def test_assignment_of_dynamic_scalar(Simulator, rng):
with spa.Network() as model:
source = spa.Scalar()
sink = spa.Scalar()
nengo.Connection(nengo.Node(0.5), source.input)
source >> sink
p = nengo.Probe(sink.output, synapse=0.03)
with Simulator(model) as sim:
sim.run(0.5)
assert_allclose(sim.data[p][sim.trange() > 0.3], 0.5, atol=0.2)
def test_product_of_scalars(Simulator):
with spa.Network() as model:
stimulus = nengo.Node(0.5)
a = spa.Scalar()
b = spa.Scalar()
nengo.Connection(stimulus, a.input)
nengo.Connection(stimulus, b.input)
x = a * b
p = nengo.Probe(x.construct(), synapse=0.03)
with Simulator(model) as sim:
sim.run(0.5)
assert_allclose(sim.data[p][sim.trange() > 0.3], 0.25, atol=0.2)
def test_access_thal_and_bg_objects():
with spa.Network() as m:
m.a = spa.Scalar()
m.b = spa.Scalar()
m.c = spa.Scalar()
m.d = spa.Scalar()
with spa.ActionSelection() as actions:
spa.ifmax(m.a, 0 >> m.c)
spa.ifmax(m.b, 1 >> m.c)
assert isinstance(actions.bg, spa.BasalGanglia)
assert isinstance(actions.thalamus, spa.Thalamus)
def model(self):
with spa.Network() as model:
model.state_a = spa.State(16)
model.state_b = spa.State(32)
model.state_c = spa.State(32)
model.scalar = spa.Scalar()
return model
def test_assignment_of_fixed_scalar(Simulator, rng):
with spa.Network() as model:
sink = spa.Scalar()
0.5 >> sink
p = nengo.Probe(sink.output, synapse=0.03)
with Simulator(model) as sim:
sim.run(0.5)
assert_allclose(sim.data[p][sim.trange() > 0.3], 0.5, atol=0.2)
def test_scalar_addition(Simulator):
with spa.Network() as model:
a = spa.Scalar()
b = spa.Scalar()
0.3 >> a
0.2 >> b
n1 = (a + b).construct()
n2 = nengo.Node(size_in=1)
(a + b).connect_to(n2)
p1 = nengo.Probe(n1, synapse=0.03)
p2 = nengo.Probe(n2, synapse=0.03)
with Simulator(model) as sim:
sim.run(0.3)
assert np.all(np.abs(sim.data[p1][sim.trange() > 0.2] - 0.5) < 0.1)
assert np.all(np.abs(sim.data[p2][sim.trange() > 0.2] - 0.5) < 0.1)
def test_action_selection(Simulator, rng):
vocab = spa.Vocabulary(64)
vocab.populate("A; B; C; D; E; F")
with spa.Network() as model:
state = spa.Transcode(lambda t: "ABCDEF"[min(5, int(t / 0.5))],
output_vocab=vocab)
scalar = spa.Scalar()
pointer = spa.State(vocab)
with ActionSelection():
spa.ifmax(spa.dot(state, PointerSymbol("A")), 0.5 >> scalar)
spa.ifmax(spa.dot(state, PointerSymbol("B")),
PointerSymbol("B") >> pointer)
spa.ifmax(spa.dot(state, PointerSymbol("C")), state >> pointer)
d_utility = spa.ifmax(0, PointerSymbol("D") >> pointer)
spa.ifmax(
spa.dot(state, PointerSymbol("E")),
0.25 >> scalar,
PointerSymbol("E") >> pointer,
)
nengo.Connection(nengo.Node(lambda t: 1.5 < t <= 2.0), d_utility)
p_scalar = nengo.Probe(scalar.output, synapse=0.03)
p_pointer = nengo.Probe(pointer.output, synapse=0.03)
with Simulator(model) as sim:
sim.run(3.0)
t = sim.trange()
assert_allclose(sim.data[p_scalar][(0.3 < t) & (t <= 0.5)], 0.5, atol=0.2)
assert_sp_close(sim.trange(),
sim.data[p_pointer],
vocab["B"],
skip=0.8,
duration=0.2)
assert_sp_close(sim.trange(),
sim.data[p_pointer],
vocab["C"],
skip=1.3,
duration=0.2)
assert_sp_close(sim.trange(),
sim.data[p_pointer],
vocab["D"],
skip=1.8,
duration=0.2)
assert_allclose(sim.data[p_scalar][(2.3 < t) & (t <= 2.5)], 0.25, atol=0.2)
assert_sp_close(sim.trange(),
sim.data[p_pointer],
vocab["E"],
skip=2.3,
duration=0.2)
def test_assignment_of_nengo_scalar(source, use_ens, Simulator, rng):
with spa.Network() as model:
source = eval(source)
if use_ens:
ens = nengo.Ensemble(50, 1)
nengo.Connection(source, ens)
source = ens
sink = spa.Scalar()
source >> sink
p = nengo.Probe(sink.output, synapse=0.03)
with Simulator(model) as sim:
sim.run(0.5)
assert_allclose(sim.data[p][sim.trange() > 0.3], 0.5, atol=0.2)
def test_dot_product(Simulator, seed, plt):
d = 16
with spa.Network(seed=seed) as model:
model.state_a = spa.State(d)
model.state_b = spa.State(d)
model.result = spa.Scalar()
model.stimulus = spa.Transcode(lambda t: "A" if t <= 0.3 else "B",
output_vocab=d)
spa.sym.A >> model.state_a
model.stimulus >> model.state_b
spa.dot(model.state_a, model.state_b) >> model.result
p = nengo.Probe(model.result.output, synapse=0.03)
with Simulator(model) as sim:
sim.run(0.6)
plt.plot(sim.trange(), sim.data[p])
t = sim.trange()
assert np.mean(sim.data[p][(t > 0.1) & (t <= 0.3)]) > 0.8
assert np.mean(sim.data[p][t > 0.4]) < 0.15
def test_pointer_symbol_with_dynamic_scalar(Simulator, rng):
with spa.Network():
scalar = spa.Scalar()
with pytest.raises(SpaTypeError):
PointerSymbol("A") * scalar
def test_scalar_product():
with spa.Network() as model:
model.scalar = spa.Scalar()
with spa.ActionSelection():
spa.ifmax(model.scalar * model.scalar, 1 >> model.scalar)