def _basic_model(n_blocks=2):
model = Model()
blocks = []
for _ in range(n_blocks):
block = LoihiBlock(1)
block.compartment.configure_lif()
model.add_block(block)
blocks.append(block)
for i in range(n_blocks - 1):
axon = Axon(1)
blocks[i].add_axon(axon)
synapse = Synapse(1)
synapse.set_weights([[1]])
axon.target = synapse
blocks[i + 1].add_synapse(synapse)
axon0 = Axon(1)
input = LoihiInput()
input.add_axon(axon0)
model.add_input(input)
synapse0 = Synapse(1)
synapse0.set_weights([[1]])
axon0.target = synapse0
blocks[0].add_synapse(synapse0)
discretize_model(model)
return model
def test_multiple_get_probe_output():
n_steps = 15
n_axons = 3
model = Model()
# n_axons controls number of input spikes and thus amount of overflow
input = SpikeInput(n_axons)
for t in np.arange(1, n_steps + 1):
input.add_spikes(t, np.arange(n_axons)) # send spikes to all axons
model.add_input(input)
block = LoihiBlock(1)
block.compartment.configure_relu()
block.compartment.configure_filter(0.1)
model.add_block(block)
synapse = Synapse(n_axons)
synapse.set_weights(np.ones((n_axons, 1)))
block.add_synapse(synapse)
axon = Axon(n_axons)
axon.target = synapse
input.add_axon(axon)
probe_u = LoihiProbe(target=block, key="current", synapse=Lowpass(0.005))
model.add_probe(probe_u)
probe_v = LoihiProbe(target=block, key="voltage", synapse=Lowpass(0.005))
model.add_probe(probe_v)
probe_s = LoihiProbe(target=block, key="spiked", synapse=Lowpass(0.005))
model.add_probe(probe_s)
discretize_model(model)
# must set these after `discretize` to specify discretized values
block.compartment.vmin = -(2**22) + 1
block.compartment.vth[:] = VTH_MAX
with EmulatorInterface(model) as emu:
emu.run_steps(n_steps)
first_u = emu.get_probe_output(probe_u)
first_v = emu.get_probe_output(probe_v)
first_s = emu.get_probe_output(probe_s)
second_u = emu.get_probe_output(probe_u)
second_v = emu.get_probe_output(probe_v)
second_s = emu.get_probe_output(probe_s)
assert np.all(first_u == second_u)
assert np.all(first_v == second_v)
assert np.all(first_s == second_s)
def test_negative_base(request, seed):
n_axons = 3
model = Model()
input = SpikeInput(n_axons)
input.add_spikes(1, list(range(n_axons)), permanent=True)
model.add_input(input)
axon = Axon(n_axons)
input.add_axon(axon)
block = LoihiBlock(3)
block.compartment.configure_relu()
model.add_block(block)
synapse = Synapse(n_axons)
weights = [0.1, 0.1, 0.1]
indices = [0, 1, 2]
axon_to_weight_map = list(range(n_axons))
bases = [0, 1, -1]
synapse.set_population_weights(
weights, indices, axon_to_weight_map, bases, pop_type=32
)
axon.target = synapse
block.add_synapse(synapse)
probe = LoihiProbe(target=block, key="voltage")
model.add_probe(probe)
discretize_model(model)
n_steps = 2
if request.config.getoption("--target") == "loihi":
with HardwareInterface(model, use_snips=False, seed=seed) as sim:
sim.run_steps(n_steps)
y = sim.collect_probe_output(probe)
else:
with EmulatorInterface(model, seed=seed) as sim:
sim.run_steps(n_steps)
y = sim.collect_probe_output(probe)
