def __init__(self, in_dim, hidden_dim, n_classes,hidden_layers,n_steps,readout,
activation_func,dropout,grid,device):
super(Classifier, self).__init__()
self.device = device
self.readout = readout
self.layers = nn.ModuleList()
self.batch_norms = nn.ModuleList()
self.grid = grid
# input layer
self.layers.append(conv.GatedGraphConv(in_dim,hidden_dim,n_steps,1))
self.batch_norms.append(nn.BatchNorm1d(hidden_dim))
# hidden layers
for k in range(0,hidden_layers):
self.layers.append(conv.GatedGraphConv(hidden_dim,hidden_dim,n_steps,1))
self.batch_norms.append(nn.BatchNorm1d(hidden_dim))
# dropout layer
self.dropout=nn.Dropout(p=dropout)
# last layer
if self.readout == 'max':
self.readout_fcn = conv.MaxPooling()
elif self.readout == 'mean':
self.readout_fcn = conv.AvgPooling()
elif self.readout == 'sum':
self.readout_fcn = conv.SumPooling()
elif self.readout == 'gap':
self.readout_fcn = conv.GlobalAttentionPooling(nn.Linear(hidden_dim,1),nn.Linear(hidden_dim,hidden_dim*2))
elif self.readout == 'sort':
self.readout_fcn = conv.SortPooling(100)
elif self.readout == 'set':
self.readout_fcn = conv.Set2Set(hidden_dim,2,2)
else:
self.readout_fcn = SppPooling(hidden_dim,self.grid)
if self.readout == 'spp':
self.classify = nn.Sequential(
nn.Dropout(),
nn.Linear(hidden_dim * self.grid * self.grid, hidden_dim),
nn.ReLU(inplace=True),
nn.Linear(hidden_dim, n_classes),
)
elif self.readout == 'sort':
self.classify = nn.Sequential(
nn.Dropout(),
nn.Linear(hidden_dim*100, n_classes),
)
else:
var=hidden_dim
if self.readout == 'gap' or self.readout == 'set':
var*=2
self.classify = nn.Linear(var, n_classes)
def test_set2set():
g = dgl.DGLGraph(nx.path_graph(10))
s2s = nn.Set2Set(5, 3, 3) # hidden size 5, 3 iters, 3 layers
print(s2s)
# test#1: basic
h0 = th.rand(g.number_of_nodes(), 5)
h1 = s2s(h0, g)
assert h1.shape[0] == 10 and h1.dim() == 1
# test#2: batched graph
g1 = dgl.DGLGraph(nx.path_graph(11))
g2 = dgl.DGLGraph(nx.path_graph(5))
bg = dgl.batch([g, g1, g2])
h0 = th.rand(bg.number_of_nodes(), 5)
h1 = s2s(h0, bg)
assert h1.shape[0] == 3 and h1.shape[1] == 10 and h1.dim() == 2
def test_set2set():
ctx = F.ctx()
g = dgl.DGLGraph(nx.path_graph(10))
s2s = nn.Set2Set(5, 3, 3) # hidden size 5, 3 iters, 3 layers
s2s = s2s.to(ctx)
print(s2s)
# test#1: basic
h0 = F.randn((g.number_of_nodes(), 5))
h1 = s2s(g, h0)
assert h1.shape[0] == 1 and h1.shape[1] == 10 and h1.dim() == 2
# test#2: batched graph
g1 = dgl.DGLGraph(nx.path_graph(11))
g2 = dgl.DGLGraph(nx.path_graph(5))
bg = dgl.batch([g, g1, g2])
h0 = F.randn((bg.number_of_nodes(), 5))
h1 = s2s(bg, h0)
assert h1.shape[0] == 3 and h1.shape[1] == 10 and h1.dim() == 2
def __init__(self, in_dim, hidden_dim, embed_dim, hidden_layers, hops,
readout, activation_func, dropout, local, norm, grid, K,
device):
super(Classifier, self).__init__()
self.device = device
self.readout = readout
self.layers = nn.ModuleList()
self.batch_norms = nn.ModuleList()
self.grid = grid
self.K = K
self.hidden_dim = hidden_dim
self.local = local
self.norm = norm
self.layers.append(
conv.TAGConv(in_dim, hidden_dim, hops, activation=activation_func))
# hidden layers
for k in range(0, hidden_layers):
self.layers.append(
conv.TAGConv(hidden_dim,
hidden_dim,
hops,
activation=activation_func))
# dropout layer
self.dropout = nn.Dropout(p=dropout)
if self.local:
return
# readout layer
if self.readout == 'max':
self.readout_fcn = conv.MaxPooling()
elif self.readout == 'mean':
self.readout_fcn = conv.AvgPooling()
elif self.readout == 'sum':
self.readout_fcn = conv.SumPooling()
elif self.readout == 'gap':
self.readout_fcn = conv.GlobalAttentionPooling(
nn.Linear(hidden_dim, 1), nn.Linear(hidden_dim,
hidden_dim * 2))
elif self.readout == 'sort':
self.readout_fcn = conv.SortPooling(self.K)
elif self.readout == 'set':
self.readout_fcn = conv.Set2Set(hidden_dim, 2, 1)
elif self.readout == 'cov':
self.readout_fcn = CovPooling(hidden_dim)
else:
self.readout_fcn = SppPooling(hidden_dim, self.grid)
if self.readout == 'spp':
self.embed = nn.Sequential(
nn.Dropout(),
nn.Linear(hidden_dim * self.grid * self.grid, hidden_dim * 2),
nn.ReLU(inplace=True), nn.Dropout(),
nn.Linear(2 * hidden_dim, 2 * hidden_dim),
nn.ReLU(inplace=True), nn.Linear(2 * hidden_dim, embed_dim))
elif self.readout == 'sort':
self.embed = nn.Sequential(
#nn.Dropout(),
nn.Linear(hidden_dim * self.K, embed_dim))
elif self.readout == 'cov':
self.embed = nn.Sequential(
nn.Dropout(),
nn.Linear(int(((hidden_dim + 1) * hidden_dim) / 2), embed_dim))
else:
var = hidden_dim
if self.readout == 'gap' or self.readout == 'set':
var *= 2
self.embed = nn.Linear(var, embed_dim)
def __init__(self, in_dim, hidden_dim, n_classes,hidden_layers,in_stats,out_stats,gfc_layers,readout,
activation_func,dropout,grid,K,device):
super(Classifier, self).__init__()
self.device = device
self.readout = readout
self.layers = nn.ModuleList()
self.batch_norms = nn.ModuleList()
self.grid = grid
self.K = K
self.hidden_dim = hidden_dim
self.layers.append(GcapsConv(in_dim,hidden_dim,gfc_layers,1,out_stats,activation=activation_func))
self.batch_norms.append(nn.BatchNorm1d(hidden_dim))
# hidden layers
for k in range(0,hidden_layers):
self.layers.append(GcapsConv(hidden_dim,hidden_dim,gfc_layers,in_stats,out_stats,activation=activation_func))
self.batch_norms.append(nn.BatchNorm1d(hidden_dim))
# dropout layer
self.dropout=nn.Dropout(p=dropout)
# last layer
if self.readout == 'max':
self.readout_fcn = conv.MaxPooling()
elif self.readout == 'mean':
self.readout_fcn = conv.AvgPooling()
elif self.readout == 'sum':
self.readout_fcn = conv.SumPooling()
elif self.readout == 'gap':
self.readout_fcn = conv.GlobalAttentionPooling(nn.Linear(hidden_dim,1),nn.Linear(hidden_dim,hidden_dim*2))
elif self.readout == 'sort':
self.readout_fcn = conv.SortPooling(self.K)
elif self.readout == 'set':
self.readout_fcn = conv.Set2Set(hidden_dim,2,1)
elif self.readout == 'cov':
self.readout_fcn = CovPooling(hidden_dim)
else:
self.readout_fcn = SppPooling(hidden_dim,self.grid)
if self.readout == 'spp':
self.classify = nn.Sequential(
nn.Dropout(),
nn.Linear(hidden_dim * self.grid * self.grid, n_classes)
# nn.Conv2d(hidden_dim,64,kernel_size=3,padding=1),
# nn.ReLU(inplace=True),
# nn.Dropout(),
# nn.Linear(2*hidden_dim, 2*hidden_dim),
# nn.ReLU(inplace=True),
# nn.Linear(2*hidden_dim, n_classes),
# nn.Conv2d(hidden_dim,64,kernel_size=3,padding=1),
# nn.ReLU(inplace=True),
# nn.Conv2d(384,256,kernel_size=3,padding=1),
#nn.ReLU(inplace=True),
#nn.Flatten(1),
#nn.Dropout(p=dropout),
#nn.Linear(64*self.grid*self.grid, n_classes)
)
elif self.readout == 'sort':
self.classify = nn.Sequential(
#nn.Dropout(),
