def test_mnist_pipeline(self):
network = DiehlAndCook2015(n_inpt=784, n_neurons=400, exc=22.5, inh=17.5, dt=1.0, norm=78.4)
environment = DatasetEnvironment(dataset=MNIST(path='../data/MNIST', download=True), train=True, intensity=0.25)
pipeline = Pipeline(network=network, environment=environment, encoding=poisson, time=350)
assert pipeline.network == network
assert pipeline.env == environment
assert pipeline.encoding == poisson
assert pipeline.time == 350
assert pipeline.history_length is None
network = DiehlAndCook2015(n_input=32 * 32 * 3,
n_neurons=100,
dt=1.0,
exc=22.5,
inh=17.5,
nu=[0, 1e-2],
norm=78.4)
# Specify dataset wrapper environment.
environment = DatasetEnvironment(dataset=CIFAR10(path='../../data/CIFAR10'),
train=True)
# Build pipeline from components.
pipeline = Pipeline(network=network,
environment=environment,
encoding=poisson,
time=50,
plot_interval=1)
# Train the network.
labels = environment.labels
for i in range(60000):
# Choose an output neuron to clamp to spiking behavior.
c = choice(10, size=1, replace=False)
c = 10 * labels[i].long() + Tensor(c).long()
clamp = torch.zeros(pipeline.time, network.n_neurons, dtype=torch.uint8)
clamp[:, c] = 1
clamp_v = torch.zeros(pipeline.time, network.n_neurons, dtype=torch.float)
clamp_v[:, c] = network.layers['Ae'].thresh + network.layers['Ae'].theta[
c] + 10
network.add_connection(input_exc_conn, source='X', target='E')
network.add_connection(exc_readout_conn, source='E', target='R')
# Add all monitors to the network.
for layer in layers:
network.add_monitor(spikes[layer], name='%s_spikes' % layer)
if layer in voltages:
network.add_monitor(voltages[layer], name='%s_voltages' % layer)
# Load SpaceInvaders environment.
environment = GymEnvironment('Asteroids-v0')
environment.reset()
pipeline = Pipeline(network, environment, encoding=bernoulli, time=1, history=5, delta=10, plot_interval=plot_interval,
print_interval=print_interval, render_interval=render_interval, action_function=select_multinomial,
output='R')
total = 0
rewards = []
avg_rewards = []
lengths = []
avg_lengths = []
i = 0
try:
while i < n:
pipeline.step()
if pipeline.done:
pipeline.reset_()
norm=0.15 * middle.n)
# Add all layers and connections to the network.
network.add_layer(inpt, name='X')
network.add_layer(middle, name='Y')
network.add_layer(out, name='Z')
network.add_connection(inpt_middle, source='X', target='Y')
network.add_connection(middle_out, source='Y', target='Z')
# Load SpaceInvaders environment.
environment = GymEnvironment('SpaceInvaders-v0')
environment.reset()
# Build pipeline from specified components.
pipeline = Pipeline(network,
environment,
encoding=bernoulli,
feedback=select_multinomial,
output='Z',
time=1,
history_length=2,
delta=4,
plot_interval=100,
render_interval=5)
# Run environment simulation and network training.
while True:
pipeline.step()
if pipeline.done == True:
pipeline._reset()
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer], state_vars=['s'], time=time)
network.add_monitor(spikes[layer], name='%s_spikes' % layer)
voltages = {}
for layer in set(network.layers) - {'X'}:
voltages[layer] = Monitor(network.layers[layer],
state_vars=['v'],
time=time)
network.add_monitor(voltages[layer], name='%s_voltages' % layer)
# Build pipeline from above-specified components.
pipeline = Pipeline(network=network,
environment=environment,
encoding=encoding,
time=time,
plot_interval=1)
# Neuron assignments and spike proportions.
assignments = -torch.ones_like(torch.Tensor(n_neurons))
proportions = torch.zeros_like(torch.Tensor(n_neurons, 10))
rates = torch.zeros_like(torch.Tensor(n_neurons, 10))
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
# Get data labels.
labels = pipeline.env.labels
# Sequence of accuracy estimates.
from bindsnet.encoding import poisson from bindsnet.pipeline import Pipeline from bindsnet.models import DiehlAndCook2015 from bindsnet.environment import DatasetEnvironment # Build Diehl & Cook 2015 network. network = DiehlAndCook2015(n_inpt=784, n_neurons=400, exc=22.5, inh=17.5, dt=1.0, norm=78.4) # Specify dataset wrapper environment. environment = DatasetEnvironment(dataset=MNIST(path='../../data/MNIST'), train=True, download=True, intensity=0.25) # Build pipeline from components. pipeline = Pipeline(network=network, environment=environment, encoding=poisson, time=350, plot_interval=1) # Train the network. for i in range(60000): pipeline.step() network._reset()
target="Hidden Layer")
network.add_connection(middle_out,
source="Hidden Layer",
target="Output Layer")
