Struct RRelu 

pub struct RRelu {
    pub lower: f64,
    pub upper: f64,
    pub training: Param<Flag>,
}

Randomized Leaky ReLU (RReLU) layer, from Empirical Evaluation of Rectified Activations.

During training the negative slope is sampled element-wise from a uniform distribution [lower, upper); during evaluation the fixed midpoint slope (lower + upper) / 2 is used, which is identical to a LeakyReLU. Following the same convention as Dropout, the training behaviour is enabled when the input is on an autodiff backend and the layer’s training flag is enabled.

Should be created with RReluConfig.

Fields

lower: f64

The lower bound of the uniform slope range.

upper: f64

The upper bound of the uniform slope range.

training: Param<Flag>

Whether to behave as during training. Cleared by freeze and matching freeze_group traversals.

Implementations

impl RRelu

pub fn forward<const D: usize>(&self, input: Tensor<D>) -> Tensor<D>

Applies the forward pass on the input tensor.

See RRelu for more information.

Shapes

• input: [..., any]
• output: [..., any]

Trait Implementations

impl Clone for RRelu

fn clone(&self) -> RRelu

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for RRelu

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Display for RRelu

fn fmt(&self, f: &mut Formatter<'_>) -> Result<(), Error>

Formats the value using the given formatter.

impl Module for RRelu

fn num_params(&self) -> usize

Get the number of parameters the module has, including all of its sub-modules, without initializing the ones not initialized yet.

fn visit<Visitor>(&self, visitor: &mut Visitor)

where Visitor: ModuleVisitor,

Visit each parameter and module-owned control value with a visitor.

fn map<Mapper>(self, mapper: &mut Mapper) -> RRelu

where Mapper: ModuleMapper,

Map each parameter and module-owned control value with a mapper.

fn collect_devices(&self, devices: Vec<Device>) -> Vec<Device>

Return all the devices found in the underneath module tree added to the given vector without duplicates.

fn to_device(self, device: &Device) -> RRelu

Move the module and all of its sub-modules to the given device.

fn fork(self, device: &Device) -> RRelu

Fork the module and all of its sub-modules to the given device.

fn valid(&self) -> RRelu

Returns a validation snapshot without autodiff or active training flags.

fn train(self) -> RRelu

Enables autodiff and restores configured training state throughout the module.

fn materialize(self) -> RRelu

Fold parameter reparameterizations into their effective values and remove them.

fn devices(&self) -> Vec<Device>

Return all the devices found in the underneath module tree without duplicates.

fn set_require_grad(self, require_grad: bool) -> Self

Set whether every floating-point tensor parameter in the module tree requires gradients.

fn set_require_grad_group(self, group: ParamGroup, require_grad: bool) -> Self

Set whether matched floating-point tensor parameters require gradients.

fn no_grad(self) -> Self

Disable gradients for every floating-point tensor parameter in the module tree.

fn freeze(self) -> Self

Freeze the whole module tree.

fn unfreeze(self) -> Self

Unfreeze the whole module tree.

fn freeze_group(self, group: ParamGroup) -> Self

Freeze every module-owned value in the given group, leaving the rest of the module untouched.

fn unfreeze_group(self, group: ParamGroup) -> Self

Unfreeze every module-owned value in the given group, leaving the rest of the module untouched.

fn quantize_weights(self, quantizer: &mut Quantizer) -> Self

Quantize the weights of the module.

fn quantize_weights_group( self, quantizer: &mut Quantizer, group: ParamGroup, ) -> Self

Quantize the weights of the given parameter group.

fn apply_reparameterization<R>(self, reparameterizer: R) -> Self

where Self: Sized, R: Reparameterizer,

Attach reparameterizations using the given Reparameterizer.

fn apply_lora(self, lora: Lora) -> Self

where Self: Sized,

Attach LoRA adapters to the module’s 2-D weights, freezing all base tensor parameters.

fn apply_qlora(self, qlora: QLora) -> Self

where Self: Sized,

Apply QLoRA to the module: quantize the (frozen) base tensor parameters and attach trainable LoRA adapters to 2-D weights.

fn into_record(self) -> ModuleRecord

where Self: Sized,

Collect this module’s tensor parameters into a ModuleRecord.

fn into_record_group(self, group: ParamGroup) -> ModuleRecord

where Self: Sized,

Collect the tensor parameters group names into a ModuleRecord.

fn try_load_record(self, record: ModuleRecord) -> Result<Self, RecordError>

where Self: Sized,

Apply a ModuleRecord to this module, returning the loaded module.

fn load_record(self, record: ModuleRecord) -> Self

where Self: Sized,

Apply a ModuleRecord to this module, consuming and returning it.

fn save_file<P>(self, path: P) -> Result<(), RecordError>

where P: AsRef<Path>, Self: Sized,

Save this module’s parameters to a burnpack file on disk.

fn load_file<P>(self, path: P) -> Self

where P: AsRef<Path>, Self: Sized,

Load this module’s parameters from a burnpack file on disk, returning the loaded module.

fn try_load_file<P>(self, path: P) -> Result<Self, RecordError>

where P: AsRef<Path>, Self: Sized,

Fallible variant of load_file.

impl ModuleDisplay for RRelu

fn custom_settings(&self) -> Option<DisplaySettings>

Custom display settings for the module.

fn custom_content(&self, content: Content) -> Option<Content>

Custom attributes for the module.

fn format(&self, passed_settings: DisplaySettings) -> String

Formats the module with provided display settings.

impl ModuleDisplayDefault for RRelu

fn content(&self, content: Content) -> Option<Content>

Attributes of the module used for display purposes.

fn num_params(&self) -> usize

Gets the number of the parameters of the module.