Does model.compile() initialize all the weights and biases in Keras (tensorflow backend)?

by

When to use?

If you’re using compile, surely it must be after load_model(). After all, you need a model to compile. (PS: load_model automatically compiles the model with the optimizer that was saved along with the model)

What does compile do?

Compile defines the loss function, the optimizer and the metrics. That’s all.

It has nothing to do with the weights and you can compile a model as many times as you want without causing any problem to pretrained weights.

You need a compiled model to train (because training uses the loss function and the optimizer). But it’s not necessary to compile a model for predicting.

Do you need to use compile more than once?

Only if:

  • You want to change one of these:
    • Loss function
    • Optimizer / Learning rate
    • Metrics
    • The trainable property of some layer
  • You loaded (or created) a model that is not compiled yet. Or your load/save method didn’t consider the previous compilation.

Consequences of compiling again:

If you compile a model again, you will lose the optimizer states.

This means that your training will suffer a little at the beginning until it adjusts the learning rate, the momentums, etc. But there is absolutely no damage to the weights (unless, of course, your initial learning rate is so big that the first training step wildly changes the fine tuned weights).

More Related Contents:

  1. TensorFlow and person recognition in video stream
  2. Keras : How should I prepare input data for RNN?
  3. How to Properly Combine TensorFlow’s Dataset API and Keras?
  4. What is the meaning of the “None” in model.summary of KERAS?
  5. Multivariate LSTM with missing values
  6. Specify connections in NN (in keras)
  7. What are the differences between all these cross-entropy losses in Keras and TensorFlow?
  8. Keras Loss Function with Additional Dynamic Parameter
  9. Using Gensim Fasttext model with LSTM nn in keras
  10. Create keras callback to save model predictions and targets for each batch during training
  11. Obtaining output of an Intermediate layer in TensorFlow/Keras
  12. tf.data with multiple inputs / outputs in Keras
  13. ValueError: Shapes (None, 1) and (None, 2) are incompatible
  14. Keras split train test set when using ImageDataGenerator
  15. In Keras, what exactly am I configuring when I create a stateful `LSTM` layer with N `units`?
  16. Confusion about keras Model: __call__ vs. call vs. predict methods
  17. How can I convert a trained Tensorflow model to Keras?
  18. How to display custom images in TensorBoard using Keras?
  19. What is the difference between keras and tf.keras?
  20. Checkpointing keras model: TypeError: can’t pickle _thread.lock objects
  21. How to replace (or insert) intermediate layer in Keras model?
  22. Choosing number of Steps per Epoch
  23. How to understand static shape and dynamic shape in TensorFlow?
  24. Tensorflow – ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type float)
  25. TypeError: __array__() takes 1 positional argument but 2 were given (Image classification Keras)
  26. Tensorflow 2.0 – AttributeError: module ‘tensorflow’ has no attribute ‘Session’
  27. Tensorflow : logits and labels must have the same first dimension
  28. Simple way to visualize a TensorFlow graph in Jupyter?
  29. feed data into a tf.contrib.data.Dataset like a queue
  30. How is the Keras Conv1D input specified? I seem to be lacking a dimension

Leave a Comment