def __init__(self):
ksize = 3
bn = True
act = F.relu
self.dr = 0.3
super(P4CNN, self).__init__(
l1=ConvBNAct(conv=P4ConvZ2(in_channels=1,
out_channels=10,
ksize=ksize,
stride=1,
pad=0),
bn=bn,
act=act),
l2=ConvBNAct(conv=P4ConvP4(in_channels=10,
out_channels=10,
ksize=ksize,
stride=1,
pad=0),
bn=bn,
act=act),
l3=ConvBNAct(conv=P4ConvP4(in_channels=10,
out_channels=10,
ksize=ksize,
stride=1,
pad=0),
bn=bn,
act=act),
l4=ConvBNAct(conv=P4ConvP4(in_channels=10,
out_channels=10,
ksize=ksize,
stride=1,
pad=0),
bn=bn,
act=act),
l5=ConvBNAct(conv=P4ConvP4(in_channels=10,
out_channels=10,
ksize=ksize,
stride=1,
pad=0),
bn=bn,
act=act),
l6=ConvBNAct(conv=P4ConvP4(in_channels=10,
out_channels=10,
ksize=ksize,
stride=1,
pad=0),
bn=bn,
act=act),
top=P4ConvP4(in_channels=10,
out_channels=10,
ksize=4,
stride=1,
pad=0),
)
def test_p4_net_equivariance():
from groupy.gfunc import Z2FuncArray, P4FuncArray
import groupy.garray.C4_array as c4a
from groupy.gconv.chainer_gconv.p4_conv import P4ConvZ2, P4ConvP4
im = np.random.randn(1, 1, 11, 11).astype('float32')
check_equivariance(
im=im,
layers=[
P4ConvZ2(in_channels=1, out_channels=2, ksize=3),
P4ConvP4(in_channels=2, out_channels=3, ksize=3)
],
input_array=Z2FuncArray,
output_array=P4FuncArray,
point_group=c4a,
)
def test_g_z2_conv_equivariance():
from groupy.gfunc import Z2FuncArray, P4FuncArray, P4MFuncArray
import groupy.garray.C4_array as c4a
import groupy.garray.D4_array as d4a
from groupy.gconv.chainer_gconv.p4_conv import P4ConvZ2
from groupy.gconv.chainer_gconv.p4m_conv import P4MConvZ2
im = np.random.randn(1, 1, 11, 11).astype('float32')
check_equivariance(
im=im,
layers=[P4ConvZ2(1, 2, 3)],
input_array=Z2FuncArray,
output_array=P4FuncArray,
point_group=c4a,
)
check_equivariance(
im=im,
layers=[P4MConvZ2(1, 2, 3)],
input_array=Z2FuncArray,
output_array=P4MFuncArray,
point_group=d4a,
)
def __init__(self):
bn = True
ksize = 3
pad = 1
act = F.relu
super(P4AllCNNC, self).__init__(
l1=ConvBNAct(conv=P4ConvZ2(in_channels=3,
out_channels=48,
ksize=ksize,
stride=1,
pad=pad),
bn=bn,
act=act),
l2=ConvBNAct(conv=P4ConvP4(in_channels=48,
out_channels=48,
ksize=ksize,
stride=1,
pad=pad),
bn=bn,
act=act),
l3=ConvBNAct(conv=P4ConvP4(in_channels=48,
out_channels=48,
ksize=ksize,
stride=2,
pad=pad),
bn=bn,
act=act),
l4=ConvBNAct(conv=P4ConvP4(in_channels=48,
out_channels=96,
ksize=ksize,
stride=1,
pad=pad),
bn=bn,
act=act),
l5=ConvBNAct(conv=P4ConvP4(in_channels=96,
out_channels=96,
ksize=ksize,
stride=1,
pad=pad),
bn=bn,
act=act),
l6=ConvBNAct(conv=P4ConvP4(in_channels=96,
out_channels=96,
ksize=ksize,
stride=2,
pad=pad),
bn=bn,
act=act),
l7=ConvBNAct(conv=P4ConvP4(in_channels=96,
out_channels=96,
ksize=ksize,
stride=1,
pad=pad),
bn=bn,
act=act),
l8=ConvBNAct(conv=P4ConvP4(in_channels=96,
out_channels=96,
ksize=1,
stride=1,
pad=0),
bn=bn,
act=act),
# Note: it's unusual to have a bn + relu before softmax, but this is what's described by springenberg et al.
l9=ConvBNAct(conv=P4ConvP4(in_channels=96,
out_channels=10,
ksize=1,
stride=1,
pad=0),
bn=bn,
act=act),
)
wtscale = 0.035
self.l1.conv.W.data = (np.random.randn(*self.l1.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l2.conv.W.data = (np.random.randn(*self.l2.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l3.conv.W.data = (np.random.randn(*self.l3.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l4.conv.W.data = (np.random.randn(*self.l4.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l5.conv.W.data = (np.random.randn(*self.l5.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l6.conv.W.data = (np.random.randn(*self.l6.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l7.conv.W.data = (np.random.randn(*self.l7.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l8.conv.W.data = (np.random.randn(*self.l8.conv.W.data.shape) *
wtscale).astype(np.float32)
self.l9.conv.W.data = (np.random.randn(*self.l9.conv.W.data.shape) *
wtscale).astype(np.float32)