Keras, How to get the output of each layer?

by

You can easily get the outputs of any layer by using: model.layers[index].output

For all layers use this:

from keras import backend as K

inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers]          # all layer outputs
functors = [K.function([inp, K.learning_phase()], [out]) for out in outputs]    # evaluation functions

# Testing
test = np.random.random(input_shape)[np.newaxis,...]
layer_outs = [func([test, 1.]) for func in functors]
print layer_outs

Note: To simulate Dropout use learning_phase as 1. in layer_outs otherwise use 0.

Edit: (based on comments)

K.function creates theano/tensorflow tensor functions which is later used to get the output from the symbolic graph given the input.

Now K.learning_phase() is required as an input as many Keras layers like Dropout/Batchnomalization depend on it to change behavior during training and test time.

So if you remove the dropout layer in your code you can simply use:

from keras import backend as K

inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers]          # all layer outputs
functors = [K.function([inp], [out]) for out in outputs]    # evaluation functions

# Testing
test = np.random.random(input_shape)[np.newaxis,...]
layer_outs = [func([test]) for func in functors]
print layer_outs

Edit 2: More optimized

I just realized that the previous answer is not that optimized as for each function evaluation the data will be transferred CPU->GPU memory and also the tensor calculations needs to be done for the lower layers over-n-over.

Instead this is a much better way as you don’t need multiple functions but a single function giving you the list of all outputs:

from keras import backend as K

inp = model.input                                           # input placeholder
outputs = [layer.output for layer in model.layers]          # all layer outputs
functor = K.function([inp, K.learning_phase()], outputs )   # evaluation function

# Testing
test = np.random.random(input_shape)[np.newaxis,...]
layer_outs = functor([test, 1.])
print layer_outs

More Related Contents:

  1. How to apply gradient clipping in TensorFlow?
  2. Keras replacing input layer
  3. Keras custom loss function: Accessing current input pattern
  4. How can I use a pre-trained neural network with grayscale images?
  5. Dimension of shape in conv1D
  6. Removing then Inserting a New Middle Layer in a Keras Model
  7. Custom loss function in Keras
  8. How do I get the weights of a layer in Keras?
  9. Multiple outputs in Keras
  10. ValueError: Input 0 of layer sequential is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [8, 28, 28]
  11. Keras LSTM input dimension setting
  12. How to implement Grad-CAM on a trained network
  13. How to fix “ResourceExhaustedError: OOM when allocating tensor”
  14. How do I plot a Keras/Tensorflow subclassing API model?
  15. Strange behaviour of the loss function in keras model, with pretrained convolutional base
  16. Multi-input Multi-output Model with Keras Functional API
  17. Keras Dense layer’s input is not flattened
  18. Keras + Tensorflow and Multiprocessing in Python
  19. Proper way to feed time-series data to stateful LSTM?
  20. How to use a Keras RNN model to forecast for future dates or events?
  21. How does Keras 1d convolution layer work with word embeddings – text classification problem? (Filters, kernel size, and all hyperparameter)
  22. What do I need K.clear_session() and del model for (Keras with Tensorflow-gpu)?
  23. Passing output of a CNN to BILSTM
  24. How do I check if keras is using gpu version of tensorflow?
  25. How to set layer-wise learning rate in Tensorflow?
  26. Tensorflow : logits and labels must have the same first dimension
  27. How to create a keras layer with a custom gradient in TF2.0?
  28. How to fix “AttributeError: module ‘tensorflow’ has no attribute ‘get_default_graph'”?
  29. What is right batch normalization function in Tensorflow?
  30. TensorFlow 2.0 Keras: How to write image summaries for TensorBoard

Leave a Comment