def main(seed=0,
n_neurons=100,
n_train=60000,
n_test=10000,
inhib=100,
lr=1e-2,
lr_decay=1,
time=350,
dt=1,
theta_plus=0.05,
theta_decay=1e7,
intensity=1,
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, lr_decay, time, dt, theta_plus,
theta_decay, intensity, progress_interval, update_interval
]
test_params = [
seed, n_neurons, n_train, n_test, inhib, lr, lr_decay, time, dt,
theta_plus, theta_decay, intensity, 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_sqrt = int(np.ceil(np.sqrt(n_neurons)))
n_classes = 10
# Build network.
if train:
network = DiehlAndCook2015v2(n_inpt=784,
n_neurons=n_neurons,
inh=inhib,
dt=dt,
norm=78.4,
theta_plus=theta_plus,
theta_decay=theta_decay,
nu=[0, lr])
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 = 0
network.layers['Y'].theta_plus = 0
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images = images.view(-1, 784)
images *= intensity
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
full_spike_record = torch.zeros(n_examples, n_neurons).long()
# Neuron assignments and spike proportions.
if train:
assignments = -torch.ones_like(torch.Tensor(n_neurons))
proportions = torch.zeros_like(torch.Tensor(n_neurons, n_classes))
rates = torch.zeros_like(torch.Tensor(n_neurons, n_classes))
ngram_scores = {}
else:
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
assignments, proportions, rates, ngram_scores = torch.load(
open(path, 'rb'))
# Sequence of accuracy estimates.
curves = {'all': [], 'proportion': [], 'ngram': []}
predictions = {scheme: torch.Tensor().long() for scheme in curves.keys()}
if train:
best_accuracy = 0
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)
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
inpt_axes = None
inpt_ims = None
spike_ims = None
spike_axes = None
weights_im = None
assigns_im = None
perf_ax = 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 % update_interval == 0 and i > 0:
if train:
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i %
len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
spike_record=spike_record,
assignments=assignments,
proportions=proportions,
ngram_scores=ngram_scores,
n=2)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat(
[predictions[scheme], preds[scheme]], -1)
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print(
'New best accuracy! Saving network parameters to disk.'
)
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(
params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores),
open(path, 'wb'))
best_accuracy = max([x[-1] for x in curves.values()])
# Assign labels to excitatory layer neurons.
assignments, proportions, rates = assign_labels(
spike_record, current_labels, n_classes, rates)
# Compute ngram scores.
ngram_scores = update_ngram_scores(spike_record,
current_labels, n_classes,
2, ngram_scores)
print()
# Get next input sample.
image = images[i % len(images)]
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
retries = 0
while spikes['Y'].get('s').sum() < 1 and retries < 3:
retries += 1
image *= 2
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
network.run(inpts=inpts, time=time)
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y'].get('s').t()
full_spike_record[i] = spikes['Y'].get('s').t().sum(0).long()
# Optionally plot various simulation information.
if plot:
# _input = image.view(28, 28)
# reconstruction = inpts['X'].view(time, 784).sum(0).view(28, 28)
_spikes = {layer: spikes[layer].get('s') for layer in spikes}
input_exc_weights = network.connections[('X', 'Y')].w
square_weights = get_square_weights(
input_exc_weights.view(784, n_neurons), n_sqrt, 28)
# square_assignments = get_square_assignments(assignments, n_sqrt)
# inpt_axes, inpt_ims = plot_input(_input, reconstruction, label=labels[i], axes=inpt_axes, ims=inpt_ims)
spike_ims, spike_axes = plot_spikes(_spikes,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_weights(square_weights, im=weights_im)
# assigns_im = plot_assignments(square_assignments, im=assigns_im)
# perf_ax = plot_performance(curves, ax=perf_ax)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i %
len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
spike_record=spike_record,
assignments=assignments,
proportions=proportions,
ngram_scores=ngram_scores,
n=2)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]],
-1)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
if train:
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(
params_path, '_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores),
open(path, 'wb'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print('Average accuracies:\n')
for scheme in curves.keys():
print('\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
# Save results to disk.
results = [
np.mean(curves['all']),
np.mean(curves['proportion']),
np.mean(curves['ngram']),
np.max(curves['all']),
np.max(curves['proportion']),
np.max(curves['ngram'])
]
to_write = params + results if train else test_params + results
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write(
'random_seed,n_neurons,n_train,inhib,lr,lr_decay,time,timestep,theta_plus,theta_decay,intensity,'
'progress_interval,update_interval,mean_all_activity,mean_proportion_weighting,'
'mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n'
)
else:
f.write(
'random_seed,n_neurons,n_train,n_test,inhib,lr,lr_decay,time,timestep,theta_plus,theta_decay,'
'intensity,progress_interval,update_interval,mean_all_activity,mean_proportion_weighting,'
'mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat(
[labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusions = {}
for scheme in predictions:
confusions[scheme] = confusion_matrix(labels, predictions[scheme])
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusions, os.path.join(confusion_path, f))
# Save full spike record to disk.
torch.save(full_spike_record, os.path.join(spikes_path, f))
def main(seed=0,
n_train=60000,
n_test=10000,
kernel_size=(16, ),
stride=(4, ),
n_filters=25,
padding=0,
inhib=100,
time=25,
lr=1e-3,
lr_decay=0.99,
dt=1,
intensity=1,
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_train, kernel_size, stride, n_filters, padding, inhib, time,
lr, lr_decay, dt, intensity, update_interval
]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, n_train, n_test, kernel_size, stride, n_filters, padding,
inhib, time, lr, lr_decay, dt, intensity, update_interval
]
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
input_shape = [20, 20]
if kernel_size == input_shape:
conv_size = [1, 1]
else:
conv_size = (int((input_shape[0] - kernel_size[0]) / stride[0]) + 1,
int((input_shape[1] - kernel_size[1]) / stride[1]) + 1)
n_classes = 10
n_neurons = n_filters * np.prod(conv_size)
total_kernel_size = int(np.prod(kernel_size))
total_conv_size = int(np.prod(conv_size))
# Build network.
if train:
network = Network()
input_layer = Input(n=400, shape=(1, 1, 20, 20), traces=True)
conv_layer = DiehlAndCookNodes(n=n_filters * total_conv_size,
shape=(1, n_filters, *conv_size),
thresh=-64.0,
traces=True,
theta_plus=0.05 * (kernel_size[0] / 20),
refrac=0)
conv_layer2 = LIFNodes(n=n_filters * total_conv_size,
shape=(1, n_filters, *conv_size),
refrac=0)
conv_conn = Conv2dConnection(input_layer,
conv_layer,
kernel_size=kernel_size,
stride=stride,
update_rule=WeightDependentPostPre,
norm=0.05 * total_kernel_size,
nu=[0, lr],
wmin=0,
wmax=0.25)
conv_conn2 = Conv2dConnection(input_layer,
conv_layer2,
w=conv_conn.w,
kernel_size=kernel_size,
stride=stride,
update_rule=None,
wmax=0.25)
w = -inhib * torch.ones(n_filters, conv_size[0], conv_size[1],
n_filters, conv_size[0], conv_size[1])
for f in range(n_filters):
for f2 in range(n_filters):
if f != f2:
w[f, :, :f2, :, :] = 0
w = w.view(n_filters * conv_size[0] * conv_size[1],
n_filters * conv_size[0] * conv_size[1])
recurrent_conn = Connection(conv_layer, conv_layer, w=w)
network.add_layer(input_layer, name='X')
network.add_layer(conv_layer, name='Y')
network.add_layer(conv_layer2, name='Y_')
network.add_connection(conv_conn, source='X', target='Y')
network.add_connection(conv_conn2, source='X', target='Y_')
network.add_connection(recurrent_conn, source='Y', target='Y')
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
else:
network = load_network(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 = 0
network.layers['Y'].theta_plus = 0
# Load MNIST data.
dataset = MNIST(data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images *= intensity
images = images[:, 4:-4, 4:-4].contiguous()
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
full_spike_record = torch.zeros(n_examples, n_neurons)
# Neuron assignments and spike proportions.
if train:
logreg_model = LogisticRegression(warm_start=True,
n_jobs=-1,
solver='lbfgs',
max_iter=1000,
multi_class='multinomial')
logreg_model.coef_ = np.zeros([n_classes, n_neurons])
logreg_model.intercept_ = np.zeros(n_classes)
logreg_model.classes_ = np.arange(n_classes)
else:
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
logreg_coef, logreg_intercept = torch.load(open(path, 'rb'))
logreg_model = LogisticRegression(warm_start=True,
n_jobs=-1,
solver='lbfgs',
max_iter=1000,
multi_class='multinomial')
logreg_model.coef_ = logreg_coef
logreg_model.intercept_ = logreg_intercept
logreg_model.classes_ = np.arange(n_classes)
# Sequence of accuracy estimates.
curves = {'logreg': []}
predictions = {scheme: torch.Tensor().long() for scheme in curves.keys()}
if train:
best_accuracy = 0
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)
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
inpt_ims = None
inpt_axes = None
spike_ims = None
spike_axes = None
weights_im = None
plot_update_interval = 100
start = t()
for i in range(n_examples):
if i % progress_interval == 0:
print('Progress: %d / %d (%.4f seconds)' %
(i, n_examples, t() - start))
start = t()
if i % update_interval == 0 and i > 0:
if train:
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
current_record = full_spike_record[-update_interval:]
else:
current_labels = labels[i % len(labels) - update_interval:i %
len(labels)]
current_record = full_spike_record[i % len(labels) -
update_interval:i %
len(labels)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
full_spike_record=current_record,
logreg=logreg_model)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat(
[predictions[scheme], preds[scheme]], -1)
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print(
'New best accuracy! Saving network parameters to disk.'
