def test_local_response_norm_exceptions(self):
with self.assertRaises(ValueError):
layers.LocalResponseNorm(n=2)
with self.assertRaises(LayerConnectionError):
layers.Input(10) > layers.LocalResponseNorm()
conn = layers.LocalResponseNorm()
with self.assertRaises(LayerConnectionError):
conn.output(T.tensor4())
def test_local_response_normalization_layer(self):
input_layer = layers.Input((1, 1, 1))
conn = input_layer > layers.LocalResponseNorm()
x_tensor = asfloat(np.ones((1, 1, 1, 1)))
actual_output = self.eval(conn.output(x_tensor))
expected_output = np.array([0.59458]).reshape((-1, 1, 1, 1))
np.testing.assert_array_almost_equal(expected_output,
actual_output,
decimal=5)
def test_local_response_normalization_layer(self):
network = layers.join(
layers.Input((1, 1, 1)),
layers.LocalResponseNorm(),
)
x_tensor = asfloat(np.ones((1, 1, 1, 1)))
actual_output = self.eval(network.output(x_tensor, training=True))
expected_output = np.array([0.59458]).reshape((-1, 1, 1, 1))
np.testing.assert_array_almost_equal(expected_output,
actual_output,
decimal=5)
[
layers.Convolution((nfilters[4], 1, 1)),
layers.Relu(),
layers.Convolution((nfilters[5], 5, 5), padding='half'),
layers.Relu(),
]],
layers.Concatenate(),
)
googlenet = layers.join(
layers.Input((3, None, None)),
layers.Convolution((64, 7, 7), padding='half', stride=2),
layers.Relu(),
layers.MaxPooling((3, 3), stride=2),
layers.LocalResponseNorm(alpha=0.00002, k=1),
layers.Convolution((64, 1, 1)) > layers.Relu(),
layers.Convolution((192, 3, 3), padding='half') > layers.Relu(),
layers.LocalResponseNorm(alpha=0.00002, k=1),
layers.MaxPooling((3, 3), stride=2),
Inception((32, 64, 96, 128, 16, 32)),
Inception((64, 128, 128, 192, 32, 96)),
layers.MaxPooling((3, 3), stride=2),
Inception((64, 192, 96, 208, 16, 48)),
Inception((64, 160, 112, 224, 24, 64)),
Inception((64, 128, 128, 256, 24, 64)),
Inception((64, 112, 144, 288, 32, 64)),
Inception((128, 256, 160, 320, 32, 128)),
layers.MaxPooling((3, 3), stride=2),
Inception((128, 256, 160, 320, 32, 128)),
Inception((128, 384, 192, 384, 48, 128)),
def test_local_response_norm_exceptions(self):
with self.assertRaisesRegexp(ValueError, "Only works with odd"):
layers.LocalResponseNorm(depth_radius=2)
with self.assertRaises(LayerConnectionError):
layers.Input(10) > layers.LocalResponseNorm()
def __repr__(self):
return "{}({}, {})".format(
self.__class__.__name__,
self.from_channel,
self.to_channel)
alexnet = layers.join(
layers.Input((227, 227, 3)),
layers.Convolution((11, 11, 96), stride=(4, 4), name='conv_1'),
layers.Relu(),
layers.MaxPooling((3, 3), stride=(2, 2)),
layers.LocalResponseNorm(),
[[
SliceChannels(0, 48),
layers.Convolution((5, 5, 128), padding='SAME', name='conv_2_1'),
layers.Relu(),
], [
SliceChannels(48, 96),
layers.Convolution((5, 5, 128), padding='SAME', name='conv_2_2'),
layers.Relu(),
]],
layers.Concatenate(),
layers.MaxPooling((3, 3), stride=(2, 2)),
layers.LocalResponseNorm(),
def alexnet():
"""
AlexNet network architecture with random parameters. Parameters
can be loaded using ``neupy.storage`` module.
Originally AlexNet was built in order to solve image classification
problem. It was used in the ImageNet competition. The goal of the
competition is to build a model that classifies image into one of
the 1,000 categories. Categories include animals, objects, transports
and so on.
AlexNet has roughly 61 million parameters.
Examples
--------
>>> from neupy import architectures
>>> alexnet = architectures.alexnet()
>>> alexnet
(3, 227, 227) -> [... 37 layers ...] -> 1000
>>>
>>> from neupy import algorithms
>>> network = algorithms.Momentum(alexnet)
See Also
--------
:architecture:`vgg16` : VGG16 network
:architecture:`vgg19` : VGG19 network
:architecture:`squeezenet` : SqueezeNet network
:architecture:`resnet50` : ResNet50 network
References
----------
ImageNet Classification with Deep Convolutional Neural Networks
https://goo.gl/479oZZ
"""
return layers.join(
layers.Input((3, 227, 227)),
layers.Convolution((96, 11, 11), stride=(4, 4), name='conv_1'),
layers.Relu(),
layers.MaxPooling((3, 3), stride=(2, 2)),
layers.LocalResponseNorm(),
[[
SliceChannels(0, 48),
layers.Convolution((128, 5, 5), padding=2, name='conv_2_1'),
layers.Relu(),
],
[
SliceChannels(48, 96),
layers.Convolution((128, 5, 5), padding=2, name='conv_2_2'),
layers.Relu(),
]],
layers.Concatenate(),
layers.MaxPooling((3, 3), stride=(2, 2)),
layers.LocalResponseNorm(),
layers.Convolution((384, 3, 3), padding=1, name='conv_3'),
layers.Relu(),
[[
SliceChannels(0, 192),
layers.Convolution((192, 3, 3), padding=1, name='conv_4_1'),
layers.Relu(),
],
[
SliceChannels(192, 384),
layers.Convolution((192, 3, 3), padding=1, name='conv_4_2'),
layers.Relu(),
]],
layers.Concatenate(),
[[
SliceChannels(0, 192),
layers.Convolution((128, 3, 3), padding=1, name='conv_5_1'),
layers.Relu(),
],
[
SliceChannels(192, 384),
layers.Convolution((128, 3, 3), padding=1, name='conv_5_2'),
layers.Relu(),
]],
layers.Concatenate(),
layers.MaxPooling((3, 3), stride=(2, 2)),
layers.Reshape(),
layers.Relu(4096, name='dense_1') > layers.Dropout(0.5),
layers.Relu(4096, name='dense_2') > layers.Dropout(0.5),
layers.Softmax(1000, name='dense_3'),
)