Skip to main content
grasp.study
About
Explore
Pricing
Log in
Try it for free
Back to course
👋
Welcome to a Grasp lesson
Create a free account
to keep studying and create your own study path.
Feuille de route complète LM
·
Module 11
Training Neural Networks with PyTorch
1
Loading Data with TensorDataset & DataLoader
Prepare a dataset for training using PyTorch's TensorDataset and DataLoader.
2
Loss Functions and Optimizers
Define a loss function (e.g., CrossEntropyLoss) and an optimizer (e.g., Adam).
3
Building a PyTorch Training Loop
Implement a complete training loop in PyTorch (forward pass, loss, backward pass, optimizer step).
Evaluating Model Performance with a Test Loop
Implement an evaluation loop to assess model performance on test data.
5
Training Feedforward Neural Networks on Tabular Data
Train a complete feedforward neural network on a tabular dataset.
6
Implementing Dropout for Overfitting Prevention
Apply dropout as a regularization technique to prevent overfitting in neural networks.
Saving and Loading Model State Dictionaries
Save and load a trained PyTorch model's state dictionary.
8
Making Predictions with Your Model
Use a trained model to make predictions on new, unseen data.
Previous module
Object-Oriented Programming and PyTorch Basics
Next module
Introduction to Deep Learning Architectures