Make a custom loss function in keras

by

There are two steps in implementing a parameterized custom loss function in Keras. First, writing a method for the coefficient/metric. Second, writing a wrapper function to format things the way Keras needs them to be.

  1. It’s actually quite a bit cleaner to use the Keras backend instead of tensorflow directly for simple custom loss functions like DICE. Here’s an example of the coefficient implemented that way:

    import keras.backend as K
def dice_coef(y_true, y_pred, smooth, thresh):
    y_pred = y_pred > thresh
    y_true_f = K.flatten(y_true)
    y_pred_f = K.flatten(y_pred)
    intersection = K.sum(y_true_f * y_pred_f)

    return (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)

  2. Now for the tricky part. Keras loss functions must only take (y_true, y_pred) as parameters. So we need a separate function that returns another function. 

    def dice_loss(smooth, thresh):
  def dice(y_true, y_pred)
    return -dice_coef(y_true, y_pred, smooth, thresh)
  return dice

Finally, you can use it as follows in Keras compile.

# build model 
model = my_model()
# get the loss function
model_dice = dice_loss(smooth=1e-5, thresh=0.5)
# compile model
model.compile(loss=model_dice)

More Related Contents:

  1. Keras Dense layer’s input is not flattened
  2. Keras not training on entire dataset
  3. Deep-Learning Nan loss reasons
  4. How to apply gradient clipping in TensorFlow?
  5. Can Keras with Tensorflow backend be forced to use CPU or GPU at will?
  6. Proper way to feed time-series data to stateful LSTM?
  7. ValueError at /image/ Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 4), dtype=float32) is not an element of this graph
  8. Keras custom loss function: Accessing current input pattern
  9. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  10. How can I use a pre-trained neural network with grayscale images?
  11. Removing then Inserting a New Middle Layer in a Keras Model
  12. How to know if underfitting or overfitting is occuring?
  13. Save and load model optimizer state
  14. Unknown initializer: GlorotUniform when loading Keras model
  15. How to create a keras layer with a custom gradient in TF2.0?
  16. ‘Tensor’ object has no attribute ‘lower’
  17. ValueError: Output tensors to a Model must be the output of a TensorFlow `Layer`
  18. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  19. How is the Keras Conv1D input specified? I seem to be lacking a dimension
  20. How can I use a weight matrix created by a trained neural network to make predictions in another file?
  21. Keras, How to get the output of each layer?
  22. Can I run Keras model on gpu?
  23. Loading a trained Keras model and continue training
  24. How to save final model using keras?
  25. How to use fit_generator with multiple inputs
  26. Multiple outputs in Keras
  27. How to implement Grad-CAM on a trained network
  28. Unexpected keyword argument ‘ragged’ in Keras
  29. Can I send callbacks to a KerasClassifier?
  30. TensorFlow, “‘module’ object has no attribute ‘placeholder'”

Leave a Comment