def test_nengo_dl_noise(neuron_type, seed, plt):
install_dl_builders()
net, rates, lif_kw = rate_nengo_dl_net(neuron_type)
n_noise = 1000 # number of noise samples per x point
with nengo_dl.Simulator(net, dt=net.dt, minibatch_size=n_noise,
seed=seed) as sim:
input_data = {net.stim: np.tile(net.x[None, None, :], (n_noise, 1, 1))}
sim.step(input_feeds=input_data,
extra_feeds={sim.tensor_graph.signals.training: True})
y = sim.data[net.probe][:, 0, :]
ymean = y.mean(axis=0)
y25 = np.percentile(y, 25, axis=0)
y75 = np.percentile(y, 75, axis=0)
dy25 = y25 - rates["ref"]
dy75 = y75 - rates["ref"]
# exponential models roughly fitted to 25/75th percentiles
x1mask = net.x > 1.5
x1 = net.x[x1mask]
if isinstance(neuron_type.nengo_dl_noise, AlphaRCNoise):
exp_model = 0.7 + 2.8 * np.exp(-0.22 * (x1 - 1))
atol = 0.12 * exp_model.max()
elif isinstance(neuron_type.nengo_dl_noise, LowpassRCNoise):
exp_model = 1.5 + 2.2 * np.exp(-0.22 * (x1 - 1))
atol = 0.2 * exp_model.max()
rtol = 0.2
mu_atol = 0.6 # depends on n_noise and variance of noise
# --- plots
plt.subplot(211)
plt.plot(net.x, rates["med"], '--', label='LIF(tau_ref += 0.5*dt)')
plt.plot(net.x, ymean, label='nengo_dl')
plt.plot(net.x, y25, ':', label='25th')
plt.plot(net.x, y75, ':', label='75th')
plt.plot(net.x, rates["ref"], 'k--', label='LoihiLIF')
plt.legend()
plt.subplot(212)
plt.plot(net.x, ymean - rates["ref"], 'b', label='mean')
plt.plot(net.x, mu_atol * np.ones_like(net.x), 'b:')
plt.plot(net.x, -mu_atol * np.ones_like(net.x), 'b:')
plt.plot(net.x, y25 - rates["ref"], ':', label='25th')
plt.plot(net.x, y75 - rates["ref"], ':', label='75th')
plt.plot(x1, exp_model, 'k--')
plt.plot(x1, exp_model * (1 + rtol) + atol, 'k:')
plt.plot(x1, exp_model * (1 - rtol) - atol, 'k:')
plt.plot(x1, -exp_model, 'k--')
plt.legend()
assert ymean.shape == rates["ref"].shape
assert np.allclose(ymean, rates["ref"], atol=mu_atol)
assert np.allclose(dy25[x1mask], -exp_model, atol=atol, rtol=rtol)
assert np.allclose(dy75[x1mask], exp_model, atol=atol, rtol=rtol)
def test_nengo_dl_neurons(neuron_type, inference_only, Simulator, plt,
allclose):
install_dl_builders()
dt = 0.0007
n = 256
encoders = np.ones((n, 1))
gain = np.zeros(n)
if isinstance(neuron_type, nengo.SpikingRectifiedLinear):
bias = np.linspace(0, 1001, n)
else:
bias = np.linspace(0, 30, n)
with nengo.Network() as model:
nengo_dl.configure_settings(inference_only=inference_only)
a = nengo.Ensemble(n,
1,
neuron_type=neuron_type,
encoders=encoders,
gain=gain,
bias=bias)
ap = nengo.Probe(a.neurons)
t_final = 1.0
with nengo_dl.Simulator(model, dt=dt) as dl_sim:
dl_sim.run(t_final)
with Simulator(model, dt=dt) as loihi_sim:
loihi_sim.run(t_final)
rates_dlsim = (dl_sim.data[ap] > 0).sum(axis=0) / t_final
rates_loihisim = (loihi_sim.data[ap] > 0).sum(axis=0) / t_final
zeros = np.zeros((1, gain.size))
rates_ref = neuron_type.rates(zeros, gain, bias, dt=dt).squeeze(axis=0)
plt.plot(bias, rates_loihisim, 'r', label='loihi sim')
plt.plot(bias, rates_dlsim, 'b-.', label='dl sim')
plt.plot(bias, rates_ref, 'k--', label='rates_ref')
plt.legend(loc='best')
atol = 1. / t_final # the fundamental unit for our rates
assert rates_ref.shape == rates_dlsim.shape == rates_loihisim.shape
assert allclose(rates_dlsim, rates_ref, atol=atol, rtol=0, xtol=1)
assert allclose(rates_loihisim, rates_ref, atol=atol, rtol=0, xtol=1)
def __init__( # noqa: C901
self,
network,
dt=0.001,
seed=None,
model=None,
precompute=False,
target=None,
progress_bar=None,
remove_passthrough=True,
hardware_options=None,
):
