsIouThreshold

IOU threshold used during inference in NMS post processing. Must be a float in the range [0, 1].

NumberOfEpochs

Number of training epochs. Must be a positive integer.

(Inherited from ImageModelSettings)
NumberOfWorkers

Number of data loader workers. Must be a non-negative integer.

(Inherited from ImageModelSettings)
Optimizer

Type of optimizer.

(Inherited from ImageModelSettings)
RandomSeed

Random seed to be used when using deterministic training.

(Inherited from ImageModelSettings)
StepLRGamma

Value of gamma when learning rate scheduler is 'step'. Must be a float in the range [0, 1].

(Inherited from ImageModelSettings)
StepLRStepSize

Value of step size when learning rate scheduler is 'step'. Must be a positive integer.

(Inherited from ImageModelSettings)
TileGridSize

The grid size to use for tiling each image. Note: TileGridSize must not be None to enable small object detection logic. A string containing two integers in mxn format. Note: This settings is not supported for the 'yolov5' algorithm.

TileOverlapRatio

Overlap ratio between adjacent tiles in each dimension. Must be float in the range [0, 1). Note: This settings is not supported for the 'yolov5' algorithm.

TilePredictionsNmsThreshold

The IOU threshold to use to perform NMS while merging predictions from tiles and image. Used in validation/ inference. Must be float in the range [0, 1]. Note: This settings is not supported for the 'yolov5' algorithm.

TrainingBatchSize

Training batch size. Must be a positive integer.

(Inherited from ImageModelSettings)
ValidationBatchSize

Validation batch size. Must be a positive integer.

(Inherited from ImageModelSettings)
ValidationIouThreshold

IOU threshold to use when computing validation metric. Must be float in the range [0, 1].

ValidationMetricType

Metric computation method to use for validation metrics.

WarmupCosineLRCycles

Value of cosine cycle when learning rate scheduler is 'warmup_cosine'. Must be a float in the range [0, 1].

(Inherited from ImageModelSettings)
WarmupCosineLRWarmupEpochs

Value of warmup epochs when learning rate scheduler is 'warmup_cosine'. Must be a positive integer.

(Inherited from ImageModelSettings)
WeightDecay

Value of weight decay when optimizer is 'sgd', 'adam', or 'adamw'. Must be a float in the range[0, 1].

(Inherited from ImageModelSettings)

Explicit Interface Implementations

IJsonModel<ImageModelSettings>.Create(Utf8JsonReader, ModelReaderWriterOptions)

Reads one JSON value (including objects or arrays) from the provided reader and converts it to a model.

(Inherited from ImageModelSettings)
IJsonModel<ImageModelSettings>.Write(Utf8JsonWriter, ModelReaderWriterOptions)

Writes the model to the provided Utf8JsonWriter.

(Inherited from ImageModelSettings)
IJsonModel<ImageModelSettingsObjectDetection>.Create(Utf8JsonReader, ModelReaderWriterOptions)

Reads one JSON value (including objects or arrays) from the provided reader and converts it to a model.

IJsonModel<ImageModelSettingsObjectDetection>.Write(Utf8JsonWriter, ModelReaderWriterOptions)

Writes the model to the provided Utf8JsonWriter.

IPersistableModel<ImageModelSettings>.Create(BinaryData, ModelReaderWriterOptions)

Converts the provided BinaryData into a model.

(Inherited from ImageModelSettings)
IPersistableModel<ImageModelSettings>.GetFormatFromOptions(ModelReaderWriterOptions)

Gets the data interchange format (JSON, Xml, etc) that the model uses when communicating with the service.

(Inherited from ImageModelSettings)
IPersistableModel<ImageModelSettings>.Write(ModelReaderWriterOptions)

Writes the model into a BinaryData.

(Inherited from ImageModelSettings)
IPersistableModel<ImageModelSettingsObjectDetection>.Create(BinaryData, ModelReaderWriterOptions)

Converts the provided BinaryData into a model.

IPersistableModel<ImageModelSettingsObjectDetection>.GetFormatFromOptions(ModelReaderWriterOptions)

Gets the data interchange format (JSON, Xml, etc) that the model uses when communicating with the service.

IPersistableModel<ImageModelSettingsObjectDetection>.Write(ModelReaderWriterOptions)

Writes the model into a BinaryData.

Applies to