def __init__(self, nfm, first=False, strides=1, batch_norm=False):
self.trunk = None
self.side_path = None
main_path = [
Convolution(
**conv_params(1, nfm, strides=strides, batch_norm=batch_norm)),
Convolution(**conv_params(3, nfm, batch_norm=batch_norm)),
Convolution(**conv_params(1, nfm *
4, relu=False, batch_norm=False))
]
if first or strides == 2:
self.side_path = Convolution(**conv_params(
1, nfm * 4, strides=strides, relu=False, batch_norm=False))
else:
if batch_norm:
main_path = [BatchNorm(), Activation(Rectlin())] + main_path
else:
main_path = [Activation(Rectlin())] + main_path
if strides == 2:
if batch_norm:
self.trunk = Sequential([BatchNorm(), Activation(Rectlin())])
else:
self.trunk = Sequential([Activation(Rectlin())])
self.main_path = Sequential(main_path)
def __init__(self,
inputs,
dataset,
stage_depth,
batch_norm=False,
activation=False,
preprocess=False):
nfms = [
2**(stage + 4) for stage in sorted(list(range(3)) * stage_depth)
]
strides = [
1 if cur == prev else 2 for cur, prev in zip(nfms[1:], nfms[:-1])
]
layers = []
if preprocess and dataset == 'cifar10':
layers = Preprocess(functor=cifar_mean_subtract)
layers.append(Convolution(**conv_params(3, 16, batch_norm=batch_norm)))
layers.append(f_module(nfms[0], first=True, batch_norm=batch_norm))
for nfm, stride in zip(nfms[1:], strides):
layers.append(f_module(nfm, strides=stride, batch_norm=batch_norm))
if batch_norm:
layers.append(BatchNorm())
if activation:
layers.append(Activation(Rectlin()))
layers.append(Pool2D(8, strides=2, op='avg'))
if dataset == 'cifar10':
ax.Y.length = 10
layers.append(
Affine(axes=ax.Y,
weight_init=KaimingInit(),
batch_norm=batch_norm,
activation=Softmax()))
elif dataset == 'i1k':
ax.Y.length = 1000
layers.append(
Affine(axes=ax.Y,
weight_init=KaimingInit(),
batch_norm=batch_norm,
activation=Softmax()))
else:
raise ValueError("Incorrect dataset provided")
super(mini_residual_network, self).__init__(layers=layers)
