基于MSELoss()与CrossEntropyLoss()的区别详解

class CNN (nn.Module ) :
  def __init__ ( self , hidden_size1 , output_size , dropout_p) :
    super ( CNN , self ).__init__ ( )
    self.hidden_size1 = hidden_size1
    self.output_size = output_size
    self.dropout_p = dropout_p
    
    self.conv1 = nn.Conv1d ( 1,8,3,padding =1) 
    self.fc1 = nn.Linear (8*500, self.hidden_size1 )
    self.out = nn.Linear (self.hidden_size1,self.output_size ) 
 
  
  def forward ( self , encoder_outputs ) :
    cnn_out = F.max_pool1d ( F.relu (self.conv1(encoder_outputs)),2) 
    cnn_out = F.dropout ( cnn_out ,self.dropout_p) #加一个dropout
    cnn_out = cnn_out.view (-1,8*500) 
    output_1 = torch.tanh ( self.fc1 ( cnn_out ) )
    output = self.out ( ouput_1)
    return output

cnn_optimizer = torch.optim.SGD(cnn.parameters(),learning_rate,momentum=0.9,\
              weight_decay=1e-5)
criterion = nn.CrossEntropyLoss()
 
def train ( input_variable , target_variable , cnn , cnn_optimizer , criterion ) :
  cnn_output = cnn( input_variable )
  print(cnn_output)
  print(target_variable)
  loss = criterion ( cnn_output , target_variable)
  cnn_optimizer.zero_grad ()
  loss.backward( )
  cnn_optimizer.step( )
  #print('loss: ',loss.item())
  return loss.item() #返回损失