Batch Normalization

Come miglioramento finale dell’architettura del modello, aggiungi uno strato di batch normalization dopo ciascuno dei due strati lineari. Il trucco della batch norm tende ad accelerare la convergenza dell’addestramento e protegge il modello dai problemi di vanishing ed exploding gradients.

Sia torch.nn sia torch.nn.init sono già stati importati rispettivamente come nn e init. Una volta implementata la modifica nell’architettura del modello, preparati a rispondere a una breve domanda su come funziona la batch normalization!

Questo esercizio fa parte del corso

Deep Learning intermedio con PyTorch

Visualizza il corso

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

class Net(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(9, 16)
        # Add two batch normalization layers
        ____ = ____
        self.fc2 = nn.Linear(16, 8)
        ____ = ____
        self.fc3 = nn.Linear(8, 1)
        
        init.kaiming_uniform_(self.fc1.weight)
        init.kaiming_uniform_(self.fc2.weight)
        init.kaiming_uniform_(self.fc3.weight, nonlinearity="sigmoid")

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Deep Learning intermedio con PyTorch

IntermediárioNível de habilidade

4.8+

Inizia il corso gratis

Learn how to train neural networks in a robust way. In this chapter, you will use object-oriented programming to define PyTorch datasets and models and refresh your knowledge of training and evaluating neural networks. You will also get familiar with different optimizers and, finally, get to grips with various techniques that help mitigate the problems of unstable gradients so ubiquitous in neural nets training.

Exercise 1: PyTorch e programmazione orientata agli oggetti Exercise 2: Dataset PyTorch Exercise 3: PyTorch DataLoader Exercise 4: Modello PyTorch Exercise 5: Ottimizzatori, training e valutazione Exercise 6: Training loop Exercise 7: Ottimizzatori Exercise 8: Valutazione del modello Exercise 9: Gradienti che svaniscono ed esplodono Exercise 10: Inizializzazione e attivazione Exercise 11: Attivazioni: ReLU vs. ELU Exercise 12: Batch Normalization

Esercizio in corso

Train neural networks to solve image classification tasks. In this chapter, you will learn how to handle image data in PyTorch and get to grips with convolutional neural networks (CNNs). You will practice training and evaluating an image classifier while learning about how to improve the model performance with data augmentation.

Exercise 1: Handling images with PyTorch Exercise 2: Image dataset Exercise 3: Data augmentation Exercise 4: Data augmentation in PyTorch Exercise 5: Convolutional Neural Networks Exercise 6: The convolutional layer Exercise 7: Building convolutional networks Exercise 8: Training image classifiers Exercise 9: Choosing augmentations Exercise 10: Dataset with augmentations Exercise 11: Image classifier training loop Exercise 12: Evaluating image classifiers Exercise 13: Multi-class model evaluation Exercise 14: Analyzing metrics per class

Build and train recurrent neural networks (RNNs) for processing sequential data such as time series, text, or audio. You will learn about the two most popular recurrent architectures, Long-Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks, as well as how to prepare sequential data for model training. You will practice your skills by training and evaluating a recurrent model for predicting electricity consumption.

Exercise 1: Handling sequences with PyTorch Exercise 2: Generating sequences Exercise 3: Sequential Dataset Exercise 4: Recurrent Neural Networks Exercise 5: Sequential architectures Exercise 6: Building a forecasting RNN Exercise 7: LSTM and GRU cells Exercise 8: RNN vs. LSTM vs. GRU Exercise 9: LSTM network Exercise 10: GRU network Exercise 11: Training and evaluating RNNs Exercise 12: RNN training loop Exercise 13: Evaluating forecasting models

Build multi-input and multi-output models, demonstrating how they can handle tasks requiring more than one input or generating multiple outputs. You will explore how to design and train these models using PyTorch and delve into the crucial topic of loss weighting in multi-output models. This involves understanding how to balance the importance of different tasks when training a model to perform multiple tasks simultaneously.

Exercise 1: Multi-input models Exercise 2: Two-input dataset Exercise 3: Two-input model Exercise 4: Training two-input model Exercise 5: Multi-output models Exercise 6: Two-output Dataset and DataLoader Exercise 7: Two-output model architecture Exercise 8: Training multi-output models Exercise 9: Evaluation of multi-output models and loss weighting Exercise 10: Multi-output model evaluation Exercise 11: Loss weighting Exercise 12: Wrap-up