5,337
edits
TensorFlow: Difference between revisions
→Usage (TF2)
| Line 21: | Line 21: | ||
This is using the Keras API in tensorflow.keras. | This is using the Keras API in tensorflow.keras. | ||
===Basics=== | ===Basics=== | ||
===Training Loop=== | The general pipeline using Keras is: | ||
* Define a model, typically using [https://www.tensorflow.org/api_docs/python/tf/keras/Sequential tf.keras.Sequential] | |||
* Call [https://www.tensorflow.org/api_docs/python/tf/keras/Model#compile <code>model.compile</code>] | |||
** Here you pass in your optimizer, loss function, metrics, and training callbacks. | |||
* Train your model by calling <code>model.fit</code> | |||
** Here you pass in your training data and some hyperparameters: number of epochs | |||
After training, you can use your model by calling <code>model.evaluate</code> | |||
===Custom Models=== | |||
An alternative way to define a model is by extending the Model class: | |||
* Write a python class which extends <code>tf.keras.Model</code> | |||
* Implement a forward pass in the <code>call</code> method | |||
===Custom Training Loop=== | |||
[https://www.tensorflow.org/guide/keras/train_and_evaluate#part_ii_writing_your_own_training_evaluation_loops_from_scratch Reference]<br> | [https://www.tensorflow.org/guide/keras/train_and_evaluate#part_ii_writing_your_own_training_evaluation_loops_from_scratch Reference]<br> | ||
While you can train using <code>model.compile</code> and <code>model.fit</code>, using your own custom training loop is much more flexable and easier to understand. | While you can train using <code>model.compile</code> and <code>model.fit</code>, using your own custom training loop is much more flexable and easier to understand. | ||