Initialisierung in TensorFlow

Eine gute Initialisierung kann die Zeit verkürzen, die zum Finden des globalen Minimums nötig ist. In dieser Übung initialisieren wir Gewichte und Biases für ein neuronales Netz, das Kreditkarten-Standardentscheidungen vorhersagen soll. Um ein besseres Verständnis zu bekommen, nutzen wir den Low-Level-Ansatz mit linearer Algebra statt Komfortfunktionen und High-Level-keras-Operationen. Außerdem erweitern wir die Eingabefeatures von 3 auf 23. Mehrere Operationen wurden aus tensorflow importiert: Variable(), random(), und ones().

Diese Übung ist Teil des Kurses

<Kurs>Einführung in TensorFlow mit Python</Kurs>

Übungsanweisungen

Initialisiere die Gewichte der ersten Schicht, w1, als Variable() mit der Form [23, 7], gezogen aus einer Normalverteilung.
Initialisiere den Bias der ersten Schicht mit Einsen.
Verwende eine Ziehung aus der Normalverteilung, um w2 als Variable() mit der Form [7, 1] zu initialisieren.
Definiere b2 als Variable() und setze den Anfangswert auf 0.0.

Interaktive praktische Übung

Versuche dich an dieser Übung, indem du diesen Beispielcode vervollständigst.

# Define the layer 1 weights
w1 = ____(random.normal([____, ____]))

# Initialize the layer 1 bias
b1 = Variable(____([7]))

# Define the layer 2 weights
w2 = ____

# Define the layer 2 bias
b2 = ____

Code bearbeiten und ausführen

Diese Übung ist Teil des Kurses

<Kurs>Einführung in TensorFlow mit Python</Kurs>

Mittlere SchwierigkeitSchwierigkeitsgrad

4.8+

Kurs kostenlos starten

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 Schichten Exercise 2: Die Lineare Algebra dichter Schichten Exercise 3: Der Low-Level-Ansatz mit mehreren Beispielen Exercise 4: Die Dense-Layer-Operation verwenden Exercise 5: Aktivierungsfunktionen Exercise 6: Binäre Klassifikationsprobleme Exercise 7: Multiclass-Klassifikationsprobleme Exercise 8: Optimierer Exercise 9: Die Tücken lokaler Minima Exercise 10: Lokale Minima vermeiden Exercise 11: Ein Netzwerk in TensorFlow trainieren Exercise 12: Initialisierung in TensorFlow

Aktuelle Übung

Exercise 13: Modell und Verlustfunktion definieren Exercise 14: Neuronale Netze mit TensorFlow trainieren

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!