def test_topk_nodes():
# test#1: basic
g0 = dgl.DGLGraph(nx.path_graph(14))
feat0 = F.randn((g0.number_of_nodes(), 10))
g0.ndata['x'] = feat0
# to test the case where k > number of nodes.
dgl.topk_nodes(g0, 'x', 20, idx=-1)
# test correctness
val, indices = dgl.topk_nodes(g0, 'x', 5, idx=-1)
ground_truth = F.reshape(
F.argsort(F.slice_axis(feat0, -1, 9, 10), 0, True)[:5], (5,))
assert F.allclose(ground_truth, indices)
g0.ndata.pop('x')
# test#2: batched graph
g1 = dgl.DGLGraph(nx.path_graph(12))
feat1 = F.randn((g1.number_of_nodes(), 10))
bg = dgl.batch([g0, g1])
bg.ndata['x'] = F.cat([feat0, feat1], 0)
# to test the case where k > number of nodes.
dgl.topk_nodes(bg, 'x', 16, idx=1)
# test correctness
val, indices = dgl.topk_nodes(bg, 'x', 6, descending=False, idx=0)
ground_truth_0 = F.reshape(
F.argsort(F.slice_axis(feat0, -1, 0, 1), 0, False)[:6], (6,))
ground_truth_1 = F.reshape(
F.argsort(F.slice_axis(feat1, -1, 0, 1), 0, False)[:6], (6,))
ground_truth = F.stack([ground_truth_0, ground_truth_1], 0)
assert F.allclose(ground_truth, indices)
# test idx=None
val, indices = dgl.topk_nodes(bg, 'x', 6, descending=True)
assert F.allclose(val, F.stack([F.topk(feat0, 6, 0), F.topk(feat1, 6, 0)], 0))
def test_send_twice_different_msg():
g = DGLGraph()
g.set_n_initializer(dgl.init.zero_initializer)
g.add_nodes(3)
g.add_edge(0, 1)
g.add_edge(2, 1)
def _message_a(edges):
return {'a': edges.src['a']}
def _message_b(edges):
return {'a': edges.src['a'] * 3}
def _reduce(nodes):
return {'a': F.max(nodes.mailbox['a'], 1)}
old_repr = F.randn((3, 5))
g.ndata['a'] = old_repr
g.send((0, 1), _message_a)
g.send((0, 1), _message_b)
g.recv(1, _reduce)
new_repr = g.ndata['a']
assert F.allclose(new_repr[1], old_repr[0] * 3)
g.ndata['a'] = old_repr
g.send((0, 1), _message_a)
g.send((2, 1), _message_b)
g.recv(1, _reduce)
new_repr = g.ndata['a']
assert F.allclose(new_repr[1],
F.max(F.stack([old_repr[0], old_repr[2] * 3], 0), 0))
def test_simple_readout():
g1 = dgl.DGLGraph()
g1.add_nodes(3)
g2 = dgl.DGLGraph()
g2.add_nodes(4) # no edges
g1.add_edges([0, 1, 2], [2, 0, 1])
n1 = F.randn((3, 5))
n2 = F.randn((4, 5))
e1 = F.randn((3, 5))
s1 = F.sum(n1, 0) # node sums
s2 = F.sum(n2, 0)
se1 = F.sum(e1, 0) # edge sums
m1 = F.mean(n1, 0) # node means
m2 = F.mean(n2, 0)
me1 = F.mean(e1, 0) # edge means
w1 = F.randn((3, ))
w2 = F.randn((4, ))
max1 = F.max(n1, 0)
max2 = F.max(n2, 0)
maxe1 = F.max(e1, 0)
ws1 = F.sum(n1 * F.unsqueeze(w1, 1), 0)
ws2 = F.sum(n2 * F.unsqueeze(w2, 1), 0)
wm1 = F.sum(n1 * F.unsqueeze(w1, 1), 0) / F.sum(F.unsqueeze(w1, 1), 0)
wm2 = F.sum(n2 * F.unsqueeze(w2, 1), 0) / F.sum(F.unsqueeze(w2, 1), 0)
g1.ndata['x'] = n1
g2.ndata['x'] = n2
g1.ndata['w'] = w1
g2.ndata['w'] = w2
g1.edata['x'] = e1
assert F.allclose(dgl.sum_nodes(g1, 'x'), s1)
assert F.allclose(dgl.sum_nodes(g1, 'x', 'w'), ws1)
