Keras Custom loss function to pass arguments other than y_true and y_pred

by

New answer

I think you’re looking exactly for L2 regularization. Just create a regularizer and add it in the layers:

from keras.regularizers import l2

#in the target layers, Dense, Conv2D, etc.:
layer = Dense(units, ..., kernel_regularizer = l2(some_coefficient))

You can use bias_regularizer as well.
The some_coefficient var is multiplied by the square value of the weight.

PS: if val in your code is constant, it should not harm your loss. But you can still use the old answer below for val.

Old answer

Wrap the Keras expected function (with two parameters) into an outer function with your needs:

def customLoss(layer_weights, val = 0.01):
    
    def lossFunction(y_true,y_pred):    
        loss = mse(y_true, y_pred)
        loss += K.sum(val, K.abs(K.sum(K.square(layer_weights), axis=1)))
        return loss

    return lossFunction

model.compile(loss=customLoss(weights,0.03), optimizer =..., metrics = ...)

Notice that layer_weights must come directly from the layer as a “tensor”, so you can’t use get_weights(), you must go with someLayer.kernel and someLayer.bias. (Or the respective var name in case of layers that use different names for their trainable parameters).

The answer here shows how to deal with that if your external vars are variable with batches: How to define custom cost function that depends on input when using ImageDataGenerator in Keras?

More Related Contents:

  1. Keras, How to get the output of each layer?
  2. Make a custom loss function in keras
  3. Keras not training on entire dataset
  4. Could not load dynamic library ‘cudart64_101.dll’ on tensorflow CPU-only installation
  5. Deep-Learning Nan loss reasons
  6. Failed to get convolution algorithm. This is probably because cuDNN failed to initialize,
  7. How to apply gradient clipping in TensorFlow?
  8. Why is TensorFlow 2 much slower than TensorFlow 1?
  9. NotImplementedError: Layers with arguments in `__init__` must override `get_config`
  10. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  11. What is the difference between tf.keras and tf.python.keras?
  12. Keras replacing input layer
  13. Keras Sequential model with multiple inputs
  14. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  15. expected ndim=3, found ndim=2
  16. This model has not yet been built error on model.summary()
  17. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  18. How can I use a pre-trained neural network with grayscale images?
  19. Dimension of shape in conv1D
  20. Removing then Inserting a New Middle Layer in a Keras Model
  21. How to know if underfitting or overfitting is occuring?
  22. Loading a trained Keras model and continue training
  23. Custom loss function in Keras
  24. Save and load model optimizer state
  25. Keras misinterprets training data shape
  26. How do I get the weights of a layer in Keras?
  27. Multiple outputs in Keras
  28. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  29. How to implement Grad-CAM on a trained network
  30. Unexpected keyword argument ‘ragged’ in Keras

Leave a Comment