# Load SpaceInvaders environment.
environment = GymEnvironment("BreakoutDeterministic-v4")
environment.reset()
# Build pipeline from specified components.
pipeline = Pipeline(
network,
environment,
encoding=bernoulli,
action_function=select_softmax,
output="Output Layer",
time=100,
history_length=1,
delta=1,
plot_interval=1,
render_interval=1,
)
# Train agent for 100 episodes.
print("Training: ")
for i in range(100):
pipeline.reset_()
# initialize episode reward
reward = 0
while True:
pipeline.step()
reward += pipeline.reward
def main(seed=0, n_neurons=100, n_train=60000, n_test=10000, inhib=100, lr=0.01, lr_decay=1, time=350, dt=1,
theta_plus=0.05, theta_decay=1e-7, progress_interval=10, update_interval=250, plot=False,
train=True, gpu=False):
assert n_train % update_interval == 0 and n_test % update_interval == 0, \
'No. examples must be divisible by update_interval'
params = [
seed, n_neurons, n_train, inhib, lr_decay, time, dt,
theta_plus, theta_decay, progress_interval, update_interval
]
model_name = '_'.join([str(x) for x in params])
np.random.seed(seed)
if gpu:
torch.set_default_tensor_type('torch.cuda.FloatTensor')
torch.cuda.manual_seed_all(seed)
else:
torch.manual_seed(seed)
n_examples = n_train if train else n_test
n_classes = 10
# Build network.
if train:
network = Network(dt=dt)
input_layer = Input(n=784, traces=True, trace_tc=5e-2)
network.add_layer(input_layer, name='X')
output_layer = DiehlAndCookNodes(
n=n_classes, rest=0, reset=1, thresh=1, decay=1e-2,
theta_plus=theta_plus, theta_decay=theta_decay, traces=True, trace_tc=5e-2
)
network.add_layer(output_layer, name='Y')
w = torch.rand(784, n_classes)
input_connection = Connection(
source=input_layer, target=output_layer, w=w,
update_rule=MSTDPET, nu=lr, wmin=0, wmax=1,
norm=78.4, tc_e_trace=0.1
)
network.add_connection(input_connection, source='X', target='Y')
else:
network = load(os.path.join(params_path, model_name + '.pt'))
network.connections['X', 'Y'].update_rule = NoOp(
connection=network.connections['X', 'Y'], nu=network.connections['X', 'Y'].nu
)
network.layers['Y'].theta_decay = torch.IntTensor([0])
network.layers['Y'].theta_plus = torch.IntTensor([0])
# Load MNIST data.
environment = MNISTEnvironment(
dataset=MNIST(root=data_path, download=True), train=train, time=time
)
# Create pipeline.
pipeline = Pipeline(
network=network, environment=environment, encoding=repeat,
action_function=select_spiked, output='Y', reward_delay=None
)
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer], state_vars=('s',), time=time)
network.add_monitor(spikes[layer], name='%s_spikes' % layer)
if train:
network.add_monitor(Monitor(
network.connections['X', 'Y'].update_rule, state_vars=('tc_e_trace',), time=time
), 'X_Y_e_trace')
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
spike_ims = None
spike_axes = None
weights_im = None
elig_axes = None
elig_ims = None
start = t()
for i in range(n_examples):
if i % progress_interval == 0:
print(f'Progress: {i} / {n_examples} ({t() - start:.4f} seconds)')
start = t()
if i > 0 and train:
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
# Run the network on the input.
# print("Example",i,"Results:")
# for j in range(time):
# result = pipeline.env_step()
# pipeline.step(result,a_plus=1, a_minus=0)
# print(result)
for j in range(time):
pipeline.train()
if not train:
_spikes = {layer: spikes[layer].get('s') for layer in spikes}
if plot:
_spikes = {layer: spikes[layer].get('s') for layer in spikes}
w = network.connections['X', 'Y'].w
square_weights = get_square_weights(w.view(784, n_classes), 4, 28)
spike_ims, spike_axes = plot_spikes(_spikes, ims=spike_ims, axes=spike_axes)
weights_im = plot_weights(square_weights, im=weights_im)
elig_ims, elig_axes = plot_voltages(
{'Y': network.monitors['X_Y_e_trace'].get('e_trace').view(-1, time)[1500:2000]},
plot_type='line', ims=elig_ims, axes=elig_axes
)
plt.pause(1e-8)
pipeline.reset_state_variables() # Reset state variables.
