Keras Activations
Project description
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 modelmodel_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.
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
Hashes for keract-1.1.1-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | fff7005356e1b345492936ae90223131ed7a01ebc64a874b6aac065bfe84ae64 |
|
MD5 | 5adc63191b99060967479c595ef54651 |
|
BLAKE2b-256 | 96a2db19dfdf3db82f92dda6870819a417622da2ffcf713c40ba768d01895ab2 |