nn.Linear(hidden_dim*self.K, n_classes)
)
elif self.readout == 'cov':
self.classify = nn.Sequential(
nn.Dropout(),
nn.Linear( int(((hidden_dim+1)*hidden_dim)/2), n_classes)
)
else:
var=hidden_dim
if self.readout == 'gap' or self.readout == 'set':
var*=2
self.classify = nn.Linear(var*out_stats, n_classes)
def __init__(self, in_dim, hidden_dim, n_classes, hidden_layers, ctype,
hops, readout, activation_func, dropout, grid, K, norm,
device):
super(Classifier, self).__init__()
self.device = device
self.readout = readout
self.layers = nn.ModuleList()
self.n_layers = nn.ModuleList()
self.grid = grid
self.K = K
self.hidden_dim = hidden_dim
self.norm = norm
self.mish = Mish()
# input layer
if ctype == 'tagconv':
self.layers.append(
conv.TAGConv(in_dim,
hidden_dim,
hops,
activation=activation_func))
else:
self.layers.append(
conv.SGConv(in_dim,
hidden_dim,
hops,
cached=False,
norm=activation_func))
if self.norm == 'batch':
self.n_layers.append(nn.BatchNorm1d(hidden_dim))
elif self.norm == 'layer':
self.n_layers.append(
nn.LayerNorm(hidden_dim, elementwise_affine=False))
elif self.norm == 'group':
self.n_layers.append(nn.GroupNorm(16, hidden_dim))
elif self.norm == 'instance':
self.n_layers.append(nn.InstanceNorm1d(hidden_dim))
else:
self.n_layers.append(GraphNorm(hidden_dim, affine=False))
# hidden layers
for k in range(0, hidden_layers):
if ctype == 'tagconv':
self.layers.append(
conv.TAGConv(hidden_dim,
hidden_dim,
hops,
activation=activation_func))
else:
self.layers.append(
conv.SGConv(hidden_dim,
hidden_dim,
hops,
cached=False,
norm=activation_func))
if self.norm == 'batch':
self.n_layers.append(nn.BatchNorm1d(hidden_dim))
elif self.norm == 'layer':
self.n_layers.append(
nn.LayerNorm(hidden_dim, elementwise_affine=False))
elif self.norm == 'group':
self.n_layers.append(nn.GroupNorm(16, hidden_dim))
elif self.norm == 'instance':
self.n_layers.append(nn.InstanceNorm1d(hidden_dim))
else:
self.n_layers.append(GraphNorm(hidden_dim, affine=False))
# dropout layer
self.dropout = nn.Dropout(p=dropout)
# last layer
if self.readout == 'max':
self.readout_fcn = conv.MaxPooling()
elif self.readout == 'mean':
self.readout_fcn = conv.AvgPooling()
elif self.readout == 'sum':
self.readout_fcn = conv.SumPooling()
elif self.readout == 'gap':
self.readout_fcn = conv.GlobalAttentionPooling(
nn.Linear(hidden_dim, 1), nn.Linear(hidden_dim,
hidden_dim * 2))
elif self.readout == 'sort':
self.readout_fcn = conv.SortPooling(self.K)
elif self.readout == 'set':
self.readout_fcn = conv.Set2Set(hidden_dim, 2, 1)
elif self.readout == 'cov':
self.readout_fcn = CovPooling(hidden_dim)
else:
self.readout_fcn = SppPooling(hidden_dim, self.grid)
if self.readout == 'spp':
self.classify = nn.Sequential(
nn.Dropout(),
nn.Linear(hidden_dim * self.grid * self.grid, hidden_dim * 2),
nn.ReLU(inplace=True), nn.Dropout(),
nn.Linear(2 * hidden_dim, 2 * hidden_dim),
nn.ReLU(inplace=True), nn.Linear(2 * hidden_dim, n_classes))
elif self.readout == 'sort':
self.classify = nn.Sequential(
#nn.Dropout(),
nn.Linear(hidden_dim * self.K, n_classes))
elif self.readout == 'cov':
self.classify = nn.Sequential(
nn.Dropout(),
nn.Linear(int(((hidden_dim + 1) * hidden_dim) / 2), n_classes))
else:
var = hidden_dim
if self.readout == 'gap' or self.readout == 'set':
var *= 2
self.classify = nn.Linear(var, n_classes)