assert F.allclose(dgl.sum_edges(g1, 'x'), se1)
assert F.allclose(dgl.mean_nodes(g1, 'x'), m1)
assert F.allclose(dgl.mean_nodes(g1, 'x', 'w'), wm1)
assert F.allclose(dgl.mean_edges(g1, 'x'), me1)
assert F.allclose(dgl.max_nodes(g1, 'x'), max1)
assert F.allclose(dgl.max_edges(g1, 'x'), maxe1)
g = dgl.batch([g1, g2])
s = dgl.sum_nodes(g, 'x')
m = dgl.mean_nodes(g, 'x')
max_bg = dgl.max_nodes(g, 'x')
assert F.allclose(s, F.stack([s1, s2], 0))
assert F.allclose(m, F.stack([m1, m2], 0))
assert F.allclose(max_bg, F.stack([max1, max2], 0))
ws = dgl.sum_nodes(g, 'x', 'w')
wm = dgl.mean_nodes(g, 'x', 'w')
assert F.allclose(ws, F.stack([ws1, ws2], 0))
assert F.allclose(wm, F.stack([wm1, wm2], 0))
s = dgl.sum_edges(g, 'x')
m = dgl.mean_edges(g, 'x')
max_bg_e = dgl.max_edges(g, 'x')
assert F.allclose(s, F.stack([se1, F.zeros(5)], 0))
assert F.allclose(m, F.stack([me1, F.zeros(5)], 0))
assert F.allclose(max_bg_e, F.stack([maxe1, F.zeros(5)], 0))
def call(self, x, **kwargs):
debug_print("call")
# filters = K.zeros(shape=(N_filt, Filt_dim))
min_freq = 50.0
min_band = 50.0
filt_beg_freq = K.abs(self.filt_b1) + min_freq / self.freq_scale
filt_end_freq = filt_beg_freq + (K.abs(self.filt_band) +
min_band / self.freq_scale)
n = np.linspace(0, self.Filt_dim, self.Filt_dim)
window = 0.54 - 0.46 * K.cos(2 * math.pi * n / self.Filt_dim)
window = K.cast(window, "float32")
window = K.variable(window)
t_right_linspace = np.linspace(1, (self.Filt_dim - 1) / 2,
int((self.Filt_dim - 1) / 2))
t_right = K.variable(t_right_linspace / self.fs)
# Compute the filters.
output_list = []
for i in range(self.N_filt):
low_pass1 = (
2 * self.filt_beg_freq[i] *
sinc(self.filt_beg_freq[i] * self.freq_scale, self.t_right))
low_pass2 = (
2 * self.filt_end_freq[i] *
sinc(self.filt_end_freq[i] * self.freq_scale, self.t_right))
band_pass = low_pass2 - low_pass1
band_pass = band_pass / K.max(band_pass)
output_list.append(band_pass * self.window)
filters = K.stack(output_list) # (80, 251)
filters = K.transpose(filters) # (251, 80)
filters = K.reshape(
filters, (self.Filt_dim, 1, self.N_filt)
) # (251,1,80) in TF: (filter_width, in_channels, out_channels) in
# PyTorch (out_channels, in_channels, filter_width)
"""Given an input tensor of shape [batch, in_width, in_channels] if data_format is "NWC", or [batch,
in_channels, in_width] if data_format is "NCW", and a filter / kernel tensor of shape [filter_width,
in_channels, out_channels], this op reshapes the arguments to pass them to conv2d to perform the equivalent
convolution operation. Internally, this op reshapes the input tensors and invokes tf.nn.conv2d. For example,
if data_format does not start with "NC", a tensor of shape [batch, in_width, in_channels] is reshaped to [
batch, 1, in_width, in_channels], and the filter is reshaped to [1, filter_width, in_channels, out_channels].
