Table of Contents

Class GradLSTMSequenceOp

Namespace
AiDotNet.JitCompiler.IR.Operations
Assembly
AiDotNet.dll

Backward operation for full LSTM sequence.

public class GradLSTMSequenceOp : BackwardOp
Inheritance
GradLSTMSequenceOp
Inherited Members

Remarks

Computes gradients for all timesteps of an LSTM sequence. Uses truncated backpropagation through time (TBPTT) if specified.

Properties

Bidirectional

Whether LSTM is bidirectional.

public bool Bidirectional { get; set; }

Property Value

bool

HiddenSize

Hidden state size.

public int HiddenSize { get; set; }

Property Value

int

NumLayers

Number of layers (for stacked LSTM).

public int NumLayers { get; set; }

Property Value

int

SequenceLength

Sequence length.

public int SequenceLength { get; set; }

Property Value

int

TruncationLength

Truncation length for TBPTT (0 = no truncation).

public int TruncationLength { get; set; }

Property Value

int

Methods

ToString()

Gets a string representation of this operation for debugging.

public override string ToString()

Returns

string

A string describing this operation.

Remarks

The string format is: "tOutput = OpType(tInput1, tInput2, ...) : Type [Shape]"

For Beginners: This creates a readable description of the operation.

Example outputs:

  • "t2 = Add(t0, t1) : Float32 [3, 4]"
  • "t5 = MatMul(t3, t4) : Float32 [128, 256]"
  • "t8 = ReLU(t7) : Float32 [32, 128]"

This is super helpful for debugging - you can see exactly what each operation does and what shape tensors flow through the graph.

Validate()

Validates that this operation is correctly formed.

public override bool Validate()

Returns

bool

True if valid, false otherwise.

Remarks

Basic validation checks that the operation has required information. Derived classes can override to add operation-specific validation.

For Beginners: This checks that the operation makes sense.

Basic checks:

  • Output ID is valid (non-negative)
  • Has the right number of inputs
  • Shapes are compatible

Specific operations add their own checks:

  • MatMul: inner dimensions must match
  • Conv2D: kernel size must be valid
  • Reshape: total elements must be preserved

If validation fails, the operation can't be compiled.

Edit this page