# initialize values used in __del__ and close() first
self.closed = True
self.precompute = precompute
self.networks = None
self.sims = OrderedDict()
self._run_steps = None
hardware_options = {} if hardware_options is None else hardware_options
if progress_bar:
warnings.warn("nengo-loihi does not support progress bars")
if HAS_DL:
install_dl_builders()
if model is None:
# Call the builder to make a model
self.model = Model(dt=float(dt), label="%s, dt=%f" % (network, dt))
else:
assert isinstance(model, Model), (
"model is not type 'nengo_loihi.builder.Model'")
self.model = model
assert self.model.dt == dt
if network is not None:
nengo.rc.set("decoder_cache", "enabled", "False")
config.add_params(network)
# ensure seeds are identical to nengo
seed_network(network, seeds=self.model.seeds,
seeded=self.model.seeded)
# split the host into one, two or three networks
self.networks = split(
network,
precompute=precompute,
node_neurons=self.model.node_neurons,
node_tau=self.model.decode_tau,
remove_passthrough=remove_passthrough,
)
network = self.networks.chip
self.model.chip2host_params = self.networks.chip2host_params
self.chip = self.networks.chip
self.host = self.networks.host
self.host_pre = self.networks.host_pre
if len(self.host_pre.all_objects) > 0:
host_pre_model = self._get_host_model(
self.host_pre, dt=dt, seeds=self.model.seeds,
seeded=self.model.seeded)
self.sims["host_pre"] = nengo.Simulator(self.host_pre,
dt=self.dt,
model=host_pre_model,
progress_bar=False,
optimize=False)
if len(self.host.all_objects) > 0:
host_model = self._get_host_model(
self.host, dt=dt, seeds=self.model.seeds,
seeded=self.model.seeded)
self.sims["host"] = nengo.Simulator(
self.host,
dt=self.dt,
model=host_model,
progress_bar=False,
optimize=False)
elif not precompute:
# If there is no host and precompute=False, then all objects
# must be on the chip, which is precomputable in the sense that
# no communication has to happen with the host.
# We could warn about this, but we want to avoid people having
# to specify `precompute` unless they absolutely have to.
self.precompute = True
# Build the network into the model
self.model.build(network)
self._probe_outputs = self.model.params
self.data = ProbeDict(self._probe_outputs)
for sim in self.sims.values():
self.data.add_fallback(sim.data)
if seed is None:
if network is not None and network.seed is not None:
seed = network.seed + 1
else:
seed = np.random.randint(npext.maxint)
if target is None:
target = 'loihi' if HAS_NXSDK else 'sim'
self.target = target
logger.info("Simulator target is %r", target)
logger.info("Simulator precompute is %r", self.precompute)
if target != "simreal":
discretize_model(self.model)
if target in ("simreal", "sim"):
self.sims["emulator"] = EmulatorInterface(self.model, seed=seed)
elif target == 'loihi':
assert HAS_NXSDK, "Must have NxSDK installed to use Loihi hardware"
self.sims["loihi"] = HardwareInterface(
self.model, use_snips=not self.precompute, seed=seed,
**hardware_options)
else:
raise ValidationError("Must be 'simreal', 'sim', or 'loihi'",
attr="target")
assert "emulator" in self.sims or "loihi" in self.sims
self.closed = False
self.reset(seed=seed)
def test_nengo_dl_neuron_grads(neuron_type, plt):
from nengo_extras.neurons import SoftLIFRate
import tensorflow as tf
from tensorflow.python.ops import gradient_checker
install_dl_builders()
net, rates, lif_kw = rate_nengo_dl_net(neuron_type)
with nengo_dl.Simulator(net, dt=net.dt) as sim:
sim.run_steps(1,
input_feeds={net.stim: net.x[None, None, :]},
