Keras Loss Function with Additional Dynamic Parameter

by

OK. Here is an example. 

from keras.layers import Input, Dense, Conv2D, MaxPool2D, Flatten
from keras.models import Model
from keras.losses import categorical_crossentropy

def sample_loss( y_true, y_pred, is_weight ) :
    return is_weight * categorical_crossentropy( y_true, y_pred ) 

x = Input(shape=(32,32,3), name="image_in")
y_true = Input( shape=(10,), name="y_true" )
is_weight = Input(shape=(1,), name="is_weight")
f = Conv2D(16,(3,3),padding='same')(x)
f = MaxPool2D((2,2),padding='same')(f)
f = Conv2D(32,(3,3),padding='same')(f)
f = MaxPool2D((2,2),padding='same')(f)
f = Conv2D(64,(3,3),padding='same')(f)
f = MaxPool2D((2,2),padding='same')(f)
f = Flatten()(f)
y_pred = Dense(10, activation='softmax', name="y_pred" )(f)
model = Model( inputs=[x, y_true, is_weight], outputs=y_pred, name="train_only" )
model.add_loss( sample_loss( y_true, y_pred, is_weight ) )
model.compile( loss=None, optimizer="sgd" )
print model.summary()

Note, since you’ve add loss through add_loss(), you don’t have to do it through compile( loss=xxx ).

With regards to train a model, nothing is special except you move y_true to your input end. See below

import numpy as np 
a = np.random.randn(8,32,32,3)
a_true = np.random.randn(8,10)
a_is_weight = np.random.randint(0,2,size=(8,1))
model.fit( [a, a_true, a_is_weight] )

Finally, you can make a testing model (which share all weights in model) for easier use, i.e. 

test_model = Model( inputs=x, outputs=y_pred, name="test_only" )
a_pred = test_model.predict( a )

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. Does model.compile() initialize all the weights and biases in Keras (tensorflow backend)?
  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 does TensorFlow name tensors?
  24. Keras Sequential model with multiple inputs
  25. TensorFlow: numpy.repeat() alternative
  26. How to get other metrics in Tensorflow 2.0 (not only accuracy)?
  27. Tensorflow (.pb) format to Keras (.h5)
  28. Save and load model optimizer state
  29. Keras misinterprets training data shape
  30. parallelising tf.data.Dataset.from_generator

Leave a Comment