De dense-laagoperatie gebruiken

We hebben nu gezien hoe je dense lagen in tensorflow definieert met lineaire algebra. In deze oefening slaan we de lineaire algebra over en laten we keras de details uitwerken. Zo kunnen we onderstaand netwerk bouwen — met 2 verborgen lagen en 10 features — met minder code dan we nodig hadden voor het netwerk met 1 verborgen laag en 3 features.

This image depicts an neural network with 10 inputs nodes and 1 output node.

Om dit netwerk te bouwen, moeten we drie dense lagen definiëren. Elke laag neemt de vorige laag als input, vermenigvuldigt die met gewichten en past een activatiefunctie toe. Let op: de inputdata is al gedefinieerd en beschikbaar als een 100x10-tensor: borrower_features. Daarnaast is de module keras.layers beschikbaar.

Deze oefening maakt deel uit van de cursus

Introductie tot TensorFlow in Python

Cursus bekijken

Oefeninstructies

Zet dense1 op een dense laag met 7 outputnodes en een sigmoid-activatiefunctie.
Definieer dense2 als een dense laag met 3 outputnodes en een sigmoid-activatiefunctie.
Definieer predictions als een dense laag met 1 outputnode en een sigmoid-activatiefunctie.
Print de shapes van dense1, dense2 en predictions in die volgorde met de methode .shape. Waarom hebben elk van deze tensors 100 rijen?

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Define the first dense layer
dense1 = keras.layers.Dense(____, activation='____')(borrower_features)

# Define a dense layer with 3 output nodes
dense2 = ____

# Define a dense layer with 1 output node
predictions = ____

# Print the shapes of dense1, dense2, and predictions
print('\n shape of dense1: ', dense1.shape)
print('\n shape of dense2: ', ____.shape)
print('\n shape of predictions: ', ____.shape)

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Introductie tot TensorFlow in Python

SkillTag.level.intermediateSkillTag.label

4.8+

Begin de cursus 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: Dichte lagen Exercise 2: De lineaire algebra van dense lagen Exercise 3: De low-level aanpak met meerdere voorbeelden Exercise 4: De dense-laagoperatie gebruiken

Huidige oefening

Exercise 5: Activatiefuncties Exercise 6: Binaire classificatieproblemen Exercise 7: Multiclass-classificatieproblemen Exercise 8: Optimizers Exercise 9: De gevaren van lokale minima Exercise 10: Lokale minima vermijden Exercise 11: Een netwerk trainen in TensorFlow Exercise 12: Initialisatie in TensorFlow Exercise 13: Het model en de verliesfunctie definiëren Exercise 14: Neurale netwerken trainen met 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: Defining neural networks with Keras Exercise 2: The sequential model in Keras Exercise 3: Compiling a sequential model Exercise 4: Defining a multiple input model Exercise 5: Training and validation with Keras Exercise 6: Training with Keras Exercise 7: Metrics and validation with Keras Exercise 8: Overfitting detection Exercise 9: Evaluating models Exercise 10: Training models with the Estimators API Exercise 11: Preparing to train with Estimators Exercise 12: Defining Estimators Exercise 13: Congratulations!