Declare neural networks clearly

Cuando en PyTorch se crea una red neuronal como una lista de capas

	

		
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList([
                  nn.Linear(1, 10),
                  nn.ReLU(),
                  nn.Linear(10, 1)
              ])
	
	

		
	

Luego iterar por ella en el método forward no es tan claro

	

		
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList([
                  nn.Linear(1, 10),
                  nn.ReLU(),
                  nn.Linear(10, 1)
              ])
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList([
                  nn.Linear(1, 10),
                  nn.ReLU(),
                  nn.Linear(10, 1)
              ])
          
          def forward(self, x):
              for layer in self.layers:
                  x = layer(x)
              return x
	
	

		
	

Sin embargo, cuando se crea una red neuronal como un diccionario de capas

	

		
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList([
                  nn.Linear(1, 10),
                  nn.ReLU(),
                  nn.Linear(10, 1)
              ])
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList([
                  nn.Linear(1, 10),
                  nn.ReLU(),
                  nn.Linear(10, 1)
              ])
          
          def forward(self, x):
              for layer in self.layers:
                  x = layer(x)
              return x
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList({
                  'linear': nn.Linear(1, 10),
                  'activation': nn.ReLU(),
                  'output': nn.Linear(10, 1)
              })
	
	

		
	

Luego iterar por ella en el método forward es más claro

	

		
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList([
                  nn.Linear(1, 10),
                  nn.ReLU(),
                  nn.Linear(10, 1)
              ])
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList([
                  nn.Linear(1, 10),
                  nn.ReLU(),
                  nn.Linear(10, 1)
              ])
          
          def forward(self, x):
              for layer in self.layers:
                  x = layer(x)
              return x
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList({
                  'linear': nn.Linear(1, 10),
                  'activation': nn.ReLU(),
                  'output': nn.Linear(10, 1)
              })
import torch
      import torch.nn as nn
      
      class Network(nn.Module):
          def __init__(self):
              super(Network, self).__init__()
              self.layers = nn.ModuleList({
                  'linear': nn.Linear(1, 10),
                  'activation': nn.ReLU(),
                  'output': nn.Linear(10, 1)
              })
          
          def forward(self, x):
              x = self.layers['linear'](x)
              x = self.layers['activation'](x)
              x = self.layers['output'](x)
              return x