fchollet / deep-learning-with-python-notebooks

Jupyter notebooks for the code samples of the book "Deep Learning with Python"
MIT License
18.17k stars 8.53k forks source link

Ch 6.3.2 Missing denominators in code sample #104

Open aamirg opened 5 years ago

aamirg commented 5 years ago

On page 212 under code listing 6.34 Preparing the training, validation and test generators, the last two lines which initialize the _valsteps and _teststeps are missing their denominators. Without dividing by the batch_size each training epoch can take close to 15 minutes.

The code from the github notebook includes the denominator -

val_steps = (300000 - 200001 - lookback) // batch_size test_steps = (len(float_data) - 300001 - lookback) // batch_size

image