neupy.architectures.squeezenet module

neupy.architectures.squeezenet.squeezenet()[source]

SqueezeNet network architecture with random parameters. Parameters can be loaded using neupy.storage module.

SqueezeNet has roughly 1.2 million parameters. It is almost 50 times less than in AlexNet. Parameters can be stored as 5Mb file.

See also

vgg16
VGG16 network
vgg19
VGG19 network
alexnet
AlexNet network
resnet50
ResNet50 network

References

SqueezeNet: AlexNet-level accuracy with 50x fewer parameters and <0.5MB model size https://arxiv.org/abs/1602.07360

Examples

>>> from neupy import architectures
>>> squeezenet = architectures.squeezenet()
>>> squeezenet
(3, 227, 227) -> [... 67 layers ...] -> 1000
>>>
>>> from neupy import algorithms
>>> network = algorithms.Momentum(squeezenet)