Skip to main content
Join the official 2019 Python Developers SurveyStart the survey!

Keras deep learning model implementations

Project description

# DeepModels
Implementations of various deep learning models using Keras.

## Requirements
An existing installation of either Tensorflow or Theano.

## Installation
```
pip install deep-models
```

## Usage

The models are implemented using Keras and instantiation returns a Keras Model object unless otherwise noted.

### Wide Residual Network
```python3
from deep_models import wide_residual_network as wrn

# Load your data
trainX = ...
trainY = ...
img_shape = (32, 32, 3)

# Create the model
# k is the width, 6 * n + 4 is the depth
model = wrn.build_model(img_shape, classes=10, n=4, k=10, dropout=0.3)

# Train the model
model.compile(loss="categorical_crossentropy", optimizer="adam", metrics=["acc"])
model.fit(
trainX, trainY,
batch_size=128,
epochs=100,
validation_split=0.2)
```

## Examples
Some working examples are available in the notebooks directory.

## License
See LICENSE file

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Files for Deep-Models, version 0.1.5
Filename, size File type Python version Upload date Hashes
Filename, size Deep_Models-0.1.5-py3.6.egg (4.9 kB) File type Egg Python version 3.6 Upload date Hashes View hashes
Filename, size Deep-Models-0.1.5.tar.gz (2.6 kB) File type Source Python version None Upload date Hashes View hashes

Supported by

Elastic Elastic Search Pingdom Pingdom Monitoring Google Google BigQuery Sentry Sentry Error logging AWS AWS Cloud computing DataDog DataDog Monitoring Fastly Fastly CDN SignalFx SignalFx Supporter DigiCert DigiCert EV certificate StatusPage StatusPage Status page