TinyUNet class
Minimal U-Net for [N, 1, H, W] grayscale images. Two down blocks
(stride-2 Conv2d), a mid block, then two up blocks
(ConvTranspose2d, stride-2). A per-image scalar timestep is
embedded via a linear projection and broadcast-added to the mid
features. Predicts an ε-shape tensor [N, 1, H, W].
Properties
- down1 → Conv2d
-
final
- down2 → Conv2d
-
final
- hashCode → int
-
The hash code for this object.
no setterinherited
- mid → Conv2d
-
final
- runtimeType → Type
-
A representation of the runtime type of the object.
no setterinherited
- timeProj → Linear
-
final
- totalTimesteps → 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 theircallmethod. Defaults to training mode.getter/setter pairinherited - up1 → ConvTranspose2d
-
final
- up2 → ConvTranspose2d
-
final
Methods
-
call(
Tensor x, int t) → 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
-
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.override -
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