Class: Torch::NN::PReLU

Inherits:
Module
  • Object
show all
Defined in:
lib/torch/nn/prelu.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(num_parameters: 1, init: 0.25) ⇒ PReLU

Returns a new instance of PReLU.



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

def initialize(num_parameters: 1, init: 0.25)
  @num_parameters = num_parameters
  super()
  @weight = Parameter.new(Tensor.new(num_parameters).fill!(init))
end

Dynamic Method Handling

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

Instance Method Details

#extra_inspectObject



14
15
16
# File 'lib/torch/nn/prelu.rb', line 14

def extra_inspect
  format("num_parameters: %s", @num_parameters)
end

#forward(input) ⇒ Object



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

def forward(input)
  F.prelu(input, @weight)
end