Leaky ReLU implementeren

Hoewel ReLU veel wordt gebruikt, zet het negatieve inputwaarden op 0, wat resulteert in nulgradiënten voor die waarden. Dit kan voorkomen dat delen van het model leren.

Leaky ReLU lost dit op door kleine gradiënten toe te staan voor negatieve inputs, geregeld door de parameter negative_slope. In plaats van 0 worden negatieve inputs met deze kleine waarde geschaald, zodat het leren van het model actief blijft.

In deze oefening implementeer je de leaky ReLU-functie in PyTorch en oefen je met het gebruik ervan. Het pakket torch en torch.nn als nn zijn al geïmporteerd.

Deze oefening maakt deel uit van de cursus

Introductie tot Deep Learning met PyTorch

Cursus bekijken

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# 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)

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Introductie tot Deep Learning met PyTorch

SkillTag.level.intermediateSkillTag.label

4.8+

Begin de cursus 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: Dieper duiken in het laden van data Exercise 2: TensorDataset gebruiken Exercise 3: DataLoader gebruiken Exercise 4: Onze eerste trainingslus schrijven Exercise 5: MSELoss gebruiken Exercise 6: Een trainingslus schrijven Exercise 7: ReLU-activatiefuncties Exercise 8: ReLU implementeren Exercise 9: Leaky ReLU implementeren

Huidige oefening

Exercise 10: Activatiefuncties begrijpen Exercise 11: Learning rate en momentum Exercise 12: Experimenteren met de learning rate Exercise 13: Experimenteren met 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