Struct BasicTransformerBlock 

pub struct BasicTransformerBlock<T: Float> {
    pub norm1: LayerNorm<T>,
    pub attn1: Attention<T>,
    pub norm2: LayerNorm<T>,
    pub attn2: Attention<T>,
    pub norm3: LayerNorm<T>,
    pub ff: FeedForward<T>,
    /* private fields */
}

Diffusers’ BasicTransformerBlock configured the way SD-1.5’s UNet uses it: pre-LayerNorm on every sub-layer, self-attn followed by cross-attn followed by GEGLU FeedForward, all with residuals.

State-dict layout:

norm1.{weight,bias}   [dim], [dim]
attn1.<keys>          # self-attn (Attention with cross_attention_dim=None)
norm2.{weight,bias}
attn2.<keys>          # cross-attn
norm3.{weight,bias}
ff.<keys>             # FeedForward (GEGLU)

Fields

norm1: LayerNorm<T>

LayerNorm before self-attn.

attn1: Attention<T>

Self-attention.

norm2: LayerNorm<T>

LayerNorm before cross-attn.

attn2: Attention<T>

Cross-attention.

norm3: LayerNorm<T>

LayerNorm before FF.

ff: FeedForward<T>

GEGLU FeedForward.

Implementations

impl<T: Float> BasicTransformerBlock<T>

pub fn new( dim: usize, heads: usize, dim_head: usize, cross_attention_dim: usize, ) -> FerrotorchResult<Self>

Build a randomly-initialized BasicTransformerBlock.

Errors

Returns the underlying FerrotorchError for invalid dims.

pub fn forward_xattn( &self, x: &Tensor<T>, encoder_hidden_states: &Tensor<T>, ) -> FerrotorchResult<Tensor<T>>

Forward with optional encoder hidden states. Self-attn ignores encoder_hidden_states, cross-attn uses it.

Errors

Returns FerrotorchError::ShapeMismatch on rank disagreement, underlying op errors otherwise.

Trait Implementations

impl<T: Debug + Float> Debug for BasicTransformerBlock<T>

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

Formats the value using the given formatter.

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

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).