Struct Timesteps 

pub struct Timesteps {
    pub num_channels: usize,
    pub flip_sin_to_cos: bool,
    pub downscale_freq_shift: f64,
    pub max_period: f64,
}

Timesteps — sinusoidal positional encoding of a scalar timestep.

Parameter-free. Reproduces diffusers.models.embeddings.Timesteps(num_channels, flip_sin_to_cos, downscale_freq_shift) for flip_sin_to_cos=true and downscale_freq_shift=0 (the SD-1.5 settings).

Fields

num_channels: usize

Output channel count (must be even). For SD UNet: 320.

flip_sin_to_cos: bool

If true, cat([cos, sin]) (SD-style). If false, cat([sin, cos]).

downscale_freq_shift: f64

downscale_freq_shift from diffusers (subtracted in the exponent denominator). Always 0 for SD-1.5.

max_period: f64

Maximum period of the sinusoid (diffusers default: 10000).

Implementations

impl Timesteps

pub fn new( num_channels: usize, flip_sin_to_cos: bool, downscale_freq_shift: f64, ) -> FerrotorchResult<Self>

Build a Timesteps module.

Errors

Returns FerrotorchError::InvalidArgument when num_channels is not a positive even integer.

pub fn forward_t<T: Float>( &self, timesteps: &Tensor<T>, ) -> FerrotorchResult<Tensor<T>>

Compute the sinusoidal encoding for a batch of timesteps.

timesteps has shape [B] (1-D, dtype T). The output has shape [B, num_channels].

Errors

Returns FerrotorchError::ShapeMismatch when the input is not rank-1, FerrotorchError::InvalidArgument if the half-channel math overflows T.

Trait Implementations

impl Clone for Timesteps

fn clone(&self) -> Timesteps

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for Timesteps

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

Formats the value using the given formatter.

impl<T: Float> Module<T> for Timesteps

fn forward(&self, input: &Tensor<T>) -> FerrotorchResult<Tensor<T>>

Forward pass. Takes input tensor, returns output tensor.

fn parameters(&self) -> Vec<&Parameter<T>>

Iterate over all learnable parameters.

fn parameters_mut(&mut self) -> Vec<&mut Parameter<T>>

Iterate over all learnable parameters mutably.

fn named_parameters(&self) -> Vec<(String, &Parameter<T>)>

Named parameters for state dict serialization.

fn train(&mut self)

Set training mode. Affects dropout, batchnorm, etc.

fn eval(&mut self)

Set evaluation mode.

fn is_training(&self) -> bool

Whether the module is in training mode.

fn load_state_dict( &mut self, _state: &StateDict<T>, _strict: bool, ) -> FerrotorchResult<()>

Load parameters from a state dict.

fn to_device(&mut self, device: Device) -> Result<(), FerrotorchError>

Move all parameters and buffers to a device.

fn state_dict(&self) -> HashMap<String, Tensor<T>>

Export parameters and buffers as a state dict (torch parity).

fn buffers(&self) -> Vec<&Buffer<T>>

Iterate over all non-trainable buffers (e.g. running mean / variance in BatchNorm). Default returns empty — concrete modules with buffers override.

fn buffers_mut(&mut self) -> Vec<&mut Buffer<T>>

Mutable iteration over all buffers. Default returns empty.

fn named_buffers(&self) -> Vec<(String, &Buffer<T>)>

Named buffers (dot-separated paths for nested modules). Default returns empty.

fn as_any(&self) -> Option<&(dyn Any + 'static)>

Downcast hook for type-erased buffer-loader dispatch. (#984)

fn children(&self) -> Vec<&dyn Module<T>>

Direct child modules. Default returns empty (leaf module).

fn named_children(&self) -> Vec<(String, &dyn Module<T>)>

Direct child modules with their attribute names. Default returns empty.

fn modules(&self) -> Vec<&dyn Module<T>>

where Self: Sized,

All modules in this subtree, depth-first (self first, then each child’s descendants in order).

fn descendants_dyn(&self) -> Vec<&dyn Module<T>>

All strict descendants of self in depth-first order. Object-safe.

fn named_modules(&self) -> Vec<(String, &dyn Module<T>)>

where Self: Sized,

All modules in this subtree with dot-separated path names. The root is named ""; children paths are joined with ..

fn named_descendants_dyn(&self) -> Vec<(String, &dyn Module<T>)>

Strict descendants with dot-paths. Object-safe.

fn with_forward_hook( self, hook: Box<dyn Fn(&Tensor<T>, &Tensor<T>) + Send + Sync>, ) -> (HookedModule<Self, T>, HookHandle)

where Self: Sized,

Wrap this module in a HookedModule and register a forward hook. Returns the wrapper paired with a HookHandle that can be used to remove the hook later. The wrapper implements Module<T> itself, so it slots into any place the original module did. Mirrors torch.nn.Module.register_forward_hook.

fn with_forward_pre_hook( self, hook: Box<dyn Fn(&Tensor<T>) -> Result<Tensor<T>, FerrotorchError> + Send + Sync>, ) -> (HookedModule<Self, T>, HookHandle)

where Self: Sized,

Wrap this module in a HookedModule and register a forward pre-hook. See Self::with_forward_hook. Mirrors torch.nn.Module.register_forward_pre_hook.

fn with_backward_hook( self, hook: Box<dyn Fn(&Tensor<T>, &Tensor<T>) + Send + Sync>, ) -> (HookedModule<Self, T>, HookHandle)

where Self: Sized,

Wrap this module in a HookedModule and register a backward hook. See Self::with_forward_hook. Mirrors torch.nn.Module.register_backward_hook.

fn zero_grad(&self) -> Result<(), FerrotorchError>

Set the gradient of every parameter to None.

fn requires_grad_(&mut self, requires_grad: bool)

Toggle requires_grad on every parameter (freeze / unfreeze the module). Mirrors torch.nn.Module.requires_grad_.

fn apply_to_parameters(&mut self, f: &mut dyn FnMut(&mut Parameter<T>))

Apply a function to every parameter in this module. Mirrors torch.nn.Module.apply for the parameter case (true apply recurses over all submodules; the recursive form requires &mut dyn Module which conflicts with this trait’s &mut self borrow).