Keras models as ASCII diagrams
Project description
Print ASCII diagrams of your Keras models to visualize the layers and their shapes.
InputLayer (None, 50, 300) Reshape (None, 1, 50, 300) Convolution2D (None, 250, 48, 1) Relu (None, 250, 48, 1) MaxPooling2D (None, 250, 1, 1) Flatten (None, 250) Dropout (None, 250) Dense (None, 7) Softmax (None, 7)
A more complex model from babi_rnn.py:
InputLayer (None, 5) Embedding (None, 5, 50) InputLayer (None, 552) Dropout (None, 5, 50) Embedding (None, 552, 50) LSTM (None, 50) Dropout (None, 552, 50) RepeatVector (None, 552, 50) \______________________________/ | Merge (None, 552, 50) LSTM (None, 50) Dropout (None, 50) Dense (None, 36)
To install
pip install keras_diagram
Note for Conda installation (Python 3.5): pip install pypandoc
To use
from keras_diagram import ascii model = Sequential() model.add(...) print(ascii(model))
Developing
./test.py # run tests via docker ./publish.py # build distributions and publish to pypi ./shell.py # run bash above docker container with current folder mounted
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
keras_diagram-1.0.4.tar.gz
(4.5 kB
view hashes)
Built Distribution
Close
Hashes for keras_diagram-1.0.4-py2-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | 58603d459e8bcb08553fd57fdfa87f4d4c4b6621aee31430979870922fc26f85 |
|
MD5 | 513116bfe92054056d4913eeb027d3ea |
|
BLAKE2b-256 | 4eb81e00d19eb1cba2564cb2efcd36f01cab8d86b2ee351e61a5045a11161233 |