The result is then reshaped back to [batch, out_width, out_channels] (where out_width is a function of the
stride and padding as in conv2d) and returned to the caller. """
# Do the convolution.
debug_print("call")
debug_print(" x", x)
debug_print(" filters", filters)
out = K.conv1d(x, kernel=filters)
debug_print(" out", out)
return out
def test_broadcast_edges():
# test#1: basic
g0 = dgl.DGLGraph(nx.path_graph(10))
feat0 = F.randn((40, ))
ground_truth = F.stack([feat0] * g0.number_of_edges(), 0)
assert F.allclose(dgl.broadcast_edges(g0, feat0), ground_truth)
# test#2: batched graph
g1 = dgl.DGLGraph(nx.path_graph(3))
g2 = dgl.DGLGraph()
g3 = dgl.DGLGraph(nx.path_graph(12))
bg = dgl.batch([g0, g1, g2, g3])
feat1 = F.randn((40, ))
feat2 = F.randn((40, ))
feat3 = F.randn((40, ))
ground_truth = F.stack(
[feat0] * g0.number_of_edges() +\
[feat1] * g1.number_of_edges() +\
[feat2] * g2.number_of_edges() +\
[feat3] * g3.number_of_edges(), 0
)
assert F.allclose(
dgl.broadcast_edges(bg, F.stack([feat0, feat1, feat2, feat3], 0)),
ground_truth)
def answer(*args):
return F.max(F.stack(args, 0), 0)
def test_level2():
#edges = {
# 'follows': ([0, 1], [1, 2]),
# 'plays': ([0, 1, 2, 1], [0, 0, 1, 1]),
# 'wishes': ([0, 2], [1, 0]),
# 'develops': ([0, 1], [0, 1]),
#}
g = create_test_heterograph()
def rfunc(nodes):
return {'y': F.sum(nodes.mailbox['m'], 1)}
def rfunc2(nodes):
return {'y': F.max(nodes.mailbox['m'], 1)}
def mfunc(edges):
return {'m': edges.src['h']}
def afunc(nodes):
return {'y': nodes.data['y'] + 1}
#############################################################
# send_and_recv
#############################################################
g.nodes['user'].data['h'] = F.ones((3, 2))
g.send_and_recv([2, 3], mfunc, rfunc, etype='plays')
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[0., 0.], [2., 2.]]))
# only one type
g['plays'].send_and_recv([2, 3], mfunc, rfunc)
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[0., 0.], [2., 2.]]))
# test fail case
# fail due to multiple types
fail = False
try:
g.send_and_recv([2, 3], mfunc, rfunc)
except dgl.DGLError:
fail = True
assert fail
# test multi
g.multi_send_and_recv(
{
'plays': (g.edges(etype='plays'), mfunc, rfunc),
('user', 'wishes', 'game'):
(g.edges(etype='wishes'), mfunc, rfunc2)
}, 'sum')
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[3., 3.], [3., 3.]]))
# test multi
g.multi_send_and_recv(
{
'plays': (g.edges(etype='plays'), mfunc, rfunc, afunc),
('user', 'wishes', 'game'):
(g.edges(etype='wishes'), mfunc, rfunc2)
}, 'sum', afunc)
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[5., 5.], [5., 5.]]))
# test cross reducer
g.nodes['user'].data['h'] = F.randn((3, 2))
for cred in ['sum', 'max', 'min', 'mean']:
g.multi_send_and_recv(
{
'plays': (g.edges(etype='plays'), mfunc, rfunc, afunc),
'wishes': (g.edges(etype='wishes'), mfunc, rfunc2)
}, cred, afunc)
y = g.nodes['game'].data['y']
g['plays'].send_and_recv(g.edges(etype='plays'), mfunc, rfunc, afunc)
y1 = g.nodes['game'].data['y']
g['wishes'].send_and_recv(g.edges(etype='wishes'), mfunc, rfunc2)
y2 = g.nodes['game'].data['y']
yy = get_redfn(cred)(F.stack([y1, y2], 0), 0)
yy = yy + 1 # final afunc
assert F.array_equal(y, yy)
# test fail case
# fail because cannot infer ntype
fail = False
try:
g.multi_send_and_recv(
{
'plays': (g.edges(etype='plays'), mfunc, rfunc),
'follows': (g.edges(etype='follows'), mfunc, rfunc2)
}, 'sum')
except dgl.DGLError:
fail = True
assert fail
g.nodes['game'].data.clear()
#############################################################
# pull
#############################################################
g.nodes['user'].data['h'] = F.ones((3, 2))
g.pull(1, mfunc, rfunc, etype='plays')
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[0., 0.], [2., 2.]]))