)
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(
params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
torch.save((logreg_model.coef_, logreg_model.intercept_),
open(path, 'wb'))
best_accuracy = max([x[-1] for x in curves.values()])
# Refit logistic regression model.
logreg_model = logreg_fit(full_spike_record[:i], labels[:i],
logreg_model)
print()
# Get next input sample.
image = images[i % len(images)]
sample = bernoulli(datum=image, time=time, dt=dt,
max_prob=1).unsqueeze(1).unsqueeze(1)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
network.connections['X', 'Y_'].w = network.connections['X', 'Y'].w
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y_'].get('s').view(
time, -1)
full_spike_record[i] = spikes['Y_'].get('s').view(time, -1).sum(0)
# Optionally plot various simulation information.
if plot and i % plot_update_interval == 0:
_input = inpts['X'].view(time, 400).sum(0).view(20, 20)
w = network.connections['X', 'Y'].w
_spikes = {
'X': spikes['X'].get('s').view(400, time),
'Y': spikes['Y'].get('s').view(n_filters * total_conv_size,
time),
'Y_': spikes['Y_'].get('s').view(n_filters * total_conv_size,
time)
}
inpt_axes, inpt_ims = plot_input(image.view(20, 20),
_input,
label=labels[i % len(labels)],
ims=inpt_ims,
axes=inpt_axes)
spike_ims, spike_axes = plot_spikes(spikes=_spikes,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_conv2d_weights(
w, im=weights_im, wmax=network.connections['X', 'Y'].wmax)
plt.pause(1e-2)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
current_record = full_spike_record[-update_interval:]
else:
current_labels = labels[i % len(labels) - update_interval:i %
len(labels)]
current_record = full_spike_record[i % len(labels) -
update_interval:i % len(labels)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
full_spike_record=current_record,
logreg=logreg_model)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]],
-1)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
torch.save((logreg_model.coef_, logreg_model.intercept_),
open(path, 'wb'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print('Average accuracies:\n')
for scheme in curves.keys():
print('\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
to_write = [str(x) for x in to_write]
f = '_'.join(to_write) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
# Save results to disk.
results = [np.mean(curves['logreg']), np.std(curves['logreg'])]
to_write = params + results if train else test_params + results
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
columns = [
'seed', 'n_train', 'kernel_size', 'stride', 'n_filters',
'padding', 'inhib', 'time', 'lr', 'lr_decay', 'dt',
'intensity', 'update_interval', 'mean_logreg', 'std_logreg'
]
header = ','.join(columns) + '\n'
f.write(header)
else:
columns = [
'seed', 'n_train', 'n_test', 'kernel_size', 'stride',
'n_filters', 'padding', 'inhib', 'time', 'lr', 'lr_decay',
'dt', 'intensity', 'update_interval', 'mean_logreg',
'std_logreg'
]
header = ','.join(columns) + '\n'
f.write(header)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat(
[labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusions = {}
for scheme in predictions:
confusions[scheme] = confusion_matrix(labels, predictions[scheme])
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusions, os.path.join(confusion_path, f))
network.add_connection(conv_conn_, source='X', target='Y_')
network.add_connection(recurrent_conn, source='Y', target='Y')
network.add_connection(conv_conn2, source='Y', target='Z')
network.add_connection(recurrent_conn2, source='Z', target='Z')
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(path=os.path.join('..', '..', 'data', 'MNIST'), download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images *= intensity
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
# Neuron assignments and spike proportions.
if train:
assignments = -torch.ones_like(torch.Tensor(n_neurons))
proportions = torch.zeros_like(torch.Tensor(n_neurons, n_classes))
rates = torch.zeros_like(torch.Tensor(n_neurons, n_classes))
ngram_scores = {}
else:
path = os.path.join('..', '..', 'params', data, model)
path = os.path.join(path, '_'.join(['auxiliary', model_name]) + '.pt')
def main(seed=0, p_remove=0):
model = '0_16_2_250_4_0.01_0.99_60000_250.0_250_1.0_0.05_1e-07_0.5_0.2_10_250.pt'
np.random.seed(seed)
torch.manual_seed(seed)
torch.set_default_tensor_type('torch.cuda.FloatTensor')
torch.cuda.manual_seed_all(seed)
crop = 4
time = 250
n_filters = 250
intensity = 0.5
n_examples = 10000
n_classes = 10
# Load network.
network = load_network(
os.path.join(
ROOT_DIR, 'params', 'mnist', 'crop_locally_connected', model
)
)
network.connections['X', 'Y'].update_rule = NoOp(
connection=network.connections['X', 'Y'], nu=network.connections['X', 'Y'].nu
)
network.layers['Y'].theta_decay = 0
network.layers['Y'].theta_plus = 0
network.connections['X', 'Y'].norm = None
# Remove `p_remove` percentage of neurons (set outgoing synapses to 0).
mask = torch.bernoulli(p_remove * torch.ones(network.layers['Y'].shape)).byte()
network.connections['X', 'Y'].w[:, mask] = 0
conv_size = network.connections['X', 'Y'].conv_size
conv_prod = int(np.prod(conv_size))
n_neurons = n_filters * conv_prod
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(path=data_path, download=True, shuffle=True)
images, labels = dataset.get_test()
images *= intensity
images = images[:, crop:-crop, crop:-crop]
update_interval = 250
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
# Neuron assignments and spike proportions.
path = os.path.join(
ROOT_DIR, 'params', 'mnist', 'crop_locally_connected', f'auxiliary_{model}'
)
assignments, proportions, rates, ngram_scores = torch.load(open(path, 'rb'))
# Sequence of accuracy estimates.
curves = {'all': [], 'proportion': [], 'ngram': []}
predictions = {
scheme: torch.Tensor().long() for scheme in curves.keys()
}
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer], state_vars=['s'], time=time)
network.add_monitor(spikes[layer], name=f'{layer}_spikes')
start = t()
for i in range(n_examples):
if i % 10 == 0:
print(f'Progress: {i} / {n_examples} ({t() - start:.4f} seconds)')
start = t()
if i % update_interval == 0 and i > 0:
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]], -1)
# Get next input sample.
image = images[i % len(images)].contiguous().view(-1)
sample = poisson(datum=image, time=time, dt=1)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
retries = 0
while spikes['Y'].get('s').sum() < 5 and retries < 3:
retries += 1
image *= 2
sample = poisson(datum=image, time=time, dt=1)
inpts = {'X': sample}
network.run(inpts=inpts, time=time)
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y'].get('s').t()
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]], -1)
print('Average accuracies:\n')
for scheme in curves.keys():
print('\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save results to disk.
