PatchEmbed class

Splits the input image into non-overlapping patches and projects them to an embedding space using a convolution.

Input: (batch, 3, height, width) → Output: (batch, numPatches, embedDim)

Constructors

PatchEmbed({required List<int> imgSize, int patchSize = 4, int inChannels = 3, int embedDim = 128})

Properties

embedDim → int

final

hashCode → int

The hash code for this object.

no setter, inherited

inChannels → int

final

norm ↔ LayerNorm

getter/setter pair

numPatches → int

Number of patches.

no setter

numPatchesH ↔ int

getter/setter pair

numPatchesW ↔ int

getter/setter pair

patchSize → int

final

proj ↔ Conv2d

getter/setter pair

runtimeType → Type

A representation of the runtime type of the object.

no setter, inherited

Methods

forward(Tensor x) → Tensor

Forward pass.

noSuchMethod(Invocation invocation) → dynamic

Invoked when a nonexistent method or property is accessed.

inherited

toString() → String

A string representation of this object.

inherited

Operators

operator ==(Object other) → bool

The equality operator.

inherited