https://github.com/RedaOps/ann-visualizer
A python library for visualizing Artificial Neural Networks (ANN)
https://github.com/RedaOps/ann-visualizer
ann ann-visualizer neural-network python-library
Last synced: 6 months ago
JSON representation
A python library for visualizing Artificial Neural Networks (ANN)
- Host: GitHub
- URL: https://github.com/RedaOps/ann-visualizer
- Owner: RedaOps
- License: mit
- Archived: true
- Created: 2018-03-27T18:05:44.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2020-10-16T16:57:02.000Z (over 4 years ago)
- Last Synced: 2024-11-14T15:33:35.694Z (6 months ago)
- Topics: ann, ann-visualizer, neural-network, python-library
- Language: Python
- Size: 60.5 KB
- Stars: 1,241
- Watchers: 43
- Forks: 216
- Open Issues: 21
-
Metadata Files:
- Readme: README.md
- License: LICENSE.txt
Awesome Lists containing this project
README
# ANN Visualizer
[](https://badge.fury.io/py/ann_visualizer) [](https://travis-ci.org/Prodicode/ann-visualizer) [](https://liberapay.com/Prodicode/donate)
A great visualization python library used to work with Keras. It uses python's graphviz library to create a presentable graph of the neural network you are building.
## Version 2.0 is Out!
Version 2.0 of the ann_visualizer is now released! The community demanded a CNN visualizer, so we updated our module. You can check out an example of a CNN visualization below!
Happy visualizing!
## Installation
### From Github
1. Download the `ann_visualizer` folder from the github repository.
2. Place the `ann_visualizer` folder in the same directory as your main python script.
### From pip
Use the following command:
```bash
pip3 install ann_visualizer
```
Make sure you have graphviz installed. Install it using:
```bash
sudo apt-get install graphviz && pip3 install graphviz
```
## Usage
```python
from ann_visualizer.visualize import ann_viz;
#Build your model here
ann_viz(model)
```
## Documentation
### ann_viz(model, view=True, filename="network.gv", title="MyNeural Network")
* `model` - The Keras Sequential model
* `view` - If True, it opens the graph preview after executed
* `filename` - Where to save the graph. (.gv file format)
* `title` - A title for the graph
## Example ANN
```python
import keras;
from keras.models import Sequential;
from keras.layers import Dense;
network = Sequential();
#Hidden Layer#1
network.add(Dense(units=6,
activation='relu',
kernel_initializer='uniform',
input_dim=11));
#Hidden Layer#2
network.add(Dense(units=6,
activation='relu',
kernel_initializer='uniform'));
#Exit Layer
network.add(Dense(units=1,
activation='sigmoid',
kernel_initializer='uniform'));
from ann_visualizer.visualize import ann_viz;
ann_viz(network, title="");
```
This will output:
## Example CNN
```python
import keras;
from keras.models import Sequential;
from keras.layers import Dense;
from ann_visualizer.visualize import ann_viz
model = build_cnn_model()
ann_viz(model, title="")
def build_cnn_model():
model = keras.models.Sequential()
model.add(
Conv2D(
32, (3, 3),
padding="same",
input_shape=(32, 32, 3),
activation="relu"))
model.add(Dropout(0.2))
model.add(
Conv2D(
32, (3, 3),
padding="same",
input_shape=(32, 32, 3),
activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(
Conv2D(
64, (3, 3),
padding="same",
input_shape=(32, 32, 3),
activation="relu"))
model.add(Dropout(0.2))
model.add(
Conv2D(
64, (3, 3),
padding="same",
input_shape=(32, 32, 3),
activation="relu"))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(512, activation="relu"))
model.add(Dropout(0.2))
model.add(Dense(10, activation="softmax"))
return model
```
This will output:
## Contributions
This library is still unstable. Please report all bug to the issues section. It is currently tested with `python3.5` and `python3.6`, but it should run just fine on any python3.