results = [
np.mean(curves['all']), np.mean(curves['proportion']), np.mean(curves['ngram']),
np.max(curves['all']), np.max(curves['proportion']), np.max(curves['ngram'])
]
to_write = [str(x) for x in [seed, p_remove] + results]
name = 'neuron_robust.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
f.write(
'random_seed,p_remove\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
def main(seed=0, n_examples=100, gpu=False, plot=False):
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)
model_name = '0_12_4_150_4_0.01_0.99_60000_250.0_250_1.0_0.05_1e-07_0.5_0.2_10_250'
network = load_network(os.path.join(params_path, f'{model_name}.pt'))
for l in network.layers:
network.layers[l].dt = network.dt
for c in network.connections:
network.connections[c].dt = network.dt
network.layers['Y'].one_spike = True
network.layers['Y'].lbound = None
kernel_size = 12
side_length = 20
n_filters = 150
time = 250
intensity = 0.5
crop = 4
conv_size = network.connections['X', 'Y'].conv_size
locations = network.connections['X', 'Y'].locations
conv_prod = int(np.prod(conv_size))
n_neurons = n_filters * conv_prod
n_classes = 10
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
images, labels = dataset.get_test()
images *= intensity
images = images[:, crop:-crop, crop:-crop]
# Neuron assignments and spike proportions.
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
assignments, proportions, rates, ngram_scores = torch.load(open(
path, 'rb'))
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer],
state_vars=['s'],
time=time)
network.add_monitor(spikes[layer], name=f'{layer}_spikes')
# Train the network.
print('\nBegin black box adversarial attack.\n')
spike_ims = None
spike_axes = None
weights_im = None
inpt_ims = None
inpt_axes = None
max_iters = 25
delta = 0.1
epsilon = 0.1
for i in range(n_examples):
# Get next input sample.
original = images[i % len(images)].contiguous().view(-1)
label = labels[i % len(images)]
# Check if the image is correctly classified.
sample = poisson(datum=original, time=time)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
# Check for incorrect classification.
s = spikes['Y'].get('s').view(1, n_neurons, time)
prediction = ngram(spikes=s,
ngram_scores=ngram_scores,
n_labels=10,
n=2).item()
if prediction != label:
continue
# Create adversarial example.
adversarial = False
while not adversarial:
adv_example = 255 * torch.rand(original.size())
sample = poisson(datum=adv_example, time=time)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
# Check for incorrect classification.
s = spikes['Y'].get('s').view(1, n_neurons, time)
prediction = ngram(spikes=s,
ngram_scores=ngram_scores,
n_labels=n_classes,
n=2).item()
if prediction == label:
adversarial = True
j = 0
current = original.clone()
while j < max_iters:
# Orthogonal perturbation.
# perturb = orthogonal_perturbation(delta=delta, image=adv_example, target=original)
# temp = adv_example + perturb
# # Forward perturbation.
# temp = temp.clone() + forward_perturbation(epsilon * get_diff(temp, original), temp, adv_example)
# print(temp)
perturbation = torch.randn(original.size())
unnormed_source_direction = original - perturbation
source_norm = torch.norm(unnormed_source_direction)
source_direction = unnormed_source_direction / source_norm
dot = torch.dot(perturbation, source_direction)
perturbation -= dot * source_direction
perturbation *= epsilon * source_norm / torch.norm(perturbation)
D = 1 / np.sqrt(epsilon**2 + 1)
direction = perturbation - unnormed_source_direction
spherical_candidate = current + D * direction
spherical_candidate = torch.clamp(spherical_candidate, 0, 255)
new_source_direction = original - spherical_candidate
new_source_direction_norm = torch.norm(new_source_direction)
# length if spherical_candidate would be exactly on the sphere
length = delta * source_norm
# length including correction for deviation from sphere
deviation = new_source_direction_norm - source_norm
length += deviation
# make sure the step size is positive
length = max(0, length)
# normalize the length
length = length / new_source_direction_norm
candidate = spherical_candidate + length * new_source_direction
candidate = torch.clamp(candidate, 0, 255)
sample = poisson(datum=candidate, time=time)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
# Check for incorrect classification.
s = spikes['Y'].get('s').view(1, n_neurons, time)
prediction = ngram(spikes=s,
ngram_scores=ngram_scores,
n_labels=10,
n=2).item()
# Optionally plot various simulation information.
if plot:
_input = original.view(side_length, side_length)
reconstruction = candidate.view(side_length, side_length)
_spikes = {
'X': spikes['X'].get('s').view(side_length**2, time),
'Y': spikes['Y'].get('s').view(n_neurons, time)
}
w = network.connections['X', 'Y'].w
spike_ims, spike_axes = plot_spikes(spikes=_spikes,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_locally_connected_weights(w,
n_filters,
kernel_size,
conv_size,
locations,
side_length,
im=weights_im)
inpt_axes, inpt_ims = plot_input(_input,
reconstruction,
label=labels[i],
ims=inpt_ims,
axes=inpt_axes)
plt.pause(1e-8)
if prediction == label:
print('Attack failed.')
else:
print('Attack succeeded.')
adv_example = candidate
j += 1
network.reset_() # Reset state variables.
print('\nAdversarial attack complete.\n')
def main(seed=0,
n_neurons=100,
n_train=60000,
n_test=10000,
inhib=250,
lr=1e-2,
lr_decay=1,
time=100,
dt=1,
theta_plus=0.05,
theta_decay=1e-7,
intensity=1,
progress_interval=10,
update_interval=100,
plot=False,
train=True,
gpu=False,
no_inhib=False,
no_theta=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, lr_decay, time, dt, theta_plus,
theta_decay, intensity, progress_interval, update_interval
]
test_params = [
seed, n_neurons, n_train, n_test, inhib, lr, lr_decay, time, dt,
theta_plus, theta_decay, intensity, 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_sqrt = int(np.ceil(np.sqrt(n_neurons)))
n_classes = 10
# Build network.
if train:
network = Network()
input_layer = Input(n=784, traces=True, trace_tc=5e-2)
network.add_layer(input_layer, name='X')
output_layer = DiehlAndCookNodes(n=n_neurons,
traces=True,
rest=0,
reset=0,
thresh=5,
refrac=0,
decay=1e-2,
trace_tc=5e-2,
theta_plus=theta_plus,
theta_decay=theta_decay)
network.add_layer(output_layer, name='Y')
w = 0.3 * torch.rand(784, n_neurons)
input_connection = Connection(source=network.layers['X'],
target=network.layers['Y'],
w=w,
update_rule=WeightDependentPostPre,
nu=[0, lr],
wmin=0,
wmax=1,
norm=78.4)
network.add_connection(input_connection, source='X', target='Y')
w = -inhib * (torch.ones(n_neurons, n_neurons) -
torch.diag(torch.ones(n_neurons)))
recurrent_connection = Connection(source=network.layers['Y'],
target=network.layers['Y'],
w=w,
wmin=-inhib,
wmax=0,
update_rule=WeightDependentPostPre,
nu=[0, -100 * lr],
norm=inhib / 2 * n_neurons)
network.add_connection(recurrent_connection, source='Y', target='Y')
mask = network.connections['Y', 'Y'].w == 0
masks = {('Y', 'Y'): mask}
else:
network = load_network(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.connections['Y', 'Y'].update_rule = NoOp(
connection=network.connections['X', 'Y'],
nu=network.connections['X', 'Y'].nu)
network.layers['Y'].theta_decay = 0
network.layers['Y'].theta_plus = 0
if no_inhib:
del network.connections['Y', 'Y']
if no_theta:
network.layers['Y'].theta = 0
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images = images.view(-1, 784)
images *= intensity
labels = labels.long()
monitors = {}
for layer in set(network.layers):
if 'v' in network.layers[layer].__dict__:
monitors[layer] = Monitor(network.layers[layer],
state_vars=['s', 'v'],
time=time)
else:
monitors[layer] = Monitor(network.layers[layer],
state_vars=['s'],
time=time)
network.add_monitor(monitors[layer], name=layer)
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
inpt_axes = None
inpt_ims = None
spike_ims = None
spike_axes = None
voltage_ims = None
voltage_axes = None
weights_im = None
weights2_im = None
unclamps = {}
per_class = int(n_neurons / n_classes)
for label in range(n_classes):
unclamp = torch.ones(n_neurons).byte()
unclamp[label * per_class:(label + 1) * per_class] = 0
unclamps[label] = unclamp
predictions = torch.zeros(n_examples)
corrects = torch.zeros(n_examples)
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 % update_interval == 0 and i > 0 and train:
network.save(os.path.join(params_path, model_name + '.pt'))
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
# Get next input sample.
image = images[i % len(images)]
label = labels[i % len(images)].item()
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
# Run the network on the input.
if train:
network.run(inpts=inpts,
time=time,
unclamp={'Y': unclamps[label]},
masks=masks)
else:
network.run(inpts=inpts, time=time)
if not train:
retries = 0
while monitors['Y'].get('s').sum() == 0 and retries < 3:
retries += 1
image *= 1.5
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
if train:
network.run(inpts=inpts,
time=time,
unclamp={'Y': unclamps[label]},
masks=masks)
else:
network.run(inpts=inpts, time=time)
output = monitors['Y'].get('s')
summed_neurons = output.sum(dim=1).view(n_classes, per_class)
summed_classes = summed_neurons.sum(dim=1)
prediction = torch.argmax(summed_classes).item()
correct = prediction == label
predictions[i] = prediction
corrects[i] = int(correct)
