Generare sequenze

Per poter addestrare reti neurali su dati sequenziali, prima devi pre-processarli. Dividerai i dati in coppie input-target, dove gli input sono un certo numero di punti dati consecutivi e il target è il punto dati successivo.

Il tuo compito è definire una funzione per farlo chiamata create_sequences(). Come input riceverà i dati memorizzati in un DataFrame, df, e seq_length, la lunghezza degli input. Come output, dovrebbe restituire due array NumPy: uno con le sequenze di input e l'altro con i relativi target.

Come promemoria, ecco com'è fatto il DataFrame df:

                 timestamp  consumption
0      2011-01-01 00:15:00    -0.704319
...                    ...          ...
140255 2015-01-01 00:00:00    -0.095751

Questo esercizio fa parte del corso

Deep Learning intermedio con PyTorch

Visualizza il corso

Istruzioni dell'esercizio

Itera sull'intervallo del numero di punti dati meno la lunghezza di una sequenza di input.
Definisci gli input x come lo slice di df dalla riga i alla riga i + seq_length e la colonna con indice 1.
Definisci il target y come lo slice di df alla riga con indice i + seq_length e la colonna con indice 1.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

import numpy as np

def create_sequences(df, seq_length):
    xs, ys = [], []
    # Iterate over data indices
    for i in range(____):
      	# Define inputs
        x = df.iloc[____, ____]
        # Define target
        y = df.iloc[____, ____]
        xs.append(x)
        ys.append(y)
    return np.array(xs), np.array(ys)

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 and object-oriented programming Exercise 2: PyTorch Dataset Exercise 3: PyTorch DataLoader Exercise 4: PyTorch Model Exercise 5: Optimizers, training, and evaluation Exercise 6: Training loop Exercise 7: Optimizers Exercise 8: Model evaluation Exercise 9: Vanishing and exploding gradients Exercise 10: Initialization and activation Exercise 11: Activations: ReLU vs. ELU Exercise 12: Batch Normalization

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: Gestire le sequenze con PyTorch Exercise 2: Generare sequenze

Esercizio in corso

Exercise 3: Insieme di dati sequenziale Exercise 4: Reti neurali ricorrenti Exercise 5: Architetture sequenziali Exercise 6: Costruire un RNN per il forecasting Exercise 7: Celle LSTM e GRU Exercise 8: RNN vs. LSTM vs. GRU Exercise 9: Rete LSTM Exercise 10: Rete GRU Exercise 11: Addestrare e valutare le RNN Exercise 12: Ciclo di training RNN Exercise 13: Valutare i modelli di forecasting

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