Declare neural networks clearly

22 of october of 2024

Declarar redes neuronales claramente

Disclaimer: This post has been translated to English using a machine translation model. Please, let me know if you find any mistakes.

When in PyTorch a neural network is created as a list of layers

	
		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)
              ])

Then iterating through it in the forward method is not so clear

	
		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

However, when creating a neural network as a dictionary of layers

	
		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)
              })

Then iterating through it in the forward method is clearer

	
		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

Continue reading

Langchain with open source integrations

Learn how to use Langchain with the most popular open-source integrations. In this post, we will explore how to integrate Langchain with ChromaDB, Ollama and HuggingFace.

RAG fundamentals

Forget about Ctrl+F! 🤯 With RAG, your documents will answer your questions directly. 😎 Step-by-step tutorial with Hugging Face and ChromaDB. Unleash the power of AI (and show off to your friends)! 💪

Conventional commits

😠 Are your commits written in alien language? 👽 Join the club! 😅 Learn Conventional Commits in Python and stop torturing your team with cryptic messages. git-changelog and commitizen will be your new best friends. 🤝

Last posts -->

Have you seen these projects?

Subtify

GPU monitor

Alfred

View all projects -->

Do you want to apply AI in your project? Contact me!

Do you want to improve with these tips?

DataLoader with pin_memory and num_workers

Increase DataLoader performance with pin_memory and num_workers

py-smi

Python library to get GPU data like `nvidia-smi`

Memory Calculator

Space to calculate the memory needed to run a model

Last tips -->

Use this locally

Hugging Face spaces allow us to run models with very simple demos, but what if the demo breaks? Or if the user deletes it? That's why I've created docker containers with some interesting spaces, to be able to use them locally, whatever happens. In fact, if you click on any project view button, it may take you to a space that doesn't work.