Make a custom loss function in keras

Question

Hi, I have been trying to make a custom loss function in Keras for dice_error_coefficient. It has its implementations in TensorBoard and I tried using the same function in Keras with TensorFlow but it keeps returning a NoneType when used model.train_on_batch or model.fit whereas it gives proper values when used in metrics in the model. Can please someone help me out with what should I do? I have tried following libraries like Keras-FCN by ahundt where he has used custom loss functions but none of it seems to work. The target and output in the code are y_true and y_pred respectively as used in the losses.py file in Keras.

def dice_hard_coe(target, output, threshold=0.5, axis=[1,2], smooth=1e-5):
    """References
    -----------
    - `Wiki-Dice <https://en.wikipedia.org/wiki/Sørensen–Dice_coefficient>`_
    """

    output = tf.cast(output > threshold, dtype=tf.float32)
    target = tf.cast(target > threshold, dtype=tf.float32)
    inse = tf.reduce_sum(tf.multiply(output, target), axis=axis)
    l = tf.reduce_sum(output, axis=axis)
    r = tf.reduce_sum(target, axis=axis)
    hard_dice = (2. * inse + smooth) / (l + r + smooth)
    hard_dice = tf.reduce_mean(hard_dice)
    return hard_dice

Answer 1

Yes, it possible to build the custom loss function in keras by adding new layers to model and compile them with various loss value based on datasets (loss = Binary_crossentropy if datasets have two target values such as yes or no ). Create a Sequential model by passing a list of layer instances to the constructor:

from keras.models import Sequential

from keras.layers import Dense, Activation

model = Sequential([Dense(32, input_dim=784), Activation('relu'), Dense(10),  Activation('softmax'),])

model = Sequential()

//You can also simply add layers via the .add() method:

model.add(Dense(32, input_dim=784))

model.add(Activation('relu'))

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

model.compile(loss='binary_crossentropy', optimizer='sgd', metrics=['accuracy'])

If You want to learn Machine learning, visit this machine learning interview questions.