def projection_skip(nfm, stride=1):
mainpath = [Conv(**conv_params(3, nfm, stride=stride)),
Conv(**conv_params(3, nfm, relu=False))]
sidepath = [SkipNode() if stride == 1 else Conv(**conv_params(1, nfm, stride, relu=False))]
module = [MergeSum([mainpath, sidepath]),
Activation(Rectlin())]
return module
def module_s1(nfm, first=False):
'''
non-strided
'''
sidepath = Conv(
**conv_params(1, nfm * 4, 1, False, False)) if first else SkipNode()
mainpath = [] if first else [BatchNorm(), Activation(Rectlin())]
mainpath.append(Conv(**conv_params(1, nfm)))
mainpath.append(Conv(**conv_params(3, nfm)))
mainpath.append(
Conv(**conv_params(1, nfm * 4, relu=False, batch_norm=False)))
return MergeSum([sidepath, mainpath])
def module_s2(nfm):
'''
strided
'''
module = [BatchNorm(), Activation(Rectlin())]
mainpath = [
Conv(**conv_params(1, nfm, stride=2)),
Conv(**conv_params(3, nfm)),
Conv(**conv_params(1, nfm * 4, relu=False, batch_norm=False))
]
sidepath = [
Conv(**conv_params(1, nfm * 4, stride=2, relu=False, batch_norm=False))
]
module.append(MergeSum([sidepath, mainpath]))
return module
def module_factory(nfm, bottleneck=True, stride=1):
nfm_out = nfm * 4 if bottleneck else nfm
use_skip = True if stride == 1 else False
stride = abs(stride)
sidepath = [SkipNode() if use_skip else Conv(
**conv_params(1, nfm_out, stride, False))]
if bottleneck:
mainpath = [Conv(**conv_params(1, nfm, stride)),
Conv(**conv_params(3, nfm)),
Conv(**conv_params(1, nfm_out, relu=False))]
else:
mainpath = [Conv(**conv_params(3, nfm, stride)),
Conv(**conv_params(3, nfm, relu=False))]
return [MergeSum([mainpath, sidepath]),
Activation(Rectlin())]
# weight initialization
init_norm = Gaussian(loc=0.0, scale=0.01)
# initialize model
path1 = Model(layers=[
Affine(nout=100, init=init_norm, activation=Rectlin()),
Affine(nout=100, init=init_norm, activation=Rectlin())
])
path2 = Model(layers=[
Affine(nout=100, init=init_norm, activation=Rectlin()),
Affine(nout=100, init=init_norm, activation=Rectlin())
])
layers = [
MergeSum([path1.layers, path2.layers]),
Affine(nout=10, init=init_norm, activation=Logistic(shortcut=True))
]
model = Model(layers=layers)
cost = GeneralizedCost(costfunc=CrossEntropyBinary())
# fit and validate
optimizer = GradientDescentMomentum(learning_rate=0.1, momentum_coef=0.9)
# configure callbacks
callbacks = Callbacks(model,
train_set,
output_file=args.output_file,
valid_set=valid_set,
valid_freq=args.validation_freq,