# Optionally plot various simulation information.
if plot:
# _input = image.view(28, 28)
# reconstruction = inpts['X'].view(time, 784).sum(0).view(28, 28)
# v = {'Y': monitors['Y'].get('v')}
s = {layer: monitors[layer].get('s') for layer in monitors}
input_exc_weights = network.connections['X', 'Y'].w
square_weights = get_square_weights(
input_exc_weights.view(784, n_neurons), n_sqrt, 28)
recurrent_weights = network.connections['Y', 'Y'].w
# inpt_axes, inpt_ims = plot_input(_input, reconstruction, label=labels[i], axes=inpt_axes, ims=inpt_ims)
# voltage_ims, voltage_axes = plot_voltages(v, ims=voltage_ims, axes=voltage_axes)
spike_ims, spike_axes = plot_spikes(s,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_weights(square_weights, im=weights_im)
weights2_im = plot_weights(recurrent_weights,
im=weights2_im,
wmin=-inhib,
wmax=0)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
if train:
network.save(os.path.join(params_path, model_name + '.pt'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
accuracy = torch.mean(corrects).item() * 100
print(f'\nAccuracy: {accuracy}\n')
to_write = params + [accuracy] if train else test_params + [accuracy]
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write(
'random_seed,n_neurons,n_train,inhib,lr,lr_decay,time,timestep,theta_plus,'
'theta_decay,intensity,progress_interval,update_interval,accuracy\n'
)
else:
f.write(
'random_seed,n_neurons,n_train,n_test,inhib,lr,lr_decay,time,timestep,'
'theta_plus,theta_decay,intensity,progress_interval,update_interval,accuracy\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat(
[labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusion = confusion_matrix(labels, predictions)
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusion, os.path.join(confusion_path, f))
def main(seed=0,
n_train=60000,
n_test=10000,
inhib=250,
kernel_size=(16, ),
stride=(2, ),
time=100,
n_filters=25,
crop=0,
lr=1e-2,
lr_decay=0.99,
dt=1,
theta_plus=0.05,
theta_decay=1e-7,
intensity=5,
norm=0.2,
progress_interval=10,
update_interval=250,
train=True,
plot=False,
gpu=False):
assert n_train % update_interval == 0 and n_test % update_interval == 0, \
'No. examples must be divisible by update_interval'
params = [
seed, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train,
inhib, time, dt, theta_plus, theta_decay, intensity, norm,
progress_interval, update_interval
]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train,
n_test, inhib, time, dt, theta_plus, theta_decay, intensity, norm,
progress_interval, update_interval
]
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)
side_length = 28 - crop * 2
n_inpt = side_length**2
n_examples = n_train if train else n_test
n_classes = 10
# Build network.
if train:
network = LocallyConnectedNetwork(
n_inpt=n_inpt,
input_shape=[side_length, side_length],
kernel_size=kernel_size,
stride=stride,
n_filters=n_filters,
inh=inhib,
dt=dt,
nu=[0, lr],
theta_plus=theta_plus,
theta_decay=theta_decay,
wmin=0.0,
wmax=1.0,
norm=norm)
else:
network = load_network(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 = 0
network.layers['Y'].theta_plus = 0
conv_size = network.connections['X', 'Y'].conv_size
locations = network.connections['X', 'Y'].locations
conv_prod = int(np.prod(conv_size))
n_neurons = n_filters * conv_prod
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images *= intensity
images = images[:, crop:-crop, crop:-crop]
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
full_spike_record = torch.zeros(n_examples, n_neurons)
# Neuron assignments and spike proportions.
if train:
logreg_model = LogisticRegression(warm_start=True,
n_jobs=-1,
solver='lbfgs',
max_iter=1000,
multi_class='multinomial')
logreg_model.coef_ = np.zeros([n_classes, n_neurons])
logreg_model.intercept_ = np.zeros(n_classes)
logreg_model.classes_ = np.arange(n_classes)
else:
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
logreg_coef, logreg_intercept = torch.load(open(path, 'rb'))
logreg_model = LogisticRegression(warm_start=True,
n_jobs=-1,
solver='lbfgs',
max_iter=1000,
multi_class='multinomial')
logreg_model.coef_ = logreg_coef
logreg_model.intercept_ = logreg_intercept
logreg_model.classes_ = np.arange(n_classes)
if train:
best_accuracy = 0
# Sequence of accuracy estimates.
curves = {'logreg': []}
predictions = {scheme: torch.Tensor().long() for scheme in curves.keys()}
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer],
state_vars=['s'],
time=time)
network.add_monitor(spikes[layer], name=f'{layer}_spikes')
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
spike_ims = None
spike_axes = None
weights_im = None
weights2_im = 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 % update_interval == 0 and i > 0:
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
current_record = full_spike_record[-update_interval:]
else:
current_labels = labels[i % len(labels) - update_interval:i %
len(labels)]
current_record = full_spike_record[i % len(labels) -
update_interval:i %
len(labels)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
full_spike_record=current_record,
logreg=logreg_model)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat(
[predictions[scheme], preds[scheme]], -1)
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print(
'New best accuracy! Saving network parameters to disk.'
)
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(
params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
torch.save((logreg_model.coef_, logreg_model.intercept_),
open(path, 'wb'))
best_accuracy = max([x[-1] for x in curves.values()])
# Refit logistic regression model.
logreg_model = logreg_fit(full_spike_record[:i], labels[:i],
logreg_model)
print()
# Get next input sample.
image = images[i % len(images)].contiguous().view(-1)
sample = bernoulli(datum=image, time=time, dt=dt)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
retries = 0
while spikes['Y'].get('s').sum() < 5 and retries < 3:
retries += 1
image *= 2
sample = bernoulli(datum=image, time=time, dt=dt)
inpts = {'X': sample}
network.run(inpts=inpts, time=time)
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y'].get('s').view(time, -1)
full_spike_record[i] = spikes['Y'].get('s').view(time, -1).sum(0)
if plot:
# Optionally plot various simulation information.
_spikes = {
'X': spikes['X'].get('s').view(side_length**2, time),
'Y': spikes['Y'].get('s').view(n_filters * conv_prod, time)
}
spike_ims, spike_axes = plot_spikes(spikes=_spikes,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_locally_connected_weights(
network.connections[('X', 'Y')].w,
n_filters,
kernel_size,
conv_size,
locations,
side_length,
im=weights_im)
weights2_im = plot_weights(logreg_model.coef_, im=weights2_im)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
current_record = full_spike_record[-update_interval:]
else:
current_labels = labels[i % len(labels) - update_interval:i %
len(labels)]
current_record = full_spike_record[i % len(labels) -
update_interval:i % len(labels)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
full_spike_record=current_record,
logreg=logreg_model)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]],
-1)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
torch.save((logreg_model.coef_, logreg_model.intercept_),
open(path, 'wb'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print('Average accuracies:\n')
for scheme in curves.keys():
print('\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save accuracy curves to disk.
if train:
to_write = ['train'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
# Save results to disk.
results = [np.mean(curves['logreg']), np.std(curves['logreg'])]
to_write = params + results if train else test_params + results
to_write = [str(x) for x in to_write]
if train:
name = 'train.csv'
else:
name = 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write(
'random_seed,kernel_size,stride,n_filters,crop,lr,lr_decay,n_train,inhib,time,timestep,theta_plus,'
'theta_decay,intensity,norm,progress_interval,update_interval,mean_logreg,std_logreg\n'
)
else:
f.write(
'random_seed,kernel_size,stride,n_filters,crop,lr,lr_decay,n_train,n_test,inhib,time,timestep,'
'theta_plus,theta_decay,intensity,norm,progress_interval,update_interval,mean_logreg,std_logreg\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat(
[labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusions = {}
for scheme in predictions:
confusions[scheme] = confusion_matrix(labels, predictions[scheme])
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusions, os.path.join(confusion_path, f))
def main(seed=0, n_neurons=100, n_train=60000, n_test=10000, inhib=250, time=50, lr=1e-2, lr_decay=0.99, dt=1,
theta_plus=0.05, theta_decay=1e-7, progress_interval=10, update_interval=250, train=True, plot=False,
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, time, lr, lr_decay,
theta_plus, theta_decay, progress_interval, update_interval
]
test_params = [
seed, n_neurons, n_train, n_test, inhib, time, lr, lr_decay,
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)
if train:
n_examples = n_train
else:
n_examples = n_test
n_sqrt = int(np.ceil(np.sqrt(n_neurons)))
