TorchLean API

NN.Spec.Layers.Pooling.Aliases

Pooling Aliases #

Short names for the dimension-polymorphic pooling specs.

Friendly aliases #

@[reducible, inline]
abbrev Spec.maxPool {α : Type} [Context α] {d C : } {inSpatial kernel stride padding : Vector d} {hKernel : ∀ (i : Fin d), kernel.get i 0} {hStride : ∀ (i : Fin d), stride.get i 0} (layer : MaxPoolSpec d kernel stride padding hKernel hStride) (input : Tensor α (Shape.ofList (C :: inSpatial.toList))) :
Tensor α (Shape.ofList (C :: (poolOutSpatialPad inSpatial kernel stride padding).toList))

Alias for max_pool_spec.

Instances For
    @[reducible, inline]
    abbrev Spec.avgPool {α : Type} [Context α] {d C : } {inSpatial kernel stride padding : Vector d} {hKernel : ∀ (i : Fin d), kernel.get i 0} {hStride : ∀ (i : Fin d), stride.get i 0} (layer : AvgPoolSpec d kernel stride padding hKernel hStride) (input : Tensor α (Shape.ofList (C :: inSpatial.toList))) :
    Tensor α (Shape.ofList (C :: (poolOutSpatialPad inSpatial kernel stride padding).toList))

    Alias for avg_pool_spec.

    Instances For
      @[reducible, inline]
      abbrev Spec.smoothMaxPool {α : Type} [Context α] {d C : } {inSpatial kernel stride padding : Vector d} {hKernel : ∀ (i : Fin d), kernel.get i 0} {hStride : ∀ (i : Fin d), stride.get i 0} (layer : MaxPoolSpec d kernel stride padding hKernel hStride) (beta : α) (input : Tensor α (Shape.ofList (C :: inSpatial.toList))) :
      Tensor α (Shape.ofList (C :: (poolOutSpatialPad inSpatial kernel stride padding).toList))

      Alias for smooth_max_pool_spec.

      Instances For
        @[reducible, inline]
        abbrev Spec.maxPoolBackward {α : Type} [Context α] {d C : } {inSpatial kernel stride padding : Vector d} {hKernel : ∀ (i : Fin d), kernel.get i 0} {hStride : ∀ (i : Fin d), stride.get i 0} (layer : MaxPoolSpec d kernel stride padding hKernel hStride) (input : Tensor α (Shape.ofList (C :: inSpatial.toList))) (grad_output : Tensor α (Shape.ofList (C :: (poolOutSpatialPad inSpatial kernel stride padding).toList))) :
        Tensor α (Shape.ofList (C :: inSpatial.toList))

        Alias for max_pool_backward_spec.

        Instances For
          @[reducible, inline]
          abbrev Spec.avgPoolBackward {α : Type} [Context α] {d C : } {inSpatial kernel stride padding : Vector d} {hKernel : ∀ (i : Fin d), kernel.get i 0} {hStride : ∀ (i : Fin d), stride.get i 0} (layer : AvgPoolSpec d kernel stride padding hKernel hStride) (grad_output : Tensor α (Shape.ofList (C :: (poolOutSpatialPad inSpatial kernel stride padding).toList))) :
          Tensor α (Shape.ofList (C :: inSpatial.toList))

          Alias for avg_pool_backward_spec.

          Instances For
            @[reducible, inline]
            abbrev Spec.smoothMaxPoolBackward {α : Type} [Context α] {d C : } {inSpatial kernel stride padding : Vector d} {hKernel : ∀ (i : Fin d), kernel.get i 0} {hStride : ∀ (i : Fin d), stride.get i 0} (layer : MaxPoolSpec d kernel stride padding hKernel hStride) (beta : α) (input : Tensor α (Shape.ofList (C :: inSpatial.toList))) (grad_output : Tensor α (Shape.ofList (C :: (poolOutSpatialPad inSpatial kernel stride padding).toList))) :
            Tensor α (Shape.ofList (C :: inSpatial.toList))

            Alias for smooth_max_pool_backward_spec.

            Instances For