Implementare la leaky ReLU

Sebbene la ReLU sia ampiamente utilizzata, imposta gli input negativi a 0, producendo gradienti nulli per quei valori. Questo può impedire a parti del modello di apprendere.

La leaky ReLU supera questo limite consentendo piccoli gradienti per gli input negativi, controllati dal parametro negative_slope. Invece di 0, gli input negativi vengono moltiplicati per questo piccolo valore, mantenendo attivo l’apprendimento del modello.

In questo esercizio implementerai la funzione leaky ReLU in PyTorch e farai pratica a usarla. Il pacchetto torch e torch.nn come nn sono già stati importati.

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.

# Create a leaky relu function in PyTorch
leaky_relu_pytorch = ____

x = torch.tensor(-2.0)
# Call the above function on the tensor x
output = ____
print(output)

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

Esercizio in corso

Exercise 10: Capire le funzioni di attivazione Exercise 11: Learning rate e momentum Exercise 12: Sperimentare con il learning rate 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