n_classes = 10
# Build network.
if train:
network = Network(dt=dt)
input_layer = RealInput(n=784, traces=True, trace_tc=5e-2)
network.add_layer(input_layer, name='X')
output_layer = DiehlAndCookNodes(
n=n_neurons, traces=True, rest=0, reset=0, thresh=1, refrac=0,
decay=1e-2, trace_tc=5e-2, theta_plus=theta_plus, theta_decay=theta_decay
)
network.add_layer(output_layer, name='Y')
w = 0.3 * torch.rand(784, n_neurons)
input_connection = Connection(
source=network.layers['X'], target=network.layers['Y'], w=w, update_rule=PostPre,
nu=[0, lr], wmin=0, wmax=1, norm=78.4
)
network.add_connection(input_connection, source='X', target='Y')
w = -inhib * (torch.ones(n_neurons, n_neurons) - torch.diag(torch.ones(n_neurons)))
recurrent_connection = Connection(
source=network.layers['Y'], target=network.layers['Y'], w=w, wmin=-inhib, wmax=0
)
network.add_connection(recurrent_connection, source='Y', target='Y')
else:
path = os.path.join('..', '..', 'params', data, model)
network = load_network(os.path.join(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 = 0
network.layers['Y'].theta_plus = 0
# Load MNIST data.
dataset = MNIST(path=os.path.join('..', '..', 'data', 'MNIST'), download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images = images.view(-1, 784)
images = images / 255
# if train:
# for i in range(n_neurons):
# network.connections['X', 'Y'].w[:, i] = images[i] + images[i].mean() * torch.randn(784)
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
# Neuron assignments and spike proportions.
if train:
assignments = -torch.ones_like(torch.Tensor(n_neurons))
proportions = torch.zeros_like(torch.Tensor(n_neurons, n_classes))
rates = torch.zeros_like(torch.Tensor(n_neurons, n_classes))
ngram_scores = {}
else:
path = os.path.join('..', '..', 'params', data, model)
path = os.path.join(path, '_'.join(['auxiliary', model_name]) + '.pt')
assignments, proportions, rates, ngram_scores = torch.load(open(path, 'rb'))
# Sequence of accuracy estimates.
curves = {'all': [], 'proportion': [], 'ngram': []}
if train:
best_accuracy = 0
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)
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
inpt_axes = None
inpt_ims = None
spike_ims = None
spike_axes = None
weights_im = None
assigns_im = None
perf_ax = 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 % update_interval == 0 and i > 0:
if train:
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, predictions = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
path = os.path.join('..', '..', 'params', data, model)
if not os.path.isdir(path):
os.makedirs(path)
network.save(os.path.join(path, model_name + '.pt'))
path = os.path.join(path, '_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores), open(path, 'wb'))
best_accuracy = max([x[-1] for x in curves.values()])
# Assign labels to excitatory layer neurons.
assignments, proportions, rates = assign_labels(spike_record, current_labels, n_classes, rates)
# Compute ngram scores.
ngram_scores = update_ngram_scores(spike_record, current_labels, n_classes, 2, ngram_scores)
print()
# Get next input sample.
image = images[i % n_examples].repeat([time, 1])
inpts = {'X': image}
# Run the network on the input.
network.run(inpts=inpts, time=time)
retries = 0
while spikes['Y'].get('s').sum() < 5 and retries < 3:
retries += 1
image *= 2
inpts = {'X': image}
network.run(inpts=inpts, time=time)
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y'].get('s').t()
# Optionally plot various simulation information.
if plot and i % update_interval == 0:
_input = images[i % n_examples].view(28, 28)
reconstruction = inpts['X'].view(time, 784).sum(0).view(28, 28)
_spikes = {layer: spikes[layer].get('s') for layer in spikes}
input_exc_weights = network.connections['X', 'Y'].w
square_weights = get_square_weights(input_exc_weights.view(784, n_neurons), n_sqrt, 28)
square_assignments = get_square_assignments(assignments, n_sqrt)
# inpt_axes, inpt_ims = plot_input(_input, reconstruction, label=labels[i], axes=inpt_axes, ims=inpt_ims)
spike_ims, spike_axes = plot_spikes(_spikes, ims=spike_ims, axes=spike_axes)
weights_im = plot_weights(square_weights, im=weights_im)
# assigns_im = plot_assignments(square_assignments, im=assigns_im)
# perf_ax = plot_performance(curves, ax=perf_ax)
plt.pause(1e-1)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, predictions = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
if train:
path = os.path.join('..', '..', 'params', data, model)
if not os.path.isdir(path):
os.makedirs(path)
network.save(os.path.join(path, model_name + '.pt'))
path = os.path.join(path, '_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores), open(path, 'wb'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print('Average accuracies:\n')
for scheme in curves.keys():
print('\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save accuracy curves to disk.
path = os.path.join('..', '..', 'curves', data, model)
if not os.path.isdir(path):
os.makedirs(path)
if train:
to_write = ['train'] + params
else:
to_write = ['test'] + params
to_write = [str(x) for x in to_write]
f = '_'.join(to_write) + '.pt'
torch.save((curves, update_interval, n_examples), open(os.path.join(path, f), 'wb'))
# Save results to disk.
path = os.path.join('..', '..', 'results', data, model)
if not os.path.isdir(path):
os.makedirs(path)
results = [
np.mean(curves['all']), np.mean(curves['proportion']), np.mean(curves['ngram']),
np.max(curves['all']), np.max(curves['proportion']), np.max(curves['ngram'])
]
if train:
to_write = params + results
else:
to_write = test_params + results
to_write = [str(x) for x in to_write]
if train:
name = 'train.csv'
else:
name = 'test.csv'
if not os.path.isfile(os.path.join(path, name)):
with open(os.path.join(path, name), 'w') as f:
if train:
f.write('random_seed,n_neurons,n_train,inhib,time,lr,lr_decay,theta_plus,theta_decay,'
'progress_interval,update_interval,mean_all_activity,mean_proportion_weighting,'
'mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n')
else:
f.write('random_seed,n_neurons,n_train,n_test,inhib,time,lr,lr_decay,theta_plus,theta_decay,'
'progress_interval,update_interval,mean_all_activity,mean_proportion_weighting,'
'mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n')
with open(os.path.join(path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
def main(seed=0,
n_train=60000,
n_test=10000,
time=50,
lr=0.01,
lr_decay=0.95,
update_interval=500,
max_prob=1.0,
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_train, time, lr, lr_decay, update_interval, max_prob]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, n_train, n_test, time, lr, lr_decay, update_interval,
max_prob
]
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)
criterion = torch.nn.CrossEntropyLoss(
) # Loss function on output firing rates.
n_examples = n_train if train else n_test
if train:
# Network building.
network = Network()
# Groups of neurons.
input_layer = RealInput(n=784, sum_input=True)
output_layer = IFNodes(n=10, sum_input=True)
bias = RealInput(n=1, sum_input=True)
network.add_layer(input_layer, name='X')
network.add_layer(output_layer, name='Y')
network.add_layer(bias, name='Y_b')
# Connections between groups of neurons.
input_connection = Connection(source=input_layer,
target=output_layer,
norm=150,
wmin=-1,
wmax=1)
bias_connection = Connection(source=bias, target=output_layer)
network.add_connection(input_connection, source='X', target='Y')
network.add_connection(bias_connection, source='Y_b', target='Y')
# State variable monitoring.
for l in network.layers:
m = Monitor(network.layers[l], state_vars=['s'], time=time)
network.add_monitor(m, name=l)
else:
network = load_network(os.path.join(params_path, model_name + '.pt'))
# Load MNIST data.
dataset = MNIST(path=data_path, download=True, shuffle=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images, labels = images.view(-1, 784) / 255, labels
grads = {}
accuracies = []
predictions = []
ground_truth = []
best = -np.inf
spike_ims, spike_axes, weights_im = None, None, None
losses = torch.zeros(update_interval)
correct = torch.zeros(update_interval)
# Run training.
start = t()
for i in range(n_examples):
label = torch.Tensor([labels[i % len(labels)]]).long()
image = images[i % len(labels)]
# Run simulation for single datum.
inpts = {'X': image.repeat(time, 1), 'Y_b': torch.ones(time, 1)}
network.run(inpts=inpts, time=time)
# Retrieve spikes and summed inputs from both layers.
spikes = {
l: network.monitors[l].get('s')
for l in network.layers if '_b' not in l
}
summed_inputs = {l: network.layers[l].summed for l in network.layers}
# Compute softmax of output spiking activity and get predicted label.
output = summed_inputs['Y'].softmax(0).view(1, -1)
predicted = output.argmax(1).item()
correct[i % update_interval] = int(predicted == label[0].item())
predictions.append(predicted)
ground_truth.append(label)
# Compute cross-entropy loss between output and true label.
losses[i % update_interval] = criterion(output, label)
if train:
# Compute gradient of the loss WRT average firing rates.
grads['dl/df'] = summed_inputs['Y'].softmax(0)
grads['dl/df'][label] -= 1
# Compute gradient of the summed voltages WRT connection weights.
# This is an approximation; the summed voltages are not a
# smooth function of the connection weights.
grads['dl/dw'] = torch.ger(summed_inputs['X'], grads['dl/df'])
grads['dl/db'] = grads['dl/df']
# Do stochastic gradient descent calculation.
network.connections['X', 'Y'].w -= lr * grads['dl/dw']
network.connections['Y_b', 'Y'].w -= lr * grads['dl/db']
if i > 0 and i % update_interval == 0:
accuracies.append(correct.mean() * 100)
if train:
if accuracies[-1] > best:
print()
print(
'New best accuracy! Saving network parameters to disk.'
