AttentionBlock

class deeplay.components.diffusion.attention_unet.AttentionBlock(*args, **kwargs)

Bases: DeeplayModule

Applies attention mechanism to the input tensor. Depending on the input, it can handle both self-attention and cross-attention mechanisms. If context_embedding_dim is provided, it will apply cross-attention, else it will apply self-attention.

Methods Summary

forward(x, context)

Define the computation performed at every call.

Methods Documentation

forward(x, context)

Define the computation performed at every call.

Should be overridden by all subclasses.

Note

Although the recipe for forward pass needs to be defined within this function, one should call the Module instance afterwards instead of this since the former takes care of running the registered hooks while the latter silently ignores them.