Metriche e validazione con Keras

Nel precedente esercizio abbiamo addestrato un modello per prevedere le lettere del linguaggio dei segni, ma non è chiaro quanto bene abbia funzionato. In questo esercizio proveremo a rendere i risultati più interpretabili. Poiché non abbiamo usato una validation split, abbiamo osservato miglioramenti solo sul set di training; tuttavia, non è chiaro quanto ciò sia dovuto a overfitting. Inoltre, non avendo fornito una metrica, abbiamo visto solo la diminuzione della funzione di perdita, che non ha un’interpretazione immediata.

Nota: keras è già stato importato per te da tensorflow.

Questo esercizio fa parte del corso

Introduzione a TensorFlow in Python

Visualizza il corso

Istruzioni dell'esercizio

Imposta il primo livello denso con 32 nodi, funzione di attivazione sigmoid e input shape pari a (784,).
Usa l’ottimizzatore root mean square propagation, una loss categorical crossentropy e la metrica accuracy.
Imposta il numero di epoche a 10 e usa il 10% dell’insieme di dati per la validazione.

Esercizio pratico interattivo

Prova a risolvere questo esercizio completando il codice di esempio.

# Define sequential model
model = keras.Sequential()

# Define the first layer
model.add(keras.layers.Dense(____, ____, ____))

# Add activation function to classifier
model.add(keras.layers.Dense(4, activation='softmax'))

# Set the optimizer, loss function, and metrics
model.compile(optimizer='____', loss='____', metrics=['____'])

# Add the number of epochs and the validation split
model.fit(sign_language_features, sign_language_labels, epochs=____, validation_split=____)

Modifica ed esegui il codice

Questo esercizio fa parte del corso

Introduzione a TensorFlow in Python

IntermediárioNível de habilidade

4.8+

Inizia il corso gratis

Before you can build advanced models in TensorFlow 2, you will first need to understand the basics. In this chapter, you’ll learn how to define constants and variables, perform tensor addition and multiplication, and compute derivatives. Knowledge of linear algebra will be helpful, but not necessary.

Exercise 1: Constants and variables Exercise 2: Defining data as constants Exercise 3: Defining variables Exercise 4: Basic operations Exercise 5: Performing element-wise multiplication Exercise 6: Making predictions with matrix multiplication Exercise 7: Summing over tensor dimensions Exercise 8: Advanced operations Exercise 9: Reshaping tensors Exercise 10: Optimizing with gradients Exercise 11: Working with image data

In this chapter, you will learn how to build, solve, and make predictions with models in TensorFlow 2. You will focus on a simple class of models – the linear regression model – and will try to predict housing prices. By the end of the chapter, you will know how to load and manipulate data, construct loss functions, perform minimization, make predictions, and reduce resource use with batch training.

Exercise 1: Input data Exercise 2: Load data using pandas Exercise 3: Setting the data type Exercise 4: Loss functions Exercise 5: Loss functions in TensorFlow Exercise 6: Modifying the loss function Exercise 7: Linear regression Exercise 8: Set up a linear regression Exercise 9: Train a linear model Exercise 10: Multiple linear regression Exercise 11: Batch training Exercise 12: Preparing to batch train Exercise 13: Training a linear model in batches

The previous chapters taught you how to build models in TensorFlow 2. In this chapter, you will apply those same tools to build, train, and make predictions with neural networks. You will learn how to define dense layers, apply activation functions, select an optimizer, and apply regularization to reduce overfitting. You will take advantage of TensorFlow's flexibility by using both low-level linear algebra and high-level Keras API operations to define and train models.

Exercise 1: Dense layers Exercise 2: The linear algebra of dense layers Exercise 3: The low-level approach with multiple examples Exercise 4: Using the dense layer operation Exercise 5: Activation functions Exercise 6: Binary classification problems Exercise 7: Multiclass classification problems Exercise 8: Optimizers Exercise 9: The dangers of local minima Exercise 10: Avoiding local minima Exercise 11: Training a network in TensorFlow Exercise 12: Initialization in TensorFlow Exercise 13: Defining the model and loss function Exercise 14: Training neural networks with TensorFlow

In the final chapter, you'll use high-level APIs in TensorFlow 2 to train a sign language letter classifier. You will use both the sequential and functional Keras APIs to train, validate, make predictions with, and evaluate models. You will also learn how to use the Estimators API to streamline the model definition and training process, and to avoid errors.

Exercise 1: Definire reti neurali con Keras Exercise 2: Il modello sequenziale in Keras Exercise 3: Compilare un modello sequenziale Exercise 4: Definire un modello con input multipli Exercise 5: Training e validazione con Keras Exercise 6: Addestramento con Keras Exercise 7: Metriche e validazione con Keras

Esercizio in corso

Exercise 8: Rilevamento dell'overfitting Exercise 9: Valutare i modelli Exercise 10: Addestrare modelli con l'API Estimators Exercise 11: Prepararti all'addestramento con Estimators Exercise 12: Definire gli Estimator Exercise 13: Congratulazioni!