# only one type
g['plays'].pull(1, mfunc, rfunc)
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[0., 0.], [2., 2.]]))
# test fail case
fail = False
try:
g.pull(1, mfunc, rfunc)
except dgl.DGLError:
fail = True
assert fail
# test multi
g.multi_pull(1, {
'plays': (mfunc, rfunc),
('user', 'wishes', 'game'): (mfunc, rfunc2)
}, 'sum')
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[0., 0.], [3., 3.]]))
# test multi
g.multi_pull(
1, {
'plays': (mfunc, rfunc, afunc),
('user', 'wishes', 'game'): (mfunc, rfunc2)
}, 'sum', afunc)
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[0., 0.], [5., 5.]]))
# test cross reducer
g.nodes['user'].data['h'] = F.randn((3, 2))
for cred in ['sum', 'max', 'min', 'mean']:
g.multi_pull(1, {
'plays': (mfunc, rfunc, afunc),
'wishes': (mfunc, rfunc2)
}, cred, afunc)
y = g.nodes['game'].data['y']
g['plays'].pull(1, mfunc, rfunc, afunc)
y1 = g.nodes['game'].data['y']
g['wishes'].pull(1, mfunc, rfunc2)
y2 = g.nodes['game'].data['y']
g.nodes['game'].data['y'] = get_redfn(cred)(F.stack([y1, y2], 0), 0)
g.apply_nodes(afunc, 1, ntype='game')
yy = g.nodes['game'].data['y']
assert F.array_equal(y, yy)
# test fail case
# fail because cannot infer ntype
fail = False
try:
g.multi_pull(1, {
'plays': (mfunc, rfunc),
'follows': (mfunc, rfunc2)
}, 'sum')
except dgl.DGLError:
fail = True
assert fail
g.nodes['game'].data.clear()
#############################################################
# update_all
#############################################################
g.nodes['user'].data['h'] = F.ones((3, 2))
g.update_all(mfunc, rfunc, etype='plays')
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[2., 2.], [2., 2.]]))
# only one type
g['plays'].update_all(mfunc, rfunc)
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[2., 2.], [2., 2.]]))
# test fail case
# fail due to multiple types
fail = False
try:
g.update_all(mfunc, rfunc)
except dgl.DGLError:
fail = True
assert fail
# test multi
g.multi_update_all(
{
'plays': (mfunc, rfunc),
('user', 'wishes', 'game'): (mfunc, rfunc2)
}, 'sum')
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[3., 3.], [3., 3.]]))
# test multi
g.multi_update_all(
{
'plays': (mfunc, rfunc, afunc),
('user', 'wishes', 'game'): (mfunc, rfunc2)
}, 'sum', afunc)
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[5., 5.], [5., 5.]]))
