Class OFASubnetSummary

Namespace

AiDotNet.Models.Results

Assembly

AiDotNet.dll

Represents OnceForAll subnet configuration summary.

public sealed class OFASubnetSummary

Inheritance

object

OFASubnetSummary

Inherited Members

object.Equals(object)

object.Equals(object, object)

object.GetHashCode()

object.GetType()

object.ReferenceEquals(object, object)

object.ToString()

Remarks

For Beginners: OnceForAll (OFA) is a NAS technique that trains one large "supernet" containing many possible architectures. After training, you can extract smaller "subnets" optimized for specific hardware without retraining. This summary describes the extracted subnet.

Properties

Depths

Gets or sets the depth configuration (number of blocks per stage).

public List<int>? Depths { get; set; }

Property Value

List<int>

EstimatedAccuracy

Gets or sets the estimated accuracy of the subnet.

public double? EstimatedAccuracy { get; set; }

Property Value

double?

EstimatedLatencyMs

Gets or sets the estimated latency of the subnet on the target platform.

public double? EstimatedLatencyMs { get; set; }

Property Value

double?

ExpansionRatios

Gets or sets the expansion ratios per block.

public List<double>? ExpansionRatios { get; set; }

Property Value

List<double>

KernelSizes

Gets or sets the kernel sizes selected per block.

public List<int>? KernelSizes { get; set; }

Property Value

List<int>

Widths

Gets or sets the width multipliers per stage.

public List<double>? Widths { get; set; }

Property Value

List<double>