def reset_parameters(self):
reset(self.k_lin)
reset(self.q_lin)
reset(self.v_lin)
reset(self.a_lin)
ones(self.skip)
ones(self.p_rel)
glorot(self.a_rel)
glorot(self.m_rel)
def reset_parameters(self):
tgi.glorot(self.weight)
tgi.zeros(self.bias)
for name, param in self.named_parameters():
if name.startswith("att_scaling"):
tgi.ones(param)
elif name.startswith("att_bias"):
tgi.zeros(param)
elif name.startswith("att_mh"):
tgi.glorot(param)
def reset_parameters(self):
ones(self.beta)
zeros(self.alpha)
for layer in self.MLP_co:
layer[0].reset_parameters()
for layer in self.MLP:
layer[0].reset_parameters()
for layer in self.MLP1:
layer[0].reset_parameters()
for layer in self.MLP2:
layer[0].reset_parameters()
def reset_parameters(self):
if self.num_bases is not None:
glorot(self.basis)
glorot(self.att)
else:
glorot(self.weight)
glorot(self.q)
glorot(self.k)
zeros(self.bias)
ones(self.l1)
zeros(self.b1)
torch.full(self.l2.size(), 1 / self.out_channels)
zeros(self.b2)
if self.lin_edge is not None:
glorot(self.lin_edge)
glorot(self.e)
def test_inits():
x = torch.empty(1, 4)
uniform(size=4, tensor=x)
assert x.min() >= -0.5
assert x.max() <= 0.5
glorot(x)
assert x.min() >= -1.25
assert x.max() <= 1.25
zeros(x)
assert x.tolist() == [[0, 0, 0, 0]]
ones(x)
assert x.tolist() == [[1, 1, 1, 1]]
def reset_parameters(self):
glorot(self.att)
ones(self.l1)
zeros(self.b1)
const(self.l2, 1 / self.nhid)
zeros(self.b2)
def reset_parameters(self):
for name, param in self.named_parameters():
if name.startswith("r_scaling"):
tgi.ones(param)
elif name.startswith("r_bias"):
tgi.zeros(param)
def reset_parameters(self):
#size = self.in_channels
#uniform(size, self.weight)
ones(self.weight)
def reset_parameters(self):
# normal(self.weight, 0, 0.1)
glorot(self.weight)
# ones(self.weight)
if self.bias is not None:
ones(self.bias)
def reset_parameters(self):
ones(self.weight)
self.cached_result = None
self.cached_num_edges = None
def reset_parameters(self):
ones(self.weight)
zeros(self.bias)