# test cross reducer
g.nodes['user'].data['h'] = F.randn((3, 2))
for cred in ['sum', 'max', 'min', 'mean', 'stack']:
g.multi_update_all(
{
'plays': (mfunc, rfunc, afunc),
'wishes': (mfunc, rfunc2)
}, cred, afunc)
y = g.nodes['game'].data['y']
g['plays'].update_all(mfunc, rfunc, afunc)
y1 = g.nodes['game'].data['y']
g['wishes'].update_all(mfunc, rfunc2)
y2 = g.nodes['game'].data['y']
if cred == 'stack':
# stack has two both correct outcomes
yy1 = F.stack([F.unsqueeze(y1, 1), F.unsqueeze(y2, 1)], 1)
yy1 = yy1 + 1 # final afunc
yy2 = F.stack([F.unsqueeze(y2, 1), F.unsqueeze(y1, 1)], 1)
yy2 = yy2 + 1 # final afunc
assert F.array_equal(y, yy1) or F.array_equal(y, yy2)
else:
yy = get_redfn(cred)(F.stack([y1, y2], 0), 0)
yy = yy + 1 # final afunc
assert F.array_equal(y, yy)
# test fail case
# fail because cannot infer ntype
fail = False
try:
g.update_all({
'plays': (mfunc, rfunc),
'follows': (mfunc, rfunc2)
}, 'sum')
except dgl.DGLError:
fail = True
assert fail
g.nodes['game'].data.clear()
def test_level1():
#edges = {
# 'follows': ([0, 1], [1, 2]),
# 'plays': ([0, 1, 2, 1], [0, 0, 1, 1]),
# 'wishes': ([0, 2], [1, 0]),
# 'develops': ([0, 1], [0, 1]),
#}
g = create_test_heterograph()
def rfunc(nodes):
return {'y': F.sum(nodes.mailbox['m'], 1)}
def rfunc2(nodes):
return {'y': F.max(nodes.mailbox['m'], 1)}
def mfunc(edges):
return {'m': edges.src['h']}
def afunc(nodes):
return {'y': nodes.data['y'] + 1}
g.nodes['user'].data['h'] = F.ones((3, 2))
g.send([2, 3], mfunc, etype='plays')
g.recv([0, 1], rfunc, etype='plays')
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[0., 0.], [2., 2.]]))
g.nodes['game'].data.pop('y')
# only one type
play_g = g['plays']
play_g.send([2, 3], mfunc)
play_g.recv([0, 1], rfunc)
y = g.nodes['game'].data['y']
assert F.array_equal(y, F.tensor([[0., 0.], [2., 2.]]))
# TODO(minjie): following codes will fail because messages are
# not shared with the base graph. However, since send and recv
# are rarely used, no fix at the moment.
# g['plays'].send([2, 3], mfunc)
# g['plays'].recv([0, 1], mfunc)
# test fail case
# fail due to multiple types
fail = False
try:
g.send([2, 3], mfunc)
except dgl.DGLError:
fail = True
assert fail
fail = False
try:
g.recv([0, 1], rfunc)
except dgl.DGLError:
fail = True
assert fail
# test multi recv
g.send(g.edges(etype='plays'), mfunc, etype='plays')
g.send(g.edges(etype='wishes'), mfunc, etype='wishes')
g.multi_recv([0, 1], {
'plays': rfunc,
('user', 'wishes', 'game'): rfunc2
}, 'sum')
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[3., 3.], [3., 3.]]))
# test multi recv with apply function
g.send(g.edges(etype='plays'), mfunc, etype='plays')
g.send(g.edges(etype='wishes'), mfunc, etype='wishes')
g.multi_recv([0, 1], {
'plays': (rfunc, afunc),
('user', 'wishes', 'game'): rfunc2
}, 'sum', afunc)
assert F.array_equal(g.nodes['game'].data['y'],
F.tensor([[5., 5.], [5., 5.]]))
# test cross reducer
g.nodes['user'].data['h'] = F.randn((3, 2))
for cred in ['sum', 'max', 'min', 'mean']:
g.send(g.edges(etype='plays'), mfunc, etype='plays')
g.send(g.edges(etype='wishes'), mfunc, etype='wishes')
g.multi_recv([0, 1], {
'plays': (rfunc, afunc),
'wishes': rfunc2
}, cred, afunc)
y = g.nodes['game'].data['y']
g1 = g['plays']
g2 = g['wishes']
g1.send(g1.edges(), mfunc)
g1.recv(g1.nodes('game'), rfunc, afunc)
y1 = g.nodes['game'].data['y']
g2.send(g2.edges(), mfunc)
g2.recv(g2.nodes('game'), rfunc2)
y2 = g.nodes['game'].data['y']
yy = get_redfn(cred)(F.stack([y1, y2], 0), 0)
yy = yy + 1 # final afunc
assert F.array_equal(y, yy)
# test fail case
# fail because cannot infer ntype
fail = False
try:
g.multi_recv([0, 1], {'plays': rfunc, 'follows': rfunc2}, 'sum')
except dgl.DGLError:
fail = True
assert fail
