def test_agnn_conv():
ctx = F.ctx()
g = dgl.graph(sp.sparse.random(100, 100, density=0.1))
agnn = nn.AGNNConv(1)
feat = F.randn((100, 5))
agnn = agnn.to(ctx)
h = agnn(g, feat)
assert h.shape == (100, 5)
g = dgl.bipartite(sp.sparse.random(100, 200, density=0.1))
agnn = nn.AGNNConv(1)
feat = (F.randn((100, 5)), F.randn((200, 5)))
agnn = agnn.to(ctx)
h = agnn(g, feat)
assert h.shape == (200, 5)
def test_agnn_conv():
ctx = F.ctx()
g = dgl.DGLGraph(sp.sparse.random(100, 100, density=0.1), readonly=True)
agnn = nn.AGNNConv(1)
feat = F.randn((100, 5))
agnn = agnn.to(ctx)
h = agnn(g, feat)
assert h.shape[-1] == 5
def test_agnn_conv(g, idtype):
g = g.astype(idtype).to(F.ctx())
ctx = F.ctx()
agnn = nn.AGNNConv(1)
feat = F.randn((g.number_of_nodes(), 5))
agnn = agnn.to(ctx)
h = agnn(g, feat)
assert h.shape == (g.number_of_nodes(), 5)
def __init__(self, in_dim, n_classes, hidden_layers, init_beta, learn_beta,
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.AGNNConv(init_beta, learn_beta))
self.batch_norms.append(nn.BatchNorm1d(in_dim))
# hidden layers
for k in range(0, hidden_layers):
self.layers.append(conv.AGNNConv(init_beta, learn_beta))
self.batch_norms.append(nn.BatchNorm1d(in_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(in_dim, 1), nn.Linear(in_dim, in_dim * 2))
else:
self.readout_fcn = SppPooling(in_dim, self.grid)
if self.readout == 'spp':
self.classify = nn.Sequential(
nn.Dropout(),
nn.Linear(in_dim * self.grid * self.grid, in_dim * 2),
nn.ReLU(inplace=True),
nn.Linear(2 * in_dim, n_classes),
)
else:
var = in_dim
if self.readout == 'gap':
var *= 2
self.classify = nn.Linear(var, n_classes)
def test_agnn_conv():
ctx = F.ctx()
g = dgl.graph(sp.sparse.random(100, 100, density=0.1))
agnn = nn.AGNNConv(1)
feat = F.randn((100, 5))
agnn = agnn.to(ctx)
h = agnn(g, feat)
assert h.shape == (100, 5)
g = dgl.bipartite(sp.sparse.random(100, 200, density=0.1))
agnn = nn.AGNNConv(1)
feat = (F.randn((100, 5)), F.randn((200, 5)))
agnn = agnn.to(ctx)
h = agnn(g, feat)
assert h.shape == (200, 5)
g = dgl.graph(sp.sparse.random(100, 100, density=0.001))
seed_nodes = th.unique(g.edges()[1])
block = dgl.to_block(g, seed_nodes)
agnn = nn.AGNNConv(1)
feat = F.randn((block.number_of_src_nodes(), 5))
agnn = agnn.to(ctx)
h = agnn(block, feat)
assert h.shape == (block.number_of_dst_nodes(), 5)