Sperimentare con il learning rate

In questo esercizio, il tuo obiettivo è trovare il learning rate ottimale in modo che l'ottimizzatore trovi il minimo della funzione non convessa \(x^{4} + x^{3} - 5x^{2}\) in dieci passaggi.

Sperimenterai con tre valori diversi di learning rate. Per questo problema, prova valori di learning rate tra 0.001 e 0.1.

Ti viene fornita la funzione optimize_and_plot() che prende il learning rate come primo argomento. Questa funzione eseguirà 10 passaggi dell'ottimizzatore SGD e mostrerà i risultati.

Questo esercizio fa parte del corso

Introduzione al Deep Learning con PyTorch

Visualizza il corso

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# Try a first learning rate value
lr0 = ____
optimize_and_plot(lr=lr0)

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Introduzione al Deep Learning con PyTorch

IntermediárioNível de habilidade

4.8+

Inizia il corso gratis

Self-driving cars, smartphones, search engines... Deep learning is now everywhere. Before you begin building complex models, you will become familiar with PyTorch, a deep learning framework. You will learn how to manipulate tensors, create PyTorch data structures, and build your first neural network in PyTorch with linear layers.

Exercise 1: Introduction to deep learning with PyTorch Exercise 2: Getting started with PyTorch tensors Exercise 3: Checking and adding tensors Exercise 4: Neural networks and layers Exercise 5: Linear layer network Exercise 6: Understanding weights Exercise 7: Hidden layers and parameters Exercise 8: Your first neural network Exercise 9: Stacking linear layers Exercise 10: Counting the number of parameters

To train a neural network in PyTorch, you will first need to understand additional components, such as activation and loss functions. You will then realize that training a network requires minimizing that loss function, which is done by calculating gradients. You will learn how to use these gradients to update your model's parameters.

Exercise 1: Discovering activation functions Exercise 2: Activate your understanding!Exercise 3: The sigmoid and softmax functions Exercise 4: Running a forward pass Exercise 5: Building a binary classifier in PyTorch Exercise 6: From regression to multi-class classification Exercise 7: Using loss functions to assess model predictions Exercise 8: Creating one-hot encoded labels Exercise 9: Calculating cross entropy loss Exercise 10: Using derivatives to update model parameters Exercise 11: Accessing the model parameters Exercise 12: Updating the weights manually Exercise 13: Using the PyTorch optimizer

Now that you've learned the key components of a neural network, you'll train one using a training loop. You'll explore potential issues like vanishing gradients and learn strategies to address them, such as alternative activation functions and tuning learning rate and momentum.

Exercise 1: Approfondiamo il caricamento dei dati Exercise 2: Uso di TensorDataset Exercise 3: Uso di DataLoader Exercise 4: Scrivere il nostro primo ciclo di training Exercise 5: Uso di MSELoss Exercise 6: Scrivere un training loop Exercise 7: Funzioni di attivazione ReLU Exercise 8: Implementare ReLU Exercise 9: Implementare la leaky ReLU Exercise 10: Capire le funzioni di attivazione Exercise 11: Learning rate e momentum Exercise 12: Sperimentare con il learning rate

Esercizio in corso

Exercise 13: Sperimentare con il momentum

Training a deep learning model is an art, and to make sure our model is trained correctly, we need to keep track of certain metrics during training, such as the loss or the accuracy. We will learn how to calculate such metrics and how to reduce overfitting.

Exercise 1: Layer initialization and transfer learning Exercise 2: Fine-tuning process Exercise 3: Freeze layers of a model Exercise 4: Layer initialization Exercise 5: Evaluating model performance Exercise 6: Writing the evaluation loop Exercise 7: Calculating accuracy using torchmetrics Exercise 8: Fighting overfitting Exercise 9: Experimenting with dropout Exercise 10: Understanding overfitting Exercise 11: Improving model performance Exercise 12: Implementing random search Exercise 13: Wrap-up video