Keras Activations
Project description
Keras Activations
pip install keract
You have just found a (easy) way to get the activations for each layer of your Keras model (recurrent nets, conv nets, resnets...).
API
from keract import get_activations
get_activations(model, x)
Inputs
model
is akeras.models.Model
objectx
is a numpy array to feed to the model as input. In the case of multi-input,x
is of type List. We use the Keras convention (as used in predict, fit...).
Output
- A dictionary containing the activations for each layer of
model
for the inputx
:
{
'conv2d_1/Relu:0': np.array(...),
'conv2d_2/Relu:0': np.array(...),
...,
'dense_2/Softmax:0': np.array(...)
}
The key is the name of the layer and the value is the corresponding output of the layer for the given input x
.
Examples
Examples are provided for:
keras.models.Sequential
- mnist.pykeras.models.Model
- multi_inputs.py- Recurrent networks - recurrent.py
In the case of MNIST with LeNet, we are able to fetch the activations for a batch of size 128:
conv2d_1/Relu:0
(128, 26, 26, 32)
conv2d_2/Relu:0
(128, 24, 24, 64)
max_pooling2d_1/MaxPool:0
(128, 12, 12, 64)
dropout_1/cond/Merge:0
(128, 12, 12, 64)
flatten_1/Reshape:0
(128, 9216)
dense_1/Relu:0
(128, 128)
dropout_2/cond/Merge:0
(128, 128)
dense_2/Softmax:0
(128, 10)
We can even visualise some of them.
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!
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
keract-1.1.2.tar.gz
(3.0 kB
view hashes)
Built Distribution
Close
Hashes for keract-1.1.2-py2.py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | bad97d36b4e826d48d88ae68794d30cb6bf5e08628d782140dea476753b46b79 |
|
MD5 | ae2ef1d828534fccce4f46e81cd1b8a0 |
|
BLAKE2b-256 | 8570012ab03c6d380d7bfaf32a03c0cb3a86bb1eca0aaa4350dc8a1bfba2b63a |