network.connections['X', 'Y'].update_rule.tc_e_trace = torch.zeros(784, n_classes)
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
if train:
network.save(os.path.join(params_path, model_name + '.pt'))
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
def test_gym_pipeline(self):
# Build network.
network = Network(dt=1.0)
# Layers of neurons.
inpt = Input(n=6552, traces=True)
middle = LIFNodes(n=225, traces=True, thresh=-52.0 + torch.randn(225))
out = LIFNodes(n=60, refrac=0, traces=True, thresh=-40.0)
# Connections between layers.
inpt_middle = Connection(source=inpt, target=middle, wmax=1e-2)
middle_out = Connection(source=middle,
target=out,
wmax=0.5,
update_rule=m_stdp_et,
nu=2e-2,
norm=0.15 * middle.n)
# Add all layers and connections to the network.
network.add_layer(inpt, name='X')
network.add_layer(middle, name='Y')
network.add_layer(out, name='Z')
network.add_connection(inpt_middle, source='X', target='Y')
network.add_connection(middle_out, source='Y', target='Z')
# Load SpaceInvaders environment.
environment = GymEnvironment('SpaceInvaders-v0')
environment.reset()
# Build pipeline from specified components.
for history_length in [3, 4, 5, 6]:
for delta in [2, 3, 4]:
p = Pipeline(network,
environment,
encoding=bernoulli,
action_function=select_multinomial,
output='Z',
time=1,
history_length=history_length,
delta=delta)
assert p.action_function == select_multinomial
assert p.history_length == history_length
assert p.delta == delta
# Checking assertion errors
for time in [0, -1]:
try:
p = Pipeline(network,
environment,
encoding=bernoulli,
action_function=select_multinomial,
output='Z',
time=time,
history_length=2,
delta=4)
except ValueError:
pass
for delta in [0, -1]:
try:
p = Pipeline(network,
environment,
encoding=bernoulli,
action_function=select_multinomial,
output='Z',
time=time,
history_length=2,
delta=delta)
except ValueError:
pass
for output in ['K']:
try:
p = Pipeline(network,
environment,
encoding=bernoulli,
action_function=select_multinomial,
output=output,
time=time,
history_length=2,
delta=4)
except ValueError:
pass
p = Pipeline(network,
environment,
encoding=bernoulli,
action_function=select_random,
output='Z',
time=1,
history_length=2,
delta=4,
save_interval=50,
render_interval=5)
assert p.action_function == select_random
assert p.encoding == bernoulli
assert p.save_interval == 50
assert p.render_interval == 5
assert p.time == 1
def test_MNIST_pipeline(self):
network = DiehlAndCook2015(n_inpt=784,
n_neurons=400,
exc=22.5,
inh=17.5,
dt=1.0,
norm=78.4)
environment = DatasetEnvironment(dataset=MNIST(path='../../data/MNIST',
download=True),
train=True,
intensity=0.25)
p = Pipeline(network=network,
environment=environment,
encoding=poisson,
time=350)
assert p.network == network
assert p.env == environment
assert p.encoding == poisson
assert p.time == 350
assert p.history_length is None
def test_Gym_pipeline(self):
# Build network.
network = Network(dt=1.0)
# Layers of neurons.
inpt = Input(n=6552, traces=True)
middle = LIFNodes(n=225,
traces=True,
thresh=-52.0 + torch.randn(225))
out = LIFNodes(n=60, refrac=0, traces=True, thresh=-40.0)
# Connections between layers.
inpt_middle = Connection(source=inpt, target=middle, wmax=1e-2)
middle_out = Connection(source=middle,
target=out,
wmax=0.5,
update_rule=m_stdp_et,
nu=2e-2,
norm=0.15 * middle.n)
# Add all layers and connections to the network.
network.add_layer(inpt, name='X')
network.add_layer(middle, name='Y')
network.add_layer(out, name='Z')
network.add_connection(inpt_middle, source='X', target='Y')
network.add_connection(middle_out, source='Y', target='Z')
# Load SpaceInvaders environment.
environment = GymEnvironment('SpaceInvaders-v0')
environment.reset()
# Build pipeline from specified components.
for history_length in [3, 4, 5, 6]:
for delta in [2, 3, 4]:
p = Pipeline(network,
environment,
encoding=bernoulli,
feedback=select_multinomial,
output='Z',
time=1,
history_length=2,
delta=4)
assert p.feedback == select_multinomial
assert p.history_length == history_length
assert p.delta == delta
# Checking assertion errors
for time in [0, -1]:
try:
p = Pipeline(network,
environment,
encoding=bernoulli,
feedback=select_multinomial,
output='Z',
time=time,
history_length=2,
delta=4)
except Exception as es:
assert es == AssertionError
for delta in [0, -1]:
try:
p = Pipeline(network,
environment,
encoding=bernoulli,
feedback=select_multinomial,
output='Z',
time=time,
history_length=2,
delta=delta)
except Exception as es:
assert es == AssertionError
for output in ['K']:
try:
p = Pipeline(network,
environment,
encoding=bernoulli,
feedback=select_multinomial,
output=output,
time=time,
history_length=2,
delta=4)
except Exception as es:
assert es == AssertionError
p = Pipeline(network,
environment,
encoding=bernoulli,
feedback=select_random,
output='Z',
time=1,
history_length=2,
delta=4,
save_interval=50,
render_interval=5)
assert p.feedback == select_random
assert p.encoding == bernoulli
assert p.save_interval == 50
assert p.render_interval == 5
assert p.time == 1