deep-learning-with-python-notebooks
deep-learning-with-python-notebooks copied to clipboard
fchollet
Jupyter notebooks for the code samples of the book "Deep Learning with Python"
At the end of the "Key Attributes" section, just before figure 2.2, it is written that we display the fourth element, but it's the fifth: ... Let’s display the fourth...
At the end of Chapter 8, "Fine-tuning a pretrained model", it seems that conv_base.trainable = True is missing from the code (though it is mentionned in the book in the...
In Listing 8.9 of Chapter 8, the batch size is set to 64. But later in Listing 8.14, the batch size becomes 32. Where is the batch size changed?
**Title:** Fix department label inconsistency in custom model example **Description:** In one of the custom model examples, the department classification head is defined as: ```python self.department_classifier = layers.Dense(num_departments, activation="softmax") ```...
Running listing 10.10 on colab fails with an InvalidArgumentError and the error message "Only one input size may be -1, not both 0 and 1". (see https://colab.research.google.com/github/fchollet/deep-learning-with-python-notebooks/blob/master/chapter10_dl-for-timeseries.ipy)
According to F. Chollet, the code he shared for the second ed of his book is supposed to run under TF 2.6. When I try running that code in more...
in order to use the vectorizer, the data must be preprocessed. the dataset here is used contains non-standard character. the added code snippet ensures that all the data read from...
Self explanatory. The source code of the 3rd edition of the book Deep Learning with Python is suppposed to be at the link, but the notebooks for the third edition...
`model.compile(optimizer="rmsprop", loss={"priority": "mean_squared_error", "department": "categorical_crossentropy"}, metrics={"priority": ["mean_absolute_error"], "department": ["accuracy"]}) model.fit({"title": title_data, "text_body": text_body_data, "tags": tags_data}, {"priority": priority_data, "department": department_data}, epochs=1) model.evaluate({"title": title_data, "text_body": text_body_data, "tags": tags_data}, {"priority": priority_data, "department": department_data})...
