gluon2keras

The deep learning models convertor


Keywords
densenet, gluon, gluon-to-keras, keras, mobilenet, mobilenetv2, model-converter, neural-network, neural-networks, neural-networks-tools, resnet
License
MIT
Install
pip install gluon2keras==0.0.2

Documentation

gluon2keras

Gluon to Keras deep neural network model converter

Build Status GitHub License Python Version

Installation

git clone https://github.com/nerox8664/gluon2keras
cd gluon2keras
pip install -e .

or you can use pip:

pip install gluon2keras

Usage

# Get a model from gluon cv
from gluoncv2.model_provider import get_model as glcv2_get_model
net = glcv2_get_model("xception")

# Make sure it's hybrid and initialized
net.hybridize()
net.collect_params().initialize()

# Test input
input_np = np.random.uniform(0, 1, (1, 3, 299, 299))
gluon_output = net(mx.nd.array(input_np))

# Keras model
k_model = gluon2keras(net, [(1, 3, 299, 299)], verbose=True, names='short')
error = check_error(gluon_output, k_model, input_np)

Code snippets

Look at the tests directory.

License

This software is covered by MIT License.