Residual Convolutional Classifier

The model accepts any batchShape and spatial rank. Residual branches operate on a common typed shape, and global average pooling reduces every spatial axis before the classifier head.

structure TorchLean.nn.models.ResNet.Config (d : ℕ) : Type

Configuration for a residual classifier over d spatial axes.

• inputChannels : ℕ

  Number of channels in each input sample.

• spatial : Tensor ℕ [d]

  Size of each input axis. Values such as [32, 32] work directly.

• hiddenChannels : ℕ

  Channel width used by the residual trunk.

• kernelRadius : Tensor ℕ [d]

  Radius of the same-padding convolution kernel on each axis.

  A radius of 1 gives the familiar kernel size 3; all convolutions therefore preserve the input grid without an additional shape proof.

• classCount : ℕ

  Number of classifier logits per sample.

def TorchLean.nn.models.ResNet.Config.validate {d : ℕ} (config : Config d) : Except String Unit

Validate the complete residual classifier before allocating any branch parameters.

@[reducible, inline]

abbrev TorchLean.nn.models.ResNet.Config.inputShape {d : ℕ} (config : Config d) (batchShape : Shape := []) : Shape

Input tensor shape with an arbitrary batch shape.

@[reducible, inline]

abbrev TorchLean.nn.models.ResNet.Config.hiddenShape {d : ℕ} (config : Config d) (batchShape : Shape := []) : Shape

Hidden activation shape shared by the residual branches.

@[reducible, inline]

abbrev TorchLean.nn.models.ResNet.Config.outputShape {d : ℕ} (config : Config d) (batchShape : Shape := []) : Shape

Classifier output shape with the same batch shape as the input.

def TorchLean.nn.models.resnet {d : ℕ} (config : ResNet.Config d) (batchShape : Shape := []) : Builder (Sequential (config.inputShape batchShape) (config.outputShape batchShape))

Build a convolutional stem, two residual blocks, global pooling, and a linear classifier.