ConvTranspose2d class

Inheritance

Constructors

ConvTranspose2d(int inChannels, int outChannels, {int kernel = 3, int? kernelH, int? kernelW, int stride = 1, int padding = 0, int? paddingH, int? paddingW, int outputPadding = 0, int? outputPaddingH, int? outputPaddingW, bool bias = true, Device device = Device.CPU, int seed = 0})

Properties

bias → Tensor?
Optional per-output-channel bias, shape [Cout].
final
hashCode → int
The hash code for this object.
no setterinherited
inChannels → int
final
kernelH → int
final
kernelW → int
final
outChannels → int
final
outputPaddingH → int
final
outputPaddingW → int
final
paddingH → int
final
paddingW → int
final
runtimeType → Type
A representation of the runtime type of the object.
no setterinherited
stride → int
final
training ↔ bool
Whether this module is in training mode. Layers that behave differently between training and inference (e.g. Dropout) read this flag in their call method. Defaults to training mode.
getter/setter pairinherited
weight → Tensor
Weight shape: [Cin, Cout, Kh, Kw] — same as PyTorch nn.ConvTranspose2d.weight.
final

Methods

call(Tensor x) → Tensor
eval() → void
Put this module (and any registered submodules) into evaluation mode.
inherited
noSuchMethod(Invocation invocation) → dynamic
Invoked when a nonexistent method or property is accessed.
inherited
outputHeight(int h) → int
outputWidth(int w) → int
parameters() → List<Tensor>
Trainable tensors owned by this module (and its submodules).
override
submodules() → List<Module>
Submodules owned by this module. Subclasses that compose other modules should override this so train() / eval() propagate. Default: empty.
inherited
toString() → String
A string representation of this object.
inherited
train() → void
Put this module (and any registered submodules) into training mode.
inherited
zeroGrad() → void
Zero every parameter's gradient. Safe to call before each backward.
inherited

Operators

operator ==(Object other) → bool
The equality operator.
inherited