)
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
best = accuracies[-1]
print()
print(f'Progress: {i} / {n_examples} ({t() - start:.3f} seconds)')
print(f'Average cross-entropy loss: {losses.mean():.3f}')
print(f'Last accuracy: {accuracies[-1]:.3f}')
print(f'Average accuracy: {np.mean(accuracies):.3f}')
# Decay learning rate.
lr *= lr_decay
if train:
print(f'Best accuracy: {best:.3f}')
print(f'Current learning rate: {lr:.3f}')
start = t()
if plot:
w = network.connections['X', 'Y'].w
weights = [w[:, i].view(28, 28) for i in range(10)]
w = torch.zeros(5 * 28, 2 * 28)
for i in range(5):
for j in range(2):
w[i * 28:(i + 1) * 28,
j * 28:(j + 1) * 28] = weights[i + j * 5]
spike_ims, spike_axes = plot_spikes(spikes,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_weights(w, im=weights_im, wmin=-1, wmax=1)
plt.pause(1e-1)
network.reset_() # Reset state variables.
accuracies.append(correct.mean() * 100)
if train:
lr *= lr_decay
for c in network.connections:
network.connections[c].update_rule.weight_decay *= lr_decay
if accuracies[-1] > best:
print()
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
best = accuracies[-1]
print()
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.3f} seconds)')
print(f'Average cross-entropy loss: {losses.mean():.3f}')
print(f'Last accuracy: {accuracies[-1]:.3f}')
print(f'Average accuracy: {np.mean(accuracies):.3f}')
if train:
print(f'Best accuracy: {best:.3f}')
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print(f'Average accuracy: {np.mean(accuracies):.3f}')
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((accuracies, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
results = [np.mean(accuracies), np.max(accuracies)]
to_write = params + results if train else test_params + results
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write(
'seed,n_train,time,lr,lr_decay,update_interval,max_prob,mean_accuracy,max_accuracy\n'
)
else:
f.write(
'seed,n_train,n_test,time,lr,lr_decay,update_interval,max_prob,mean_accuracy,max_accuracy\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
# Compute confusion matrices and save them to disk.
confusion = confusion_matrix(ground_truth, predictions)
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusion, os.path.join(confusion_path, f))
def main(seed=0,
n_train=60000,
n_test=10000,
inhib=250,
kernel_size=(16, ),
stride=(2, ),
n_filters=25,
n_output=100,
time=100,
crop=0,
lr=1e-2,
lr_decay=0.99,
dt=1,
theta_plus=0.05,
theta_decay=1e-7,
intensity=1,
norm=0.2,
progress_interval=10,
update_interval=250,
train=True,
plot=False,
gpu=False):
assert n_train % update_interval == 0, 'No. examples must be divisible by update_interval'
params = [
seed, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train,
inhib, time, dt, theta_plus, theta_decay, intensity, norm,
progress_interval, update_interval
]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train,
n_test, inhib, time, dt, theta_plus, theta_decay, intensity, norm,
progress_interval, update_interval
]
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)
side_length = 28 - crop * 2
n_inpt = side_length**2
n_examples = n_train if train else n_test
n_classes = 10
# Build network.
if train:
network = load_network(
os.path.join(
ROOT_DIR, 'params', 'mnist', 'crop_locally_connected',
'0_12_4_150_4_0.01_0.99_60000_250.0_250_1.0_0.05_1e-07_0.5_0.2_10_250.pt'
))
for l in network.layers:
network.layers[l].dt = 1
network.layers[l].lbound = None
for m in network.monitors:
network.monitors[m].record_length = 0
network.connections['X', 'Y'].update_rule = NoOp(
connection=network.connections['X', 'Y'],
nu=network.connections['X', 'Y'].nu)
network.layers['Y'].theta_decay = 0
network.layers['Y'].theta_plus = 0
network.layers['Y'].theta -= 0.5 * network.layers['Y'].theta.mean()
network.layers['Y'].one_spike = False
del network.connections['Y', 'Y']
output_layer = DiehlAndCookNodes(n=n_output,
traces=True,
rest=0,
reset=0,
thresh=1,
refrac=0,
decay=1e-2,
trace_tc=5e-2)
hidden_output_connection = Connection(
network.layers['Y'],
output_layer,
nu=[0, lr],
update_rule=WeightDependentPostPre,
wmin=0,
wmax=1,
norm=norm * network.layers['Y'].n)
w = -inhib * (torch.ones(n_output, n_output) -
torch.diag(torch.ones(n_output)))
output_recurrent_connection = Connection(output_layer,
output_layer,
w=w,
update_rule=NoOp,
wmin=-inhib,
wmax=0)
network.add_layer(output_layer, name='Z')
network.add_connection(hidden_output_connection,
source='Y',
target='Z')
network.add_connection(output_recurrent_connection,
source='Z',
target='Z')
else:
network = load_network(os.path.join(params_path, model_name + '.pt'))
network.connections['Y', 'Z'].update_rule = NoOp(
connection=network.connections['Y', 'Z'], nu=0)
# network.layers['Z'].theta = 0
# network.layers['Z'].theta_decay = 0
# network.layers['Z'].theta_plus = 0
# del network.connections['Z', 'Z']
conv_size = network.connections['X', 'Y'].conv_size
locations = network.connections['X', 'Y'].locations
conv_prod = int(np.prod(conv_size))
n_neurons = n_filters * conv_prod
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images *= intensity
images = images[:, crop:-crop,
crop:-crop].contiguous().view(-1, side_length**2)
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer],
state_vars=['s'],
time=time)
network.add_monitor(spikes[layer], name=f'{layer}_spikes')
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
spike_ims = None
spike_axes = None
weights_im = None
weights2_im = None
unclamps = {}
per_class = int(n_output / n_classes)
for label in range(n_classes):
unclamp = torch.ones(n_output).byte()
unclamp[label * per_class:(label + 1) * per_class] = 0
unclamps[label] = unclamp
predictions = torch.zeros(n_examples)
corrects = torch.zeros(n_examples)
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 % update_interval == 0 and i > 0:
if train:
network.save(os.path.join(params_path, model_name + '.pt'))
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
# Get next input sample.
image = images[i % len(images)]
label = labels[i % len(images)].item()
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
# Run the network on the input.
if train:
network.run(inpts=inpts, time=time, unclamp={'Z': unclamps[label]})
else:
network.run(inpts=inpts, time=time)
if not train:
retries = 0
while spikes['Z'].get('s').sum() < 5 and retries < 3:
retries += 1
image *= 1.5
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
if train:
network.run(inpts=inpts,
time=time,
unclamp={'Z': unclamps[label]})
else:
network.run(inpts=inpts, time=time)
output = spikes['Z'].get('s')
summed_neurons = output.sum(dim=1).view(per_class, n_classes)
summed_classes = summed_neurons.sum(dim=1)
prediction = torch.argmax(summed_classes).item()
correct = prediction == label
predictions[i] = prediction
corrects[i] = int(correct)
# print(spikes[].get('s').sum(), spikes['Z'].get('s').sum())
# Optionally plot various simulation information.
if plot:
_spikes = {
'X': spikes['X'].get('s').view(side_length**2, time),
'Y': spikes['Y'].get('s').view(n_neurons, time),
'Z': spikes['Z'].get('s').view(n_output, time)
}
spike_ims, spike_axes = plot_spikes(spikes=_spikes,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_locally_connected_weights(
network.connections['X', 'Y'].w,
n_filters,
kernel_size,
conv_size,
locations,
side_length,
im=weights_im)
w = network.connections['Y', 'Z'].w
weights2_im = plot_weights(w, im=weights2_im, wmax=1)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
if train:
network.save(os.path.join(params_path, model_name + '.pt'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
accuracy = torch.mean(corrects).item() * 100
print(f'\nAccuracy: {accuracy}\n')
to_write = params + [accuracy] if train else test_params + [accuracy]
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write(
'random_seed,kernel_size,stride,n_filters,crop,lr,lr_decay,n_train,inhib,time,timestep,theta_plus,'
'theta_decay,intensity,norm,progress_interval,accuracy\n')
else:
f.write(
'random_seed,kernel_size,stride,n_filters,crop,lr,lr_decay,n_train,n_test,inhib,time,timestep,'
'theta_plus,theta_decay,intensity,norm,progress_interval,update_interval,accuracy\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat(
[labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusion = confusion_matrix(labels, predictions)
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusion, os.path.join(confusion_path, f))
def main(seed=0,
n_neurons=100,
n_train=60000,
n_test=10000,
c_low=2.5,
c_high=250,
p_low=0.1,
time=250,
dt=1,
theta_plus=0.05,
theta_decay=1e-7,
intensity=1,
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, c_low, c_high, p_low, time, dt, theta_plus,
theta_decay, intensity, progress_interval, update_interval
]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, n_neurons, n_train, n_test, c_low, c_high, p_low, time, dt,
theta_plus, theta_decay, intensity, progress_interval,
update_interval
]
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_sqrt = int(np.ceil(np.sqrt(n_neurons)))
n_classes = 10
if train:
iter_increase = int(n_train * p_low)
print(f'Iteration to increase from c_low to c_high: {iter_increase}\n')