# Compartments 0 and 2 should change from axons 0 and 1.
# Axon 2 should have no effect, and not change compartment 1 (the sum of
# its base and index), or other compartments (e.g. 2 if base ignored)
assert np.allclose(y[1, 1], 0), "Third axon not ignored"
assert np.allclose(y[1, 0], y[1, 2]), "Third axon targeting another"
assert not np.allclose(y[1], y[0]), "Voltage not changing"
def test_builder_poptype_errors():
pytest.importorskip("nxsdk")
# Test error in build_synapse
model = Model()
block = LoihiBlock(1)
block.compartment.configure_lif()
model.add_block(block)
synapse = Synapse(1)
synapse.set_weights([[1]])
synapse.pop_type = 8
block.add_synapse(synapse)
discretize_model(model)
allocator = Greedy() # one core per ensemble
board = allocator(model, n_chips=1)
with pytest.raises(ValueError, match="[Ss]ynapse.*[Uu]nrec.*pop.*type"):
build_board(board)
# Test error in collect_axons
model = Model()
block0 = LoihiBlock(1)
block0.compartment.configure_lif()
model.add_block(block0)
block1 = LoihiBlock(1)
block1.compartment.configure_lif()
model.add_block(block1)
axon = Axon(1)
block0.add_axon(axon)
synapse = Synapse(1)
synapse.set_weights([[1]])
synapse.pop_type = 8
axon.target = synapse
block1.add_synapse(synapse)
discretize_model(model)
board = allocator(model, n_chips=1)
with pytest.raises(ValueError, match="[Aa]xon.*[Uu]nrec.*pop.*type"):
build_board(board)
def build_network(model,
network,
precompute=None,
remove_passthrough=True,
discretize=True):
if model.toplevel is None:
# We don't set model.toplevel to network because `nengo_build_network`
# will do that and relies on it being `None` initially.
# Ensure seeds are identical to Nengo
# Note: This does nothing for nengo<=2.8.0, seeds will always be different
seed_network(network, seeds=model.seeds, seeded=model.seeded)
# Determine how to split the host into one, two or three models
model.split = Split(network,
precompute=precompute,
remove_passthrough=remove_passthrough)
# Delegate most of the network building to Nengo
nengo_build_network(model, network, progress=None)
if network is model.toplevel:
# Build the extra passthrough connections into the model
passthrough = model.split.passthrough
for conn in passthrough.to_add:
# Note: connections added by the passthrough splitter do not have seeds
model.seeds[conn] = None
model.seeded[conn] = False
model.build(conn)
# Split blocks into blocks that will fit on cores
block_map = split_model(model)
model.block_comp_map = {
new_block: comp_idxs
for old_block, new_blocks in block_map.items()
for new_block, comp_idxs in new_blocks.items()
}
if discretize:
discretize_model(model)
validate_model(model)
def test_uv_overflow(n_axons, plt, allclose, monkeypatch):
# TODO: Currently this is not testing the V overflow, since it is higher
# and I haven't been able to figure out a way to make it overflow.
nt = 15
model = Model()
# n_axons controls number of input spikes and thus amount of overflow
input = SpikeInput(n_axons)
for t in np.arange(1, nt + 1):
# send spikes to all axons
input.add_spikes(t, np.arange(n_axons), permanent=True)
model.add_input(input)
block = LoihiBlock(1)
block.compartment.configure_relu()
block.compartment.configure_filter(0.1)
model.add_block(block)
synapse = Synapse(n_axons)
synapse.set_weights(np.ones((n_axons, 1)))
