pub struct Residual<F>(pub F);
Expand description

A residual connection around F: F(x) + x, as introduced in Deep Residual Learning for Image Recognition.

Generics

  • F: The underlying module to do a skip connection around.

Examples

let module: Residual<ReLU> = Default::default();
let x = Tensor1D::new([-2.0, -1.0, 0.0, 1.0, 2.0]);
let y = module.forward(x);
assert_eq!(y.data(), &[-2.0, -1.0, 0.0, 2.0, 4.0]);

Tuple Fields

0: F

Trait Implementations

Pass through to F’s CanUpdateWithGradients.

Returns a copy of the value. Read more

Performs copy-assignment from source. Read more

Formats the value using the given formatter. Read more

Returns the “default value” for a type. Read more

Pass through to F’s LoadFromNpz.

Loads data from a .npz zip archive at the specified path. Read more

Calls forward on F and then adds x to the result: F(x) + x

The type that this unit produces given Input.

Pass an Input through the unit and produce Self::Output. Can be implemented for multiple Input types. Read more

Pass through to F’s ResetParams.

Pass through to F’s SaveToNpz.

Save this object into the .npz file determined located at path. Read more

Auto Trait Implementations

Blanket Implementations

Gets the TypeId of self. Read more

Immutably borrows from an owned value. Read more

Mutably borrows from an owned value. Read more

Returns the argument unchanged.

Calls U::from(self).

That is, this conversion is whatever the implementation of From<T> for U chooses to do.

Should always be Self

The resulting type after obtaining ownership.

Creates owned data from borrowed data, usually by cloning. Read more

Uses borrowed data to replace owned data, usually by cloning. Read more

The type returned in the event of a conversion error.

Performs the conversion.

The type returned in the event of a conversion error.

Performs the conversion.