Class: Torch::NN::CTCLoss

Inherits:
Loss show all
Defined in:
lib/torch/nn/ctc_loss.rb

Instance Attribute Summary

Attributes inherited from Module

#training

Instance Method Summary collapse

Methods inherited from Module

#_apply, #add_module, #apply, #buffers, #call, #children, #cpu, #cuda, #deep_dup, #double, #eval, #float, #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(blank: 0, reduction: "mean", zero_infinity: false) ⇒ CTCLoss

Returns a new instance of CTCLoss.



4
5
6
7
8
 
# File 'lib/torch/nn/ctc_loss.rb', line 4

def initialize(blank: 0, reduction: "mean", zero_infinity: false)
  super(reduction)
  @blank = blank
  @zero_infinity = zero_infinity
end

Dynamic Method Handling

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

Instance Method Details

#forward(log_probs, targets, input_lengths, target_lengths) ⇒ Object 



10
11
12
 
# File 'lib/torch/nn/ctc_loss.rb', line 10

def forward(log_probs, targets, input_lengths, target_lengths)
  F.ctc_loss(log_probs, targets, input_lengths, target_lengths, blank: @blank, reduction: @reduction, zero_infinity: @zero_infinity)
end