keras-squeezenet

SqueezeNet v1.1 Implementation using Keras Functional Framework 2.0

This network model has AlexNet accuracy with small footprint (5.1 MB) Pretrained models are converted from original Caffe network.

# Most Recent Onepip install git+https://github.com/rcmalli/keras-squeezenet.git# Release Versionpip install keras_squeezenet

News

• Project is now up-to-date with the new Keras version (2.0).

• Old Implementation is still available at 'keras1' branch but not updated.

Library Versions

• Keras v2.1.1

• Tensorflow v1.4

Example Usage

import numpy as npfrom keras_squeezenet import SqueezeNetfrom keras.applications.imagenet_utils import preprocess_input, decode_predictionsfrom keras.preprocessing import image

model = SqueezeNet()

img = image.load_img('../images/cat.jpeg', target_size=(227, 227))
x = image.img_to_array(img)
x = np.expand_dims(x, axis=0)
x = preprocess_input(x)

preds = model.predict(x)print('Predicted:', decode_predictions(preds))

References

1. Keras Framework

2. SqueezeNet Official Github Repo

3. SqueezeNet Paper

Licence

MIT License

Note: If you find this project useful, please include reference link in your work.