jgraving / keras-squeezenet

SqueezeNet implementation with Keras Framework

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.

pip 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.

Library Versions

• Keras v2.0+
• Tensorflow 1.0+

Example Usage

import numpy as np
from keras_squeezenet import SqueezeNet
from keras.applications.imagenet_utils import preprocess_input, decode_predictions
from 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.