block.add_synapse(synapse)
axon = Axon(n_axons)
axon.target = synapse
input.add_axon(axon)
probe_u = LoihiProbe(target=block, key="current")
model.add_probe(probe_u)
probe_v = LoihiProbe(target=block, key="voltage")
model.add_probe(probe_v)
probe_s = LoihiProbe(target=block, key="spiked")
model.add_probe(probe_s)
discretize_model(model)
# must set these after `discretize` to specify discretized values
block.compartment.vmin = -(2**22) + 1
block.compartment.vth[:] = VTH_MAX
assert EmulatorInterface.strict # Tests should be run in strict mode
monkeypatch.setattr(EmulatorInterface, "strict", False)
overflow_var = "q0" if n_axons == 1000 else "current"
with EmulatorInterface(model) as emu:
with pytest.warns(UserWarning, match=f"Overflow in {overflow_var}"):
emu.run_steps(nt)
emu_u = emu.collect_probe_output(probe_u)
emu_v = emu.collect_probe_output(probe_v)
emu_s = emu.collect_probe_output(probe_s)
with HardwareInterface(model, use_snips=False) as sim:
sim.run_steps(nt)
sim_u = sim.collect_probe_output(probe_u)
sim_v = sim.collect_probe_output(probe_v)
sim_s = sim.collect_probe_output(probe_s)
sim_v[sim_s > 0] = 0 # since Loihi has placeholder voltage after spike
plt.subplot(311)
plt.plot(emu_u)
plt.plot(sim_u)
plt.subplot(312)
plt.plot(emu_v)
plt.plot(sim_v)
plt.subplot(313)
plt.plot(emu_s)
plt.plot(sim_s)
assert allclose(emu_u, sim_u)
assert allclose(emu_v, sim_v)
def test_pop_tiny(pop_type, channels_last, nc, request, plt, seed, allclose):
tau_rc = 0.02
tau_ref = 0.001
tau_s = 0.0
dt = 0.001
neuron_bias = 1.0
pres_time = 0.4
sti, stj = 1, 1
if nc == 1:
filters = np.array([
[-0.5, 2.0, -0.25],
[-0.75, 2.0, -1.0],
[-0.5, 3.0, -0.5],
[-1.0, 6.0, -0.25],
]).reshape((1, 4, 1, 3))
inp_biases = np.array([[1, 5, 1], [2, 1, 2]])
inp_biases = inp_biases[:, :, None]
elif nc == 2:
filters = np.array([
[
[-0.5, 2.0, -0.2],
[-0.7, 2.0, -1.0],
[-0.5, 3.0, -0.5],
[-1.0, 6.0, -0.2],
],
[
[-1.0, 2.0, -1.0],
[-0.5, 2.0, -0.5],
[-0.8, 3.0, -0.2],
[-1.0, 4.0, -0.2],
],
]).reshape((2, 4, 1, 3))
inp_biases = np.array([[[1, 5, 1], [2, 1, 2]], [[0, 3, 1], [4, 2, 1]]])
inp_biases = np.transpose(inp_biases, (1, 2, 0))
# rearrange to (kernel_rows, kernel_cols, in_channels, out_channels)
filters = np.transpose(filters, (2, 3, 0, 1))
inp_biases = inp_biases / (inp_biases.max() + 0.001)
# --- compute nengo_loihi outputs
ni, nj, nk = inp_biases.shape
si, sj, nc, nf = filters.shape
nij = ni * nj
nyi = 1 + (ni - si) // sti
nyj = 1 + (nj - sj) // stj
out_size = nyi * nyj * nf
assert out_size <= 1024
model = Model()
# input block
inp = LoihiBlock(ni * nj * nk, label="inp")
model.add_block(inp)
assert inp.n_neurons <= 1024
inp.compartment.configure_relu()
inp.compartment.bias[:] = inp_biases.ravel()
inp_ax = Axon(nij, label="inp_ax")
# we always compute the pixel/channel idxs with channels_last=True
# (not sure why?), and then set it to the correct value afterwards
inp_shape = make_channel_shape((ni, nj), nk, channels_last=True)
inp_ax.set_compartment_axon_map(target_axons=conv.pixel_idxs(inp_shape),
atoms=conv.channel_idxs(inp_shape))
inp_shape.shape = make_shape((ni, nj), nk, channels_last)
inp_shape.channels_last = channels_last
inp.add_axon(inp_ax)
# conv block
neurons = LoihiBlock(out_size, label="neurons")
model.add_block(neurons)
