class MXNet::Gluon::Loss::SoftmaxCrossEntropyLoss

Overview

Computes the softmax cross-entropy loss.

If sparse_label is true (default), labels should contain integer category indicators. The labels' shape should be the predictions' shape with the axis dimension removed -- i.e. for predictions with shape [1, 2, 3, 4] and axis: 2, labels' shape should be [1, 2, 4].

If sparse_label is false, labels should contain probability distributions and labels' shape should be the same as predictions' shape.

Defined in:

mxnet/gluon/loss.cr

Constructors

Constructor methods inherited from class MXNet::Gluon::Loss

new(weight : Float64?, batch_axis : Int32, **kwargs) new

Instance methods inherited from class MXNet::Gluon::HybridBlock

export(filename, epoch = 0) export, forward(inputs : Array(T)) : Array(T) forall T forward, hybrid_forward(inputs : Array(T), params : Hash(String, T) = {} of String => T) : Array(T) forall T hybrid_forward, hybridize(active = true, flags = {} of String => String) hybridize, register_child(block, name = nil) register_child

Instance methods inherited from module MXNet::Gluon::CachedGraph

clear_cache clear_cache, infer_dtype(args) infer_dtype, infer_shape(args) infer_shape

Constructor methods inherited from module MXNet::Gluon::CachedGraph

new(**kwargs) new

Instance methods inherited from class MXNet::Gluon::Block

call(inputs : Array(T)) : Array(T) forall T call, children children, collect_params(selector = nil) collect_params, forward(inputs : Array(T)) : Array(T) forall T forward, get_attr(name : String) : Block | Parameter | Nil get_attr, hybridize(active = true) hybridize, init(init = nil, ctx = nil, force_reinit = false) init, load_parameters(fname, ctx = MXNet.cpu, allow_missing = false, ignore_extra = false) load_parameters, params : MXNet::Gluon::ParameterDict params, prefix : String prefix, register_child(block, name = nil) register_child, register_parameter(param, name = nil) register_parameter, save_parameters(fname) save_parameters, scope : MXNet::Gluon::BlockScope? scope, set_attr(name : String, value : Block | Parameter | Nil) set_attr, with_name_scope(&) with_name_scope

Constructor methods inherited from class MXNet::Gluon::Block

new(prefix = nil, params = nil) new

Constructor Detail

def self.new(axis = -1, sparse_label = true, from_logits = false, weight = nil, batch_axis = 0, **kwargs) #

Creates a new instance.

Parameters

  • axis (Int, default = -1) The axis to sum over when computing softmax and entropy.
  • sparse_label (Bool, default = true) Whether label is an integer array instead of probability distribution.
  • from_logits (Bool, default = false) Whether prediction is a log probability (usually from #log_softmax) instead of unnormalized numbers.
  • weight (Float or nil, default = nil) Global scalar weight for loss.
  • batch_axis (Int, default 0) The axis that represents the mini-batch.

[View source]