towhee.models.collaborative_experts.collaborative_experts¶

Functions

`create_model`	Create CENet model.
`drop_nans`	Remove nans, which we expect to find at missing indices.
`kronecker_prod`
`sharded_cross_view_inner_product`	Compute a similarity matrix from sharded vectors.
`sharded_single_view_inner_product`	Compute a similarity matrix from sharded vectors.

Classes

`CEModule`	CE Module
`CENet`	Collaborative Experts Module.
`ContextGating`	ContextGating Module
`ContextGatingReasoning`
`G_reason`	G_reason Module
`GatedEmbeddingUnit`
`GatedEmbeddingUnitReasoning`
`MimicCEGatedEmbeddingUnit`
`Mish`	Applies the mish function element-wise: mish(x) = x * tanh(softplus(x)) = x * tanh(ln(1 + exp(x))) SRC: https://github.com/digantamisra98/Mish/blob/master/Mish/Torch/mish.py
`ReduceDim`	ReduceDim Module
`RelationModuleMultiScale`	RelationModuleMultiScale Module
`RelationModuleMultiScale_Cat`	RelationModuleMultiScale_Cat Module
`SpatialMLP`
`TemporalAttention`	TemporalAttention Module