assert neurons.n_neurons <= 1024
neurons.compartment.configure_lif(tau_rc=tau_rc, tau_ref=tau_ref, dt=dt)
neurons.compartment.configure_filter(tau_s, dt=dt)
neurons.compartment.bias[:] = neuron_bias
synapse = Synapse(np.prod(inp_shape.spatial_shape), label="synapse")
conv2d_transform = nengo_transforms.Convolution(
nf,
inp_shape,
strides=(sti, stj),
channels_last=channels_last,
init=filters,
kernel_size=(1, 3),
)
weights, indices, axon_to_weight_map, bases = conv.conv2d_loihi_weights(
conv2d_transform)
synapse.set_population_weights(weights,
indices,
axon_to_weight_map,
bases,
pop_type=pop_type)
neurons.add_synapse(synapse)
out_probe = LoihiProbe(target=neurons, key="spiked")
model.add_probe(out_probe)
inp_ax.target = synapse
# simulation
discretize_model(model)
n_steps = int(pres_time / dt)
target = request.config.getoption("--target")
if target == "loihi":
with HardwareInterface(model, use_snips=False, seed=seed) as sim:
sim.run_steps(n_steps)
sim_out = sim.get_probe_output(out_probe)
else:
with EmulatorInterface(model, seed=seed) as sim:
sim.run_steps(n_steps)
sim_out = sim.get_probe_output(out_probe)
sim_out = np.sum(sim_out, axis=0) * (dt / pres_time)
sim_out.shape = make_shape((nyi, nyj), nf, channels_last)
if channels_last:
sim_out = np.transpose(sim_out, (2, 0, 1))
out_max = sim_out.max()
# --- plot results
rows = 1
cols = 2
ax = plt.subplot(rows, cols, 1)
plt.hist(sim_out.ravel(), bins=11)
ax = plt.subplot(rows, cols, 2)
tile(sim_out, vmin=0, vmax=out_max, grid=True, ax=ax)
# ref_out determined by emulator running code known to work
if nc == 1:
ref_out = np.array([[0.06, 0.02], [0.055, 0.0], [0.0825, 0.0225],
[0.125, 0.04]])
elif nc == 2:
ref_out = np.array([[0.0975, 0.02], [0.0825, 0.02], [0.125, 0.055],
[0.2475, 0.0825]])
assert allclose(sim_out[:, :, 0], ref_out, rtol=0, atol=1e-7)
def test_conv2d_weights(channels_last, request, plt, seed, rng, allclose):
def loihi_rates_n(neuron_type, x, gain, bias, dt):
"""Compute Loihi rates on higher dimensional inputs"""
y = x.reshape((-1, x.shape[-1]))
gain = np.asarray(gain)
bias = np.asarray(bias)
if gain.ndim == 0:
gain = gain * np.ones(x.shape[-1])
if bias.ndim == 0:
bias = bias * np.ones(x.shape[-1])
rates = loihi_rates(neuron_type, y, gain, bias, dt)
return rates.reshape(x.shape)
if channels_last:
plt.saveas = None
pytest.xfail("Blocked by CxBase cannot be > 256 bug")
target = request.config.getoption("--target")
pop_type = 32
# load data
with open(os.path.join(test_dir, "mnist10.pkl"), "rb") as f:
test10 = pickle.load(f)
test_x = test10[0][0].reshape((28, 28))
test_x = test_x[3:24, 3:24]
test_x = 1.999 * test_x - 0.999
filters = Gabor(freq=Uniform(0.5, 1)).generate(8, (7, 7), rng=rng)
sti, stj = 2, 2
tau_rc = 0.02
tau_ref = 0.002
tau_s = 0.005
dt = 0.001
encode_type = nengo.SpikingRectifiedLinear()
encode_gain = 1.0 / dt
encode_bias = 0.0
neuron_type = nengo.LIF(tau_rc=tau_rc, tau_ref=tau_ref)
neuron_gain = 1.0
neuron_bias = 1.0
pres_time = 0.2
# --- compute ideal outputs
def conv_pm(x, kernel):
y0 = scipy.signal.correlate2d(x[0], kernel, mode="valid")[::sti, ::stj]
y1 = scipy.signal.correlate2d(x[1], kernel, mode="valid")[::sti, ::stj]
return [y0, -y1]
ref_out = np.array([test_x, -test_x])
ref_out = loihi_rates_n(encode_type, ref_out, encode_gain, encode_bias, dt)