# Build network.
if train:
network = Network(dt=dt)
input_layer = Input(n=784, traces=True)
exc_layer = DiehlAndCookNodes(n=n_neurons, traces=True)
w = torch.rand(input_layer.n, exc_layer.n)
input_exc_conn = Connection(input_layer,
exc_layer,
w=w,
update_rule=PostPre,
norm=78.4,
nu=(1e-4, 1e-2),
wmax=1.0)
w = torch.zeros(exc_layer.n, exc_layer.n)
for k1 in range(n_neurons):
for k2 in range(n_neurons):
if k1 != k2:
x1, y1 = k1 // np.sqrt(n_neurons), k1 % np.sqrt(n_neurons)
x2, y2 = k2 // np.sqrt(n_neurons), k2 % np.sqrt(n_neurons)
w[k1, k2] = max(
-c_high,
-c_low * np.sqrt(euclidean([x1, y1], [x2, y2])))
recurrent_conn = Connection(exc_layer, exc_layer, w=w)
network.add_layer(input_layer, name='X')
network.add_layer(exc_layer, name='Y')
network.add_connection(input_exc_conn, source='X', target='Y')
network.add_connection(recurrent_conn, source='Y', target='Y')
else:
network = load_network(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 = 0
network.layers['Y'].theta_plus = 0
# Load MNIST data.
dataset = MNIST(data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images = images.view(-1, 784)
images *= intensity
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, int(time / dt), n_neurons)
# Neuron assignments and spike proportions.
if train:
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))
ngram_scores = {}
else:
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
assignments, proportions, rates, ngram_scores = torch.load(
open(path, 'rb'))
# Sequence of accuracy estimates.
curves = {'all': [], 'proportion': [], 'ngram': []}
predictions = {scheme: torch.Tensor().long() for scheme in curves.keys()}
if train:
best_accuracy = 0
spikes = {}
for layer in set(network.layers) - {'X'}:
spikes[layer] = Monitor(network.layers[layer],
state_vars=['s'],
time=int(time / dt))
network.add_monitor(spikes[layer], name='%s_spikes' % layer)
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
inpt_axes = None
inpt_ims = None
spike_ims = None
spike_axes = None
weights_im = None
assigns_im = None
perf_ax = None
start = t()
for i in range(n_examples):
if train and i == iter_increase:
print(
'\nChanging inhibition from low and graded to high and constant.\n'
)
w = -c_high * (torch.ones(n_neurons, n_neurons) -
torch.diag(torch.ones(n_neurons)))
network.connections['Y', 'Y'].w = w
if i % progress_interval == 0:
print(f'Progress: {i} / {n_examples} ({t() - start:.4f} seconds)')
start = t()
if i % update_interval == 0 and i > 0:
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i %
len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
spike_record=spike_record,
assignments=assignments,
proportions=proportions,
ngram_scores=ngram_scores,
n=2)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat(
[predictions[scheme], preds[scheme]], -1)
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print(
'New best accuracy! Saving network parameters to disk.'
)
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(
params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores),
open(path, 'wb'))
best_accuracy = max([x[-1] for x in curves.values()])
# Assign labels to excitatory layer neurons.
assignments, proportions, rates = assign_labels(
spike_record, labels[i - update_interval:i], 10, rates)
# Compute ngram scores.
ngram_scores = update_ngram_scores(
spike_record, labels[i - update_interval:i], 10, 2,
ngram_scores)
print()
# Get next input sample.
image = images[i]
sample = poisson(datum=image, time=int(time / dt))
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
retries = 0
while spikes['Y'].get('s').sum() < 5 and retries < 3:
retries += 1
image *= 2
sample = poisson(datum=image, time=int(time / dt))
inpts = {'X': sample}
network.run(inpts=inpts, time=time)
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y'].get('s').t()
# Optionally plot various simulation information.
if plot:
inpt = inpts['X'].view(time, 784).sum(0).view(28, 28)
_spikes = {layer: spikes[layer].get('s') for layer in spikes}
input_exc_weights = network.connections['X', 'Y'].w
square_weights = get_square_weights(
input_exc_weights.view(784, n_neurons), n_sqrt, 28)
square_assignments = get_square_assignments(assignments, n_sqrt)
# inpt_axes, inpt_ims = plot_input(images[i].view(28, 28), inpt, label=labels[i], axes=inpt_axes, ims=inpt_ims)
spike_ims, spike_axes = plot_spikes(_spikes,
ims=spike_ims,
axes=spike_axes)
weights_im = plot_weights(square_weights, im=weights_im)
# assigns_im = plot_assignments(square_assignments, im=assigns_im)
# perf_ax = plot_performance(curves, ax=perf_ax)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i %
len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(curves,
current_labels,
n_classes,
spike_record=spike_record,
assignments=assignments,
proportions=proportions,
ngram_scores=ngram_scores,
n=2)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]],
-1)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(params_path,
'_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores),
open(path, 'wb'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print('Average accuracies:\n')
for scheme in curves.keys():
print(f'\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
to_write = [str(x) for x in to_write]
f = '_'.join(to_write) + '.pt'
torch.save((curves, update_interval, n_examples),
open(os.path.join(curves_path, f), 'wb'))
results = [
np.mean(curves['all']),
np.mean(curves['proportion']),
np.mean(curves['ngram']),
np.max(curves['all']),
np.max(curves['proportion']),
np.max(curves['ngram'])
]
to_write = params + results if train else test_params + results
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write(
'random_seed,n_neurons,n_train,excite,inhib,time,timestep,theta_plus,theta_decay,'
'intensity,progress_interval,update_interval,mean_all_activity,mean_proportion_weighting,'
'mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n'
)
else:
f.write(
'random_seed,n_neurons,n_train,n_test,excite,inhib,time,timestep,theta_plus,theta_decay,'
'intensity,progress_interval,update_interval,mean_all_activity,mean_proportion_weighting,'
'mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat(
[labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusions = {}
for scheme in predictions:
confusions[scheme] = confusion_matrix(labels, predictions[scheme])
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusions, os.path.join(confusion_path, f))
print()
def main(seed=0, n_train=60000, n_test=10000, inhib=250, kernel_size=(16,), stride=(2,), n_filters=25, crop=4, lr=0.01,
lr_decay=1, time=100, dt=1, theta_plus=0.05, theta_decay=1e-7, intensity=1, norm=0.2, 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, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train, inhib, time, dt,
theta_plus, theta_decay, intensity, norm, progress_interval, update_interval
]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train, n_test, inhib, time, dt,
theta_plus, theta_decay, intensity, norm, progress_interval, update_interval
]
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)
side_length = 28 - crop * 2
n_examples = n_train if train else n_test
network = load_network(os.path.join(params_path, model_name + '.pt'))
network.layers['X'] = Input(n=400)
network.layers['Y'] = DiehlAndCookNodes(
n=network.layers['Y'].n, thresh=network.layers['Y'].thresh, rest=network.layers['Y'].rest,
reset=network.layers['Y'].reset, theta_plus=network.layers['Y'].theta_plus,
theta_decay=network.layers['Y'].theta_decay
)
network.add_layer(network.layers['X'], name='X')
network.add_layer(network.layers['Y'], name='Y')
network.connections['X', 'Y'].source = network.layers['X']
network.connections['X', 'Y'].target = network.layers['Y']
network.connections['X', 'Y'].update_rule = NoOp(
connection=network.connections['X', 'Y'], nu=network.connections['X', 'Y'].nu
)
network.layers['Y'].theta_decay = 0
network.layers['Y'].theta_plus = 0
conv_size = network.connections['X', 'Y'].conv_size
locations = network.connections['X', 'Y'].locations
conv_prod = int(np.prod(conv_size))
n_neurons = n_filters * conv_prod
n_classes = 10
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
images, labels = dataset.get_test()
images *= intensity
images = images[:, crop:-crop, crop:-crop]
