Class: Torch::NN::MSELoss
Instance Method Summary collapse
- #forward(input, target) ⇒ Object
-
#initialize(reduction: "mean") ⇒ MSELoss
constructor
A new instance of MSELoss.
Methods inherited from Module
#_apply, #add_module, #apply, #buffers, #call, #children, #cpu, #cuda, #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
#_ntuple, #_pair, #_quadrupal, #_single, #_triple
Constructor Details
#initialize(reduction: "mean") ⇒ MSELoss
Returns a new instance of MSELoss.
4 5 6 |
# File 'lib/torch/nn/mse_loss.rb', line 4 def initialize(reduction: "mean") super(reduction) end |
Dynamic Method Handling
This class handles dynamic methods through the method_missing method in the class Torch::NN::Module
Instance Method Details
#forward(input, target) ⇒ Object
8 9 10 |
# File 'lib/torch/nn/mse_loss.rb', line 8 def forward(input, target) F.mse_loss(input, target, reduction: @reduction) end |