ref_out = ref_out / encode_gain
ref_out = np.array([conv_pm(ref_out, kernel) for kernel in filters])
ref_out = ref_out.sum(axis=1) # sum positive and negative parts
ref_out = loihi_rates_n(neuron_type, ref_out, neuron_gain, neuron_bias, dt)
# --- compute nengo_loihi outputs
inp_biases = np.stack([test_x, -test_x], axis=-1 if channels_last else 0)
inp_shape = nengo_transforms.ChannelShape(inp_biases.shape,
channels_last=channels_last)
kernel = np.array([filters, -filters]) # two channels, pos and neg
kernel = np.transpose(kernel, (2, 3, 0, 1))
conv2d_transform = nengo_transforms.Convolution(
8,
inp_shape,
strides=(sti, stj),
channels_last=channels_last,
kernel_size=(7, 7),
init=kernel,
)
out_size = ref_out.size
nf, nyi, nyj = ref_out.shape
assert out_size <= 1024
model = Model()
# input block
inp = LoihiBlock(inp_shape.size, label="inp")
model.add_block(inp)
assert inp.n_neurons <= 1024
inp.compartment.configure_relu()
inp.compartment.bias[:] = inp_biases.ravel()
inp_ax = Axon(np.prod(inp_shape.spatial_shape), label="inp_ax")
inp_ax.set_compartment_axon_map(target_axons=conv.pixel_idxs(inp_shape),
atoms=conv.channel_idxs(inp_shape))
inp.add_axon(inp_ax)
# conv block
neurons = LoihiBlock(out_size, label="neurons")
model.add_block(neurons)
assert neurons.n_neurons <= 1024
neurons.compartment.configure_lif(tau_rc=tau_rc, tau_ref=tau_ref, dt=dt)
neurons.compartment.configure_filter(tau_s, dt=dt)
neurons.compartment.bias[:] = neuron_bias
synapse = Synapse(np.prod(inp_shape.spatial_shape), label="synapse")
weights, indices, axon_to_weight_map, bases = conv.conv2d_loihi_weights(
conv2d_transform)
synapse.set_population_weights(weights,
indices,
axon_to_weight_map,
bases,
pop_type=pop_type)
neurons.add_synapse(synapse)
out_probe = LoihiProbe(target=neurons, key="spiked")
model.add_probe(out_probe)
inp_ax.target = synapse
# simulation
discretize_model(model)
n_steps = int(pres_time / dt)
if target == "loihi":
with HardwareInterface(
model,
use_snips=False,
seed=seed,
allocator=RoundRobin(),
) as sim:
sim.run_steps(n_steps)
sim_out = sim.get_probe_output(out_probe)
else:
with EmulatorInterface(model, seed=seed) as sim:
sim.run_steps(n_steps)
sim_out = sim.get_probe_output(out_probe)
sim_out = np.sum(sim_out, axis=0) / pres_time
sim_out.shape = make_shape((nyi, nyj), nf, channels_last)
if channels_last:
sim_out = np.transpose(sim_out, (2, 0, 1))
out_max = max(ref_out.max(), sim_out.max())
# --- plot results
rows = 2
cols = 2
ax = plt.subplot(rows, cols, 1)
tile(filters, cols=8, ax=ax)
ax = plt.subplot(rows, cols, 2)
tile(ref_out, vmin=0, vmax=out_max, cols=8, ax=ax)
ax = plt.subplot(rows, cols, 3)
plt.hist(ref_out.ravel(), bins=31)
plt.hist(sim_out.ravel(), bins=31)
ax = plt.subplot(rows, cols, 4)
# tile(sim_out, vmin=0, vmax=1, cols=8, ax=ax)
tile(sim_out, vmin=0, vmax=out_max, cols=8, ax=ax)
assert allclose(sim_out, ref_out, atol=12, rtol=1e-3)
def test_population_input(request, allclose):
target = request.config.getoption("--target")
dt = 0.001
n_inputs = 3
n_axons = 1
n_compartments = 2
steps = 6
spike_times_inds = [(1, [0]), (3, [1]), (5, [2])]
model = Model()
input = SpikeInput(n_inputs)
model.add_input(input)
spikes = [(input, ti, inds) for ti, inds in spike_times_inds]
input_axon = Axon(n_axons)
