Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

[WIP] Image captioning #15

Open
wants to merge 4 commits into
base: master
Choose a base branch
from
Open
Changes from 1 commit
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
Prev Previous commit
Next Next commit
add the googlenet model
ebenolson committed Aug 31, 2015
commit 220da9eaf90c4acd8234b7269e3a56473f82bd31
91 changes: 91 additions & 0 deletions examples/imagecaption/googlenet.py
Original file line number Diff line number Diff line change
@@ -0,0 +1,91 @@
from lasagne.layers import InputLayer
from lasagne.layers import DenseLayer
from lasagne.layers import ConcatLayer
from lasagne.layers import NonlinearityLayer
from lasagne.layers import GlobalPoolLayer
from lasagne.layers.dnn import Conv2DDNNLayer as ConvLayer
from lasagne.layers.dnn import MaxPool2DDNNLayer as PoolLayerDNN
from lasagne.layers import MaxPool2DLayer as PoolLayer
from lasagne.layers import LocalResponseNormalization2DLayer as LRNLayer
from lasagne.nonlinearities import softmax, linear


def build_inception_module(name, input_layer, nfilters):
# nfilters: (pool_proj, 1x1, 3x3_reduce, 3x3, 5x5_reduce, 5x5)
net = {}
net['pool'] = PoolLayerDNN(input_layer, pool_size=3, stride=1, pad=1)
net['pool_proj'] = ConvLayer(net['pool'], nfilters[0], 1)

net['1x1'] = ConvLayer(input_layer, nfilters[1], 1)

net['3x3_reduce'] = ConvLayer(input_layer, nfilters[2], 1)
net['3x3'] = ConvLayer(net['3x3_reduce'], nfilters[3], 3, pad=1)

net['5x5_reduce'] = ConvLayer(input_layer, nfilters[4], 1)
net['5x5'] = ConvLayer(net['5x5_reduce'], nfilters[5], 5, pad=2)

net['output'] = ConcatLayer([
net['1x1'],
net['3x3'],
net['5x5'],
net['pool_proj'],
])

return {'{}/{}'.format(name, k): v for k, v in net.items()}


def build_model():
net = {}
net['input'] = InputLayer((None, 3, None, None))
net['conv1/7x7_s2'] = ConvLayer(net['input'], 64, 7, stride=2, pad=3)
net['pool1/3x3_s2'] = PoolLayer(net['conv1/7x7_s2'],
pool_size=3,
stride=2,
ignore_border=False)
net['pool1/norm1'] = LRNLayer(net['pool1/3x3_s2'], alpha=0.00002, k=1)
net['conv2/3x3_reduce'] = ConvLayer(net['pool1/norm1'], 64, 1)
net['conv2/3x3'] = ConvLayer(net['conv2/3x3_reduce'], 192, 3, pad=1)
net['conv2/norm2'] = LRNLayer(net['conv2/3x3'], alpha=0.00002, k=1)
net['pool2/3x3_s2'] = PoolLayer(net['conv2/norm2'], pool_size=3, stride=2)

net.update(build_inception_module('inception_3a',
net['pool2/3x3_s2'],
[32, 64, 96, 128, 16, 32]))
net.update(build_inception_module('inception_3b',
net['inception_3a/output'],
[64, 128, 128, 192, 32, 96]))
net['pool3/3x3_s2'] = PoolLayer(net['inception_3b/output'],
pool_size=3, stride=2)

net.update(build_inception_module('inception_4a',
net['pool3/3x3_s2'],
[64, 192, 96, 208, 16, 48]))
net.update(build_inception_module('inception_4b',
net['inception_4a/output'],
[64, 160, 112, 224, 24, 64]))
net.update(build_inception_module('inception_4c',
net['inception_4b/output'],
[64, 128, 128, 256, 24, 64]))
net.update(build_inception_module('inception_4d',
net['inception_4c/output'],
[64, 112, 144, 288, 32, 64]))
net.update(build_inception_module('inception_4e',
net['inception_4d/output'],
[128, 256, 160, 320, 32, 128]))
net['pool4/3x3_s2'] = PoolLayer(net['inception_4e/output'],
pool_size=3, stride=2)

net.update(build_inception_module('inception_5a',
net['pool4/3x3_s2'],
[128, 256, 160, 320, 32, 128]))
net.update(build_inception_module('inception_5b',
net['inception_5a/output'],
[128, 384, 192, 384, 48, 128]))

net['pool5/7x7_s1'] = GlobalPoolLayer(net['inception_5b/output'])
net['loss3/classifier'] = DenseLayer(net['pool5/7x7_s1'],
num_units=1000,
nonlinearity=linear)
net['prob'] = NonlinearityLayer(net['loss3/classifier'],
nonlinearity=softmax)
return net