# test#4: basic
h0 = F.ones((3, 5, 5))
h1 = conv(g, h0)
assert len(g.ndata) == 0
assert len(g.edata) == 0
# test not override features
g.ndata["h"] = 2 * F.ones((3, 1))
h1 = conv(g, h0)
assert len(g.ndata) == 1
assert len(g.edata) == 0
assert "h" in g.ndata
check_close(g.ndata['h'], 2 * F.ones((3, 1)))
@parametrize_dtype
@pytest.mark.parametrize('g', get_cases(['h**o', 'block-bipartite'], exclude=['zero-degree', 'dglgraph']))
@pytest.mark.parametrize('norm', ['none', 'both', 'right', 'left'])
@pytest.mark.parametrize('weight', [True, False])
@pytest.mark.parametrize('bias', [False])
@pytest.mark.parametrize('out_dim', [1, 2])
def test_graph_conv2(idtype, g, norm, weight, bias, out_dim):
g = g.astype(idtype).to(F.ctx())
conv = nn.GraphConv(5, out_dim, norm=norm, weight=weight, bias=bias)
conv.initialize(ctx=F.ctx())
ext_w = F.randn((5, out_dim)).as_in_context(F.ctx())
nsrc = g.number_of_src_nodes()
ndst = g.number_of_dst_nodes()
h = F.randn((nsrc, 5)).as_in_context(F.ctx())
if weight:
h_out = conv(g, h)
else:
h0 = F.ones((3, 5, 5))
h1 = conv(g, h0)
assert len(g.ndata) == 0
assert len(g.edata) == 0
# test not override features
g.ndata["h"] = 2 * F.ones((3, 1))
h1 = conv(g, h0)
assert len(g.ndata) == 1
assert len(g.edata) == 0
assert "h" in g.ndata
check_close(g.ndata['h'], 2 * F.ones((3, 1)))
@pytest.mark.parametrize('g',
get_cases(['path', 'bipartite', 'small'],
exclude=['zero-degree']))
@pytest.mark.parametrize('norm', ['none', 'both', 'right'])
@pytest.mark.parametrize('weight', [True, False])
@pytest.mark.parametrize('bias', [False])
def test_graph_conv2(g, norm, weight, bias):
conv = nn.GraphConv(5, 2, norm=norm, weight=weight, bias=bias)
conv.initialize(ctx=F.ctx())
ext_w = F.randn((5, 2)).as_in_context(F.ctx())
nsrc = g.number_of_nodes() if isinstance(
g, dgl.DGLGraph) else g.number_of_src_nodes()
ndst = g.number_of_nodes() if isinstance(
g, dgl.DGLGraph) else g.number_of_dst_nodes()
h = F.randn((nsrc, 5)).as_in_context(F.ctx())
h_dst = F.randn((ndst, 2)).as_in_context(F.ctx())
if weight:
h_out = conv(g, h)
h1 = conv(g, h0)
assert len(g.ndata) == 0
assert len(g.edata) == 0
# test#4: basic
h0 = F.ones((3, 5, 5))
h1 = conv(g, h0)
assert len(g.ndata) == 0
assert len(g.edata) == 0
# test rest_parameters
old_weight = deepcopy(conv.weight.data)
conv.reset_parameters()
new_weight = conv.weight.data
assert not F.allclose(old_weight, new_weight)
@pytest.mark.parametrize('g', get_cases(['path', 'bipartite', 'small'], exclude=['zero-degree']))
@pytest.mark.parametrize('norm', ['none', 'both', 'right'])
@pytest.mark.parametrize('weight', [True, False])
@pytest.mark.parametrize('bias', [True, False])
def test_graph_conv2(g, norm, weight, bias):
conv = nn.GraphConv(5, 2, norm=norm, weight=weight, bias=bias).to(F.ctx())
ext_w = F.randn((5, 2)).to(F.ctx())
nsrc = g.number_of_nodes() if isinstance(g, dgl.DGLGraph) else g.number_of_src_nodes()
ndst = g.number_of_nodes() if isinstance(g, dgl.DGLGraph) else g.number_of_dst_nodes()
h = F.randn((nsrc, 5)).to(F.ctx())
if weight:
h = conv(g, h)
else:
h = conv(g, h, weight=ext_w)
assert h.shape == (ndst, 2)
g = kg(x)
check_knn(g, x, 0, 8)
g = kg(x.view(2, 4, 3))
check_knn(g, x, 0, 4)
check_knn(g, x, 4, 8)
kg = dgl.nn.SegmentedKNNGraph(3)
g = kg(x, [3, 5])
check_knn(g, x, 0, 3)
check_knn(g, x, 3, 8)
@parametrize_dtype
@pytest.mark.parametrize('g', get_cases(['h**o'], exclude=['dglgraph']))
@pytest.mark.parametrize('weight', [True, False])
@pytest.mark.parametrize('relabel', [True, False])
def test_edge_coarsening(idtype, g, weight, relabel):
num_nodes = g.num_nodes()
g = dgl.to_bidirected(g)
g = g.astype(idtype).to(F.ctx())
edge_weight = None
if weight:
edge_weight = F.abs(F.randn((g.num_edges(),))).to(F.ctx())
node_labels = neighbor_matching(g, edge_weight, relabel_idx=relabel)
unique_ids, counts = th.unique(node_labels, return_counts=True)
num_result_ids = unique_ids.size(0)
# shape correct
assert node_labels.shape == (g.num_nodes(),)
assert F.allclose(e, e1)
print('forward passed')
F.backward(F.reduce_sum(e1))
if msg != 'copy_rhs':
assert F.allclose(F.grad(lhs_frame['x']), grad_lhs)
if msg != 'copy_lhs':
assert F.allclose(F.grad(rhs_frame['y']), grad_rhs)
print('backward passed')
lhs_frame.pop('x')
rhs_frame.pop('y')
if 'm' in g.edata: g.edata.pop('m')
@pytest.mark.parametrize('g', get_cases(['clique']))
@pytest.mark.parametrize('norm_by', ['src', 'dst'])
@pytest.mark.parametrize('shp', edge_softmax_shapes)
@parametrize_dtype
def test_edge_softmax(g, norm_by, shp, idtype):
g = g.astype(idtype).to(F.ctx())
edata = F.tensor(np.random.rand(g.number_of_edges(), *shp))
e1 = F.attach_grad(F.clone(edata))
with F.record_grad():
score1 = edge_softmax(g, e1, norm_by=norm_by)
F.backward(F.reduce_sum(score1))
grad_edata = F.grad(e1)
with F.record_grad():
e2 = F.attach_grad(F.clone(edata))
import dgl
import pytest
import torch
from dglgo.model import *
from test_utils.graph_cases import get_cases
@pytest.mark.parametrize('g', get_cases(['has_scalar_e_feature']))
def test_gcn(g):
data_info = {
'num_nodes': g.num_nodes(),
'out_size': 7
}
node_feat = None
edge_feat = g.edata['scalar_w']
# node embedding + not use_edge_weight
model = GCN(data_info, embed_size=10, use_edge_weight=False)
model(g, node_feat)
# node embedding + use_edge_weight
model = GCN(data_info, embed_size=10, use_edge_weight=True)
model(g, node_feat, edge_feat)
data_info['in_size'] = g.ndata['h'].shape[-1]
node_feat = g.ndata['h']
# node feat + not use_edge_weight
model = GCN(data_info, embed_size=-1, use_edge_weight=False)
model(g, node_feat)
# node feat + use_edge_weight