target_axons = np.zeros(n_inputs, dtype=int)
atoms = np.arange(n_inputs)
input_axon.set_compartment_axon_map(target_axons, atoms=atoms)
input.add_axon(input_axon)
block = LoihiBlock(n_compartments)
block.compartment.configure_lif(tau_rc=0.0, tau_ref=0.0, dt=dt)
block.compartment.configure_filter(0, dt=dt)
model.add_block(block)
synapse = Synapse(n_axons)
weights = 0.1 * np.array([[[1, 2], [2, 3], [4, 5]]], dtype=float)
indices = np.array([[[0, 1], [0, 1], [0, 1]]], dtype=int)
axon_to_weight_map = np.zeros(n_axons, dtype=int)
bases = np.zeros(n_axons, dtype=int)
synapse.set_population_weights(weights,
indices,
axon_to_weight_map,
bases,
pop_type=32)
block.add_synapse(synapse)
input_axon.target = synapse
probe = LoihiProbe(target=block, key="voltage")
model.add_probe(probe)
discretize_model(model)
if target == "loihi":
with HardwareInterface(model, use_snips=True) as sim:
sim.run_steps(steps, blocking=False)
for ti in range(1, steps + 1):
spikes_i = [spike for spike in spikes if spike[1] == ti]
sim.host2chip(spikes=spikes_i, errors=[])
sim.chip2host(probes_receivers={})
y = sim.get_probe_output(probe)
else:
for inp, ti, inds in spikes:
inp.add_spikes(ti, inds)
with EmulatorInterface(model) as sim:
sim.run_steps(steps)
y = sim.get_probe_output(probe)
vth = block.compartment.vth[0]
assert (block.compartment.vth == vth).all()
z = y / vth
assert allclose(z[[1, 3, 5]], weights[0], atol=4e-2, rtol=0)
def test_simulator_noise(exp, request, plt, seed, allclose):
# TODO: test that the mean falls within a number of standard errors
# of the expected mean, and that non-zero offsets work correctly.
# Currently, there is an unexpected negative bias for small noise
# exponents, apparently because there is a probability of generating
# the shifted equivalent of -128, whereas with e.g. exp = 7 all the
# generated numbers fall in [-127, 127].
offset = 0
target = request.config.getoption("--target")
n_compartments = 1000
model = Model()
block = LoihiBlock(n_compartments)
model.add_block(block)
block.compartment.configure_relu()
block.compartment.vmin = -1
block.compartment.enable_noise[:] = 1
block.compartment.noise_exp = exp
block.compartment.noise_offset = offset
block.compartment.noise_at_membrane = 1
probe = LoihiProbe(target=block, key="voltage")
model.add_probe(probe)
discretize_model(model)
exp2 = block.compartment.noise_exp
offset2 = block.compartment.noise_offset
n_steps = 100
if target == "loihi":
with HardwareInterface(model, use_snips=False, seed=seed) as sim:
sim.run_steps(n_steps)
y = sim.get_probe_output(probe)
else:
with EmulatorInterface(model, seed=seed) as sim:
sim.run_steps(n_steps)
y = sim.get_probe_output(probe)
t = np.arange(1, n_steps + 1)
bias = offset2 * 2.0**(exp2 - 1)
std = 2.0**exp2 / np.sqrt(3) # divide by sqrt(3) for std of uniform -1..1
rmean = t * bias
rstd = np.sqrt(t) * std
rerr = rstd / np.sqrt(n_compartments)
ymean = y.mean(axis=1)
ystd = y.std(axis=1)
diffs = np.diff(np.vstack([np.zeros_like(y[0]), y]), axis=0)
plt.subplot(311)
plt.hist(diffs.ravel(), bins=256)
plt.subplot(312)
plt.plot(rmean, "k")
plt.plot(rmean + 3 * rerr, "k--")
plt.plot(rmean - 3 * rerr, "k--")
plt.plot(ymean)
plt.title("mean")
plt.subplot(313)
plt.plot(rstd, "k")
plt.plot(ystd)
plt.title("std")
assert allclose(ystd, rstd, rtol=0.1, atol=1)
