keract 1.1.1

Keras Activations

Extract the activation maps of your Keras models

Short code and useful examples to show how to get the activations for each layer for Keras.

A random seven from MNIST

Activation map of CONV1 of LeNet

Activation map of FC1 of LeNet

Activation map of Softmax of LeNet. Yes it's a seven!

---

The function for visualizing the activations is in the script read_activations.py

Inputs:

• model: Keras model
• model_inputs: Model inputs for which we want to get the activations (for example 200 MNIST images)
• print_shape_only: If set to True, will print the entire activations arrays (might be very verbose!)
• layer_name: Will retrieve the activations of a specific layer, if the name matches one of the existing layers of the model.

Outputs:

• returns a list of each layer (by order of definition) and its corresponding activations.

I provide a simple example to see how it works with the MNIST model. I separated the training and the visualizations because if the two are done sequentially, we have to re-train the model every time we want to visualize the activations! Not very practical! Here are the main steps:

Running python model_train.py will do:

• define the model
• if no checkpoints are detected:
  • train the model
  • save the best model in checkpoints/
• load the model from the best checkpoint
• read the activations

Shapes of the activations (one sample):

----- activations -----
(1, 26, 26, 32)
(1, 24, 24, 64)
(1, 12, 12, 64)
(1, 12, 12, 64)
(1, 9216)
(1, 128)
(1, 128)
(1, 10) # softmax output!

Shapes of the activations (200 samples):

----- activations -----
(200, 26, 26, 32)
(200, 24, 24, 64)
(200, 12, 12, 64)
(200, 12, 12, 64)
(200, 9216)
(200, 128)
(200, 128)
(200, 10)

multi_inputs.py contains very simple examples to visualize activations with multi inputs models.