Overfitting

Hi,
Any tips to deal with overfitting? Can we add dropouts?
For example, in

torchcde/example/time_series_classification.py

Lines 37 to 42 in 9ff6aba

    
           def forward(self, t, z): 
        
               # z has shape (batch, hidden_channels) 
        
               z = self.linear1(z) 
        
               z = z.relu() 
        
               z = self.linear2(z) 
        
               ######################

Can we add a dropout somewhere?

I am new to NeuralCDEs, apologies if I am missing anything obvious.

	def forward(self, t, z):
	# z has shape (batch, hidden_channels)
	z = self.linear1(z)
	z = z.relu()
	z = self.linear2(z)
	######################