extra_feeds={sim.tensor_graph.signals.training: True})
y = sim.data[net.probe][0]
# --- compute spiking rates
n_spike_steps = 1000
x_spikes = net.x + np.zeros((1, n_spike_steps, 1), dtype=net.x.dtype)
with nengo_dl.Simulator(net, dt=net.dt) as sim:
sim.run_steps(n_spike_steps,
input_feeds={net.stim: x_spikes},
extra_feeds={sim.tensor_graph.signals.training: False})
y_spikes = sim.data[net.probe]
y_spikerate = y_spikes.mean(axis=0)
# --- compute derivatives
if isinstance(neuron_type, LoihiLIF):
dy_ref = SoftLIFRate(sigma=net.sigma,
**lif_kw).derivative(net.x, net.gain, net.bias)
else:
# use the derivative of rates['med'] (the smoothed Loihi tuning curve)
dy_ref = np.zeros_like(net.j)
dy_ref[net.j > 0] = (neuron_type.amplitude /
(net.j[net.j > 0] * net.tau_ref1 + 1)**2)
with nengo_dl.Simulator(net, dt=net.dt) as sim:
n_steps = sim.unroll
assert n_steps == 1
inp = sim.tensor_graph.input_ph[net.stim]
inp_shape = inp.get_shape().as_list()
inp_shape = [n_steps if s is None else s for s in inp_shape]
inp_data = np.zeros(inp_shape) + net.x[None, :, None]
out = sim.tensor_graph.probe_arrays[net.probe] + 0
out_shape = out.get_shape().as_list()
out_shape = [n_steps if s is None else s for s in out_shape]
data = {
n: np.zeros((sim.minibatch_size, n_steps, n.size_out))
for n in sim.tensor_graph.invariant_inputs
}
data.update({
p: np.zeros((sim.minibatch_size, n_steps, p.size_in))
for p in sim.tensor_graph.target_phs
})
feed = sim._fill_feed(n_steps, data, training=True)
with tf.variable_scope(tf.get_variable_scope()) as scope:
dx, dy = gradient_checker._compute_dx_and_dy(inp, out, out_shape)
sim.sess.run(
tf.variables_initializer(
scope.get_collection("gradient_vars")))
with sim.sess.as_default():
analytic = gradient_checker._compute_theoretical_jacobian(
inp,
inp_shape,
inp_data,
dy,
out_shape,
dx,
extra_feed_dict=feed)
dy = np.array(np.diag(analytic))
dx = net.x[1] - net.x[0]
dy_est = np.diff(nengo.synapses.Alpha(10).filtfilt(rates["ref"],
dt=1)) / dx
x1 = 0.5 * (net.x[:-1] + net.x[1:])
# --- plots
plt.subplot(211)
plt.plot(net.x, rates["med"], '--', label='LIF(tau_ref += 0.5*dt)')
plt.plot(net.x, y, label='nengo_dl')
plt.plot(net.x, y_spikerate, label='nengo_dl spikes')
plt.plot(net.x, rates["ref"], 'k--', label='LoihiLIF')
plt.legend(loc=4)
plt.subplot(212)
plt.plot(x1, dy_est, '--', label='diff(smoothed_y)')
plt.plot(net.x, dy, label='nengo_dl')
plt.plot(net.x, dy_ref, 'k--', label='diff(SoftLIF)')
plt.legend(loc=1)
np.fill_diagonal(analytic, 0)
assert np.all(analytic == 0)
assert np.allclose(y, rates["ref"], atol=1e-3, rtol=1e-5)
assert np.allclose(dy, dy_ref, atol=1e-3, rtol=1e-5)
assert np.allclose(y_spikerate, rates["ref"], atol=1, rtol=1e-2)
def _install_dl_builders():
# avoid circular import by doing import in here
from nengo_loihi.builder.nengo_dl import ( # pylint: disable=import-outside-toplevel
install_dl_builders, )
install_dl_builders()
def test_nengo_dl_noise(neuron_type, seed, plt):
tf = pytest.importorskip("tensorflow")
install_dl_builders()
net, rates, lif_kw = rate_nengo_dl_net(neuron_type)
n_noise = 1000 # number of noise samples per x point
with tf.keras.backend.learning_phase_scope(1):
with nengo_dl.Simulator(net,
dt=net.dt,
minibatch_size=n_noise,
seed=seed) as sim:
input_data = {
net.stim: np.tile(net.x[None, None, :], (n_noise, 1, 1))
}
sim.step(data=input_data)
y = sim.data[net.probe][:, 0, :]
ymean = y.mean(axis=0)
y25 = np.percentile(y, 25, axis=0)
y75 = np.percentile(y, 75, axis=0)
dy25 = y25 - rates["ref"]
dy75 = y75 - rates["ref"]
