pub struct Dropout { /* private fields */ }
Expand description
Set at random some elements of the input tensor to zero during training.
This is an effective regularization technique as describe in the paper Improving neural networks by preventing co-adaptation of feature detectors.
The input is also scaled during training to 1 / (1-p)
.
Implementations
sourceimpl Dropout
impl Dropout
pub fn new(config: &DropoutConfig) -> Self
Trait Implementations
Auto Trait Implementations
impl RefUnwindSafe for Dropout
impl Send for Dropout
impl Sync for Dropout
impl Unpin for Dropout
impl UnwindSafe for Dropout
Blanket Implementations
sourceimpl<T> BorrowMut<T> for Twhere
T: ?Sized,
impl<T> BorrowMut<T> for Twhere
T: ?Sized,
const: unstable · sourcefn borrow_mut(&mut self) -> &mut T
fn borrow_mut(&mut self) -> &mut T
Mutably borrows from an owned value. Read more