Residual Classifier Training Example

This command trains the public rank-polymorphic residual classifier on a small CIFAR-10 crop. The model contains a convolutional stem, two residual branches, global average pooling over all spatial axes, and a linear classifier. The compact crop keeps the command useful as a runtime check while still exercising the same residual composition and pooling code used by larger configurations.

def NN.Examples.Models.Vision.ResNet.exeName : String

CLI subcommand name used in terminal banners and parser errors.

def NN.Examples.Models.Vision.ResNet.defaultLogJson : System.FilePath

Default JSON training-log path.

def NN.Examples.Models.Vision.ResNet.batch : ℕ

Static minibatch size carried by the checked model shape.

def NN.Examples.Models.Vision.ResNet.inChannels : ℕ

CIFAR input channels.

def NN.Examples.Models.Vision.ResNet.height : ℕ

Height of the compact CIFAR crop.

def NN.Examples.Models.Vision.ResNet.width : ℕ

Width of the compact CIFAR crop.

def NN.Examples.Models.Vision.ResNet.hiddenChannels : ℕ

Channel width of the residual trunk.

def NN.Examples.Models.Vision.ResNet.cfg : TorchLean.nn.models.ResNetConfig 2

Configuration shared by the model constructor and its typed input/output shapes.

@[reducible, inline]

abbrev NN.Examples.Models.Vision.ResNet.σ : Spec.Shape

Batched channel-first input shape.

@[reducible, inline]

abbrev NN.Examples.Models.Vision.ResNet.τ : Spec.Shape

One row of class logits per input sample.

def NN.Examples.Models.Vision.ResNet.model : TorchLean.nn.M (TorchLean.nn.Sequential σ τ)

Residual classifier from the public model API.

def NN.Examples.Models.Vision.ResNet.train (opts : Runtime.Autograd.Torch.Options) (flags : RealData.CifarModelTrainFlags) : IO TorchLean.Trainer.TrainSummary

Train the residual classifier with the public classification trainer.

def NN.Examples.Models.Vision.ResNet.main (args : List String) : IO UInt32

CLI entrypoint for the CIFAR residual-classifier training path.