def test_nn_conv():
ctx = F.ctx()
g = dgl.DGLGraph(sp.sparse.random(100, 100, density=0.1), readonly=True)
edge_func = th.nn.Linear(4, 5 * 10)
nnconv = nn.NNConv(5, 10, edge_func, 'mean')
feat = F.randn((100, 5))
efeat = F.randn((g.number_of_edges(), 4))
nnconv = nnconv.to(ctx)
h = nnconv(g, feat, efeat)
# currently we only do shape check
assert h.shape[-1] == 10
g = dgl.graph(sp.sparse.random(100, 100, density=0.1))
edge_func = th.nn.Linear(4, 5 * 10)
nnconv = nn.NNConv(5, 10, edge_func, 'mean')
feat = F.randn((100, 5))
efeat = F.randn((g.number_of_edges(), 4))
nnconv = nnconv.to(ctx)
h = nnconv(g, feat, efeat)
# currently we only do shape check
assert h.shape[-1] == 10
g = dgl.bipartite(sp.sparse.random(50, 100, density=0.1))
edge_func = th.nn.Linear(4, 5 * 10)
nnconv = nn.NNConv((5, 2), 10, edge_func, 'mean')
feat = F.randn((50, 5))
feat_dst = F.randn((100, 2))
efeat = F.randn((g.number_of_edges(), 4))
nnconv = nnconv.to(ctx)
h = nnconv(g, (feat, feat_dst), efeat)
# currently we only do shape check
assert h.shape[-1] == 10
def test_nn_conv(g, idtype):
g = g.astype(idtype).to(F.ctx())
ctx = F.ctx()
edge_func = th.nn.Linear(4, 5 * 10)
nnconv = nn.NNConv(5, 10, edge_func, 'mean')
feat = F.randn((g.number_of_nodes(), 5))
efeat = F.randn((g.number_of_edges(), 4))
nnconv = nnconv.to(ctx)
h = nnconv(g, feat, efeat)
# currently we only do shape check
assert h.shape[-1] == 10
def test_nn_conv_bi(g, idtype):
g = g.astype(idtype).to(F.ctx())
ctx = F.ctx()
#g = dgl.bipartite(sp.sparse.random(50, 100, density=0.1))
edge_func = th.nn.Linear(4, 5 * 10)
nnconv = nn.NNConv((5, 2), 10, edge_func, 'mean')
feat = F.randn((g.number_of_src_nodes(), 5))
feat_dst = F.randn((g.number_of_dst_nodes(), 2))
efeat = F.randn((g.number_of_edges(), 4))
nnconv = nnconv.to(ctx)
h = nnconv(g, (feat, feat_dst), efeat)
# currently we only do shape check
assert h.shape[-1] == 10
def __init__(self, in_dim, hidden_dim, n_classes, hidden_layers, edge_dim,
aggregate, residual, readout, activation_func, dropout, grid,
device):
super(Classifier, self).__init__()
self.device = device
self.activation = activation_func
self.readout = readout
self.layers = nn.ModuleList()
self.batch_norms = nn.ModuleList()
self.grid = grid
self.layers.append(
conv.NNConv(in_dim, hidden_dim,
nn.Linear(edge_dim, in_dim * hidden_dim), aggregate,
residual))
self.batch_norms.append(nn.BatchNorm1d(hidden_dim))
# hidden layers
for k in range(0, hidden_layers):
self.layers.append(
conv.NNConv(hidden_dim, hidden_dim,
nn.Linear(edge_dim, hidden_dim * hidden_dim),
aggregate, residual))
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, 1)
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)