Multiple outputs in Keras

by 
from keras.models import Model
from keras.layers import *    

#inp is a "tensor", that can be passed when calling other layers to produce an output 
inp = Input((10,)) #supposing you have ten numeric values as input 


#here, SomeLayer() is defining a layer, 
#and calling it with (inp) produces the output tensor x
x = SomeLayer(blablabla)(inp) 
x = SomeOtherLayer(blablabla)(x) #here, I just replace x, because this intermediate output is not interesting to keep


#here, I want to keep the two different outputs for defining the model
#notice that both left and right are called with the same input x, creating a fork
out1 = LeftSideLastLayer(balbalba)(x)    
out2 = RightSideLastLayer(banblabala)(x)


#here, you define which path you will follow in the graph you've drawn with layers
#notice the two outputs passed in a list, telling the model I want it to have two outputs.
model = Model(inp, [out1,out2])
model.compile(optimizer = ...., loss = ....) #loss can be one for both sides or a list with different loss functions for out1 and out2    

model.fit(inputData,[outputYLeft, outputYRight], epochs=..., batch_size=...)

More Related Contents:

  1. Keras, How to get the output of each layer?
  2. How to make a custom activation function with only Python in Tensorflow?
  3. How to apply gradient clipping in TensorFlow?
  4. Keras + Tensorflow and Multiprocessing in Python
  5. How to assign a value to a TensorFlow variable?
  6. Keras Sequential model input layer
  7. Keras replacing input layer
  8. Keras custom loss function: Accessing current input pattern
  9. Negative dimension size caused by subtracting 3 from 1 for ‘conv2d_2/convolution’
  10. How can I use a pre-trained neural network with grayscale images?
  11. Dimension of shape in conv1D
  12. Removing then Inserting a New Middle Layer in a Keras Model
  13. Loading a trained Keras model and continue training
  14. How do I check if keras is using gpu version of tensorflow?
  15. Custom loss function in Keras
  16. What is the role of TimeDistributed layer in Keras?
  17. How do I get the weights of a layer in Keras?
  18. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  19. Keras LSTM input dimension setting
  20. How to implement Grad-CAM on a trained network
  21. keras: how to save the training history attribute of the history object
  22. What is right batch normalization function in Tensorflow?
  23. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  24. How do I plot a Keras/Tensorflow subclassing API model?
  25. Strange behaviour of the loss function in keras model, with pretrained convolutional base
  26. Multi-input Multi-output Model with Keras Functional API
  27. how to implement custom metric in keras?
  28. expected ndim=3, found ndim=2
  29. Unbalanced data and weighted cross entropy
  30. Unexpected keyword argument ‘ragged’ in Keras

Leave a Comment