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
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
Keras Framework
SqueezeNet Official Github Repo
SqueezeNet Paper
Licence
MIT License
Note: If you find this project useful, please include reference link in your work.