Class: Torch::NN::WeightedLoss

Inherits:

Loss

• Object
• Module
• Loss
• Torch::NN::WeightedLoss

Defined in:

lib/torch/nn/weighted_loss.rb

Direct Known Subclasses

BCELoss, CrossEntropyLoss, MultiLabelSoftMarginLoss, MultiMarginLoss, NLLLoss

Instance Attribute Summary

Attributes inherited from Module

#training

Instance Method Summary

• #initialize(weight, reduction) ⇒ WeightedLoss constructor

  A new instance of WeightedLoss.

Methods inherited from Module

#_apply, #add_module, #apply, #buffers, #call, #children, #cpu, #cuda, #deep_dup, #double, #eval, #float, #forward, #half, #inspect, #load_state_dict, #method_missing, #modules, #named_buffers, #named_children, #named_modules, #named_parameters, #parameters, #register_buffer, #register_parameter, #requires_grad!, #respond_to?, #share_memory, #state_dict, #to, #train, #type, #zero_grad

Methods included from Utils

#_activation_fn, #_clones, #_ntuple, #_pair, #_quadrupal, #_single, #_triple

Constructor Details

#initialize(weight, reduction) ⇒ WeightedLoss

Returns a new instance of WeightedLoss.

# File 'lib/torch/nn/weighted_loss.rb', line 4

def initialize(weight, reduction)
  super(reduction)
  register_buffer("weight", weight)
end

Dynamic Method Handling

This class handles dynamic methods through the method_missing method in the class Torch::NN::Module