# exponential models roughly fitted to 25/75th percentiles
x1mask = net.x > 1.5
x1 = net.x[x1mask]
if isinstance(neuron_type.nengo_dl_noise, AlphaRCNoise):
exp_model = 0.7 + 2.8 * np.exp(-0.22 * (x1 - 1))
atol = 0.12 * exp_model.max()
elif isinstance(neuron_type.nengo_dl_noise, LowpassRCNoise):
exp_model = 1.5 + 2.2 * np.exp(-0.22 * (x1 - 1))
atol = 0.2 * exp_model.max()
rtol = 0.2
mu_atol = 0.6 # depends on n_noise and variance of noise
# --- plots
plt.subplot(211)
plt.plot(net.x, rates["med"], "--", label="LIF(tau_ref += 0.5*dt)")
plt.plot(net.x, ymean, label="nengo_dl")
plt.plot(net.x, y25, ":", label="25th")
plt.plot(net.x, y75, ":", label="75th")
plt.plot(net.x, rates["ref"], "k--", label="LoihiLIF")
plt.legend()
plt.subplot(212)
plt.plot(net.x, ymean - rates["ref"], "b", label="mean")
plt.plot(net.x, mu_atol * np.ones_like(net.x), "b:")
plt.plot(net.x, -mu_atol * np.ones_like(net.x), "b:")
plt.plot(net.x, y25 - rates["ref"], ":", label="25th")
plt.plot(net.x, y75 - rates["ref"], ":", label="75th")
plt.plot(x1, exp_model, "k--")
plt.plot(x1, exp_model * (1 + rtol) + atol, "k:")
plt.plot(x1, exp_model * (1 - rtol) - atol, "k:")
plt.plot(x1, -exp_model, "k--")
plt.legend()
assert ymean.shape == rates["ref"].shape
assert np.allclose(ymean, rates["ref"], atol=mu_atol)
assert np.allclose(dy25[x1mask], -exp_model, atol=atol, rtol=rtol)
assert np.allclose(dy75[x1mask], exp_model, atol=atol, rtol=rtol)
def test_nengo_dl_neuron_grads(neuron_type, plt):
tf = pytest.importorskip("tensorflow")
install_dl_builders()
net, rates, lif_kw = rate_nengo_dl_net(neuron_type)
with tf.keras.backend.learning_phase_scope(1):
with nengo_dl.Simulator(net, dt=net.dt) as sim:
sim.run_steps(1, data={net.stim: net.x[None, None, :]})
y = sim.data[net.probe][0]
# --- compute spiking rates
n_spike_steps = 1000
x_spikes = net.x + np.zeros((1, n_spike_steps, 1), dtype=net.x.dtype)
with nengo_dl.Simulator(net, dt=net.dt) as sim:
sim.run_steps(
n_spike_steps,
data={net.stim: x_spikes},
)
y_spikes = sim.data[net.probe]
y_spikerate = y_spikes.mean(axis=0)
# --- compute derivatives
if isinstance(neuron_type, LoihiLIF):
dy_ref = SoftLIFRate(sigma=net.sigma,
**lif_kw).derivative(net.x, net.gain, net.bias)
else:
# use the derivative of rates['med'] (the smoothed Loihi tuning curve)
dy_ref = np.zeros_like(net.j)
dy_ref[net.j > 0] = (neuron_type.amplitude /
(net.j[net.j > 0] * net.tau_ref1 + 1)**2)
with nengo_dl.Simulator(net, dt=net.dt) as sim:
assert sim.unroll == 1
# note: not actually checking gradients, just using this to get the
# gradients
analytic = sim.check_gradients(inputs=[net.x[None, None, :]],
atol=1e10)[net.probe]["analytic"][0]
dy = np.diagonal(analytic.copy())
dx = net.x[1] - net.x[0]
dy_est = np.diff(nengo.synapses.Alpha(10).filtfilt(rates["ref"],
dt=1)) / dx
x1 = 0.5 * (net.x[:-1] + net.x[1:])
# --- plots
plt.subplot(211)
plt.plot(net.x, rates["med"], "--", label="LIF(tau_ref += 0.5*dt)")
plt.plot(net.x, y, label="nengo_dl")
plt.plot(net.x, y_spikerate, label="nengo_dl spikes")
plt.plot(net.x, rates["ref"], "k--", label="LoihiLIF")
plt.legend(loc=4)
plt.subplot(212)
plt.plot(x1, dy_est, "--", label="diff(smoothed_y)")
plt.plot(net.x, dy, label="nengo_dl")
plt.plot(net.x, dy_ref, "k--", label="diff(SoftLIF)")
plt.legend(loc=1)
np.fill_diagonal(analytic, 0)
assert np.all(analytic == 0)
assert y.shape == rates["ref"].shape
assert np.allclose(y, rates["ref"], atol=1e-3, rtol=1e-5)
assert np.allclose(dy, dy_ref, atol=1e-3, rtol=1e-5)
assert np.allclose(y_spikerate, rates["ref"], atol=1, rtol=1e-2)
