De history-callback

De history-callback wordt standaard geretourneerd elke keer dat je een model traint met de methode .fit(). Je kunt deze metrieken benaderen via de history-dictionary in het geretourneerde h_callback-object met de bijbehorende sleutels.

De irrigatiemachine model die je in de vorige les hebt gebouwd, is voor je geladen om te trainen, samen met de features en labels die nu zijn geladen als X_train, y_train, X_test, y_test. Deze keer sla je de history-callback van het model op en gebruik je de parameter validation_data tijdens het trainen.

Je plot de resultaten die in history zijn opgeslagen met plot_accuracy() en plot_loss(), twee eenvoudige matplotlib-functies. Je kunt de code ervan bekijken in de console door show_code(plot_loss) te plakken.

Kijk mee achter de schermen van onze training!

Deze oefening maakt deel uit van de cursus

Introductie tot Deep Learning met Keras

Cursus bekijken

Oefeninstructies

Train je model op X_train en y_train, en valideer na elke epoch op X_test en y_test.
Gebruik plot_loss en haal loss en val_loss uit h_callback.
Gebruik plot_accuracy en haal accuracy en val_accuracy uit h_callback.

Praktische interactieve oefening

Probeer deze oefening eens door deze voorbeeldcode in te vullen.

# Train your model and save its history
h_callback = ____.____(____, ____, epochs = 25,
               validation_data=(____, ____))

# Plot train vs test loss during training
plot_loss(h_callback.history[____], h_callback.history[____])

# Plot train vs test accuracy during training
plot_accuracy(h_callback.history[____], h_callback.history[____])

Code bewerken en uitvoeren

Deze oefening maakt deel uit van de cursus

Introductie tot Deep Learning met Keras

SkillTag.level.intermediateSkillTag.label

4.8+

Begin de cursus gratis

In this first chapter, you will get introduced to neural networks, understand what kind of problems they can solve, and when to use them. You will also build several networks and save the earth by training a regression model that approximates the orbit of a meteor that is approaching us!

Exercise 1: What is Keras?Exercise 2: Describing Keras Exercise 3: Would you use deep learning?Exercise 4: Your first neural network Exercise 5: Hello nets!Exercise 6: Counting parameters Exercise 7: Build as shown!Exercise 8: Surviving a meteor strike Exercise 9: Specifying a model Exercise 10: Training Exercise 11: Predicting the orbit!

By the end of this chapter, you will know how to solve binary, multi-class, and multi-label problems with neural networks. All of this by solving problems like detecting fake dollar bills, deciding who threw which dart at a board, and building an intelligent system to water your farm. You will also be able to plot model training metrics and to stop training and save your models when they no longer improve.

Exercise 1: Binaire classificatie Exercise 2: Dollarbiljetten verkennen Exercise 3: Een binaire classificatiemodel Exercise 4: Is dit dollarbiljet nep?Exercise 5: Multiklassenclassificatie Exercise 6: Een multi-class model Exercise 7: Bereid je gegevensset voor Exercise 8: Trainen op darters Exercise 9: Softmax-voorspellingen Exercise 10: Multi-labelclassificatie Exercise 11: Een irrigatiemachine Exercise 12: Trainen met meerdere labels Exercise 13: Keras-callbacks Exercise 14: De history-callback

Huidige oefening

Exercise 15: Je model vroegtijdig stoppen Exercise 16: Een combinatie van callbacks

In the previous chapters, you've trained a lot of models! You will now learn how to interpret learning curves to understand your models as they train. You will also visualize the effects of activation functions, batch-sizes, and batch-normalization. Finally, you will learn how to perform automatic hyperparameter optimization to your Keras models using sklearn.

Exercise 1: Learning curves Exercise 2: Learning the digits Exercise 3: Is the model overfitting?Exercise 4: Do we need more data?Exercise 5: Activation functions Exercise 6: Different activation functions Exercise 7: Comparing activation functions Exercise 8: Comparing activation functions II Exercise 9: Batch size and batch normalization Exercise 10: Changing batch sizes Exercise 11: Batch normalizing a familiar model Exercise 12: Batch normalization effects Exercise 13: Hyperparameter tuning Exercise 14: Preparing a model for tuning Exercise 15: Tuning the model parameters Exercise 16: Training with cross-validation

It's time to get introduced to more advanced architectures! You will create an autoencoder to reconstruct noisy images, visualize convolutional neural network activations, use deep pre-trained models to classify images and learn more about recurrent neural networks and working with text as you build a network that predicts the next word in a sentence.

Exercise 1: Tensors, layers, and autoencoders Exercise 2: It's a flow of tensors Exercise 3: Neural separation Exercise 4: Building an autoencoder Exercise 5: De-noising like an autoencoder Exercise 6: Intro to CNNs Exercise 7: Building a CNN model Exercise 8: Looking at convolutions Exercise 9: Preparing your input image Exercise 10: Using a real world model Exercise 11: Intro to LSTMs Exercise 12: Text prediction with LSTMs Exercise 13: Build your LSTM model Exercise 14: Decode your predictions Exercise 15: Test your model!Exercise 16: You're done!