# Neuron assignments and spike proportions.
path = os.path.join(params_path, '_'.join(['auxiliary', model_name]) + '.pt')
assignments, proportions, rates, ngram_scores = torch.load(open(path, 'rb'))
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer], state_vars=['s'], time=time)
network.add_monitor(spikes[layer], name=f'{layer}_spikes')
# Train the network.
print('\nBegin black box adversarial attack.\n')
spike_ims = None
spike_axes = None
weights_im = None
inpt_ims = None
inpt_axes = None
max_iters = 25
delta = 0.1
epsilon = 0.1
for i in range(n_examples):
# Get next input sample.
original = images[i % len(images)].contiguous().view(-1)
label = labels[i % len(images)]
# Check if the image is correctly classified.
sample = poisson(datum=original, time=time)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
# Check for incorrect classification.
s = spikes['Y'].get('s').view(1, n_neurons, time)
prediction = ngram(spikes=s, ngram_scores=ngram_scores, n_labels=10, n=2).item()
if prediction != label:
continue
# Create adversarial example.
adversarial = False
while not adversarial:
adv_example = 255 * torch.rand(original.size())
sample = poisson(datum=adv_example, time=time)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
# Check for incorrect classification.
s = spikes['Y'].get('s').view(1, n_neurons, time)
prediction = ngram(spikes=s, ngram_scores=ngram_scores, n_labels=n_classes, n=2).item()
if prediction == label:
adversarial = True
j = 0
current = original.clone()
while j < max_iters:
# Orthogonal perturbation.
# perturb = orthogonal_perturbation(delta=delta, image=adv_example, target=original)
# temp = adv_example + perturb
# # Forward perturbation.
# temp = temp.clone() + forward_perturbation(epsilon * get_diff(temp, original), temp, adv_example)
# print(temp)
perturbation = torch.randn(original.size())
unnormed_source_direction = original - perturbation
source_norm = torch.norm(unnormed_source_direction)
source_direction = unnormed_source_direction / source_norm
dot = torch.dot(perturbation, source_direction)
perturbation -= dot * source_direction
perturbation *= epsilon * source_norm / torch.norm(perturbation)
D = 1 / np.sqrt(epsilon ** 2 + 1)
direction = perturbation - unnormed_source_direction
spherical_candidate = current + D * direction
spherical_candidate = torch.clamp(spherical_candidate, 0, 255)
new_source_direction = original - spherical_candidate
new_source_direction_norm = torch.norm(new_source_direction)
# length if spherical_candidate would be exactly on the sphere
length = delta * source_norm
# length including correction for deviation from sphere
deviation = new_source_direction_norm - source_norm
length += deviation
# make sure the step size is positive
length = max(0, length)
# normalize the length
length = length / new_source_direction_norm
candidate = spherical_candidate + length * new_source_direction
candidate = torch.clamp(candidate, 0, 255)
sample = poisson(datum=candidate, time=time)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
# Check for incorrect classification.
s = spikes['Y'].get('s').view(1, n_neurons, time)
prediction = ngram(spikes=s, ngram_scores=ngram_scores, n_labels=10, n=2).item()
# Optionally plot various simulation information.
if plot:
_input = original.view(side_length, side_length)
reconstruction = candidate.view(side_length, side_length)
_spikes = {
'X': spikes['X'].get('s').view(side_length ** 2, time),
'Y': spikes['Y'].get('s').view(n_neurons, time)
}
w = network.connections['X', 'Y'].w
spike_ims, spike_axes = plot_spikes(spikes=_spikes, ims=spike_ims, axes=spike_axes)
weights_im = plot_locally_connected_weights(
w, n_filters, kernel_size, conv_size, locations, side_length, im=weights_im
)
inpt_axes, inpt_ims = plot_input(
_input, reconstruction, label=labels[i], ims=inpt_ims, axes=inpt_axes
)
plt.pause(1e-8)
if prediction == label:
print('Attack failed.')
else:
print('Attack succeeded.')
adv_example = candidate
j += 1
network.reset_() # Reset state variables.
print('\nAdversarial attack complete.\n')
def main(seed=0, n_train=60000, n_test=10000, c_low=1, c_high=25, p_low=0.5, kernel_size=(16,), stride=(2,),
n_filters=25, crop=4, lr=0.01, lr_decay=1, time=100, dt=1, theta_plus=0.05, theta_decay=1e-7, intensity=1,
norm=0.2, 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, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train, c_low, c_high, p_low, time, dt,
theta_plus, theta_decay, intensity, norm, progress_interval, update_interval
]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, kernel_size, stride, n_filters, crop, lr, lr_decay, n_train, n_test, c_low, c_high, p_low, time, dt,
theta_plus, theta_decay, intensity, norm, progress_interval, update_interval
]
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)
side_length = 28 - crop * 2
n_inpt = side_length ** 2
input_shape = [side_length, side_length]
n_examples = n_train if train else n_test
n_classes = 10
if _pair(kernel_size) == input_shape:
conv_size = [1, 1]
else:
conv_size = (int((input_shape[0] - _pair(kernel_size)[0]) / _pair(stride)[0]) + 1,
int((input_shape[1] - _pair(kernel_size)[1]) / _pair(stride)[1]) + 1)
# Build network.
if train:
network = Network()
input_layer = Input(n=n_inpt, traces=True, trace_tc=5e-2)
output_layer = DiehlAndCookNodes(
n=n_filters * conv_size[0] * conv_size[1], traces=True, rest=-65.0, reset=-60.0,
thresh=-52.0, refrac=5, decay=1e-2, trace_tc=5e-2, theta_plus=theta_plus, theta_decay=theta_decay
)
input_output_conn = LocallyConnectedConnection(
input_layer, output_layer, kernel_size=kernel_size, stride=stride, n_filters=n_filters,
nu=[0, lr], update_rule=PostPre, wmin=0, wmax=1, norm=norm, input_shape=input_shape
)
w = torch.zeros(n_filters, *conv_size, n_filters, *conv_size)
for fltr1 in range(n_filters):
for fltr2 in range(n_filters):
if fltr1 != fltr2:
for j in range(conv_size[0]):
for k in range(conv_size[1]):
x1, y1 = fltr1 // np.sqrt(n_filters), fltr1 % np.sqrt(n_filters)
x2, y2 = fltr2 // np.sqrt(n_filters), fltr2 % np.sqrt(n_filters)
w[fltr1, j, k, fltr2, j, k] = max(-c_high, -c_low * np.sqrt(euclidean([x1, y1], [x2, y2])))
w = w.view(n_filters * conv_size[0] * conv_size[1], n_filters * conv_size[0] * conv_size[1])
recurrent_conn = Connection(output_layer, output_layer, w=w)
plt.matshow(w)
plt.colorbar()
network.add_layer(input_layer, name='X')
network.add_layer(output_layer, name='Y')
network.add_connection(input_output_conn, source='X', target='Y')
network.add_connection(recurrent_conn, source='Y', target='Y')
else:
network = load_network(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 = 0
network.layers['Y'].theta_plus = 0
conv_size = network.connections['X', 'Y'].conv_size
locations = network.connections['X', 'Y'].locations
conv_prod = int(np.prod(conv_size))
n_neurons = n_filters * conv_prod
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images *= intensity
images = images[:, crop:-crop, crop:-crop]
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
# Neuron assignments and spike proportions.
if train:
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))
ngram_scores = {}
else:
path = os.path.join(params_path, '_'.join(['auxiliary', model_name]) + '.pt')
assignments, proportions, rates, ngram_scores = torch.load(open(path, 'rb'))
if train:
best_accuracy = 0
# Sequence of accuracy estimates.
curves = {'all': [], 'proportion': [], 'ngram': []}
predictions = {
scheme: torch.Tensor().long() for scheme in curves.keys()
}
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer], state_vars=['s'], time=time)
network.add_monitor(spikes[layer], name=f'{layer}_spikes')
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
spike_ims = None
spike_axes = None
weights_im = None
# Calculate linear increase every update interval.
if train:
n_increase = int(p_low * n_examples) / update_interval
increase = (c_high - c_low) / n_increase
increases = 0
inhib = c_low
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 % update_interval == 0 and i > 0:
if train:
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
if increases < n_increase:
inhib = inhib + increase
print(f'\nIncreasing inhibition to {inhib}.\n')
w = torch.zeros(n_filters, *conv_size, n_filters, *conv_size)
for fltr1 in range(n_filters):
for fltr2 in range(n_filters):
if fltr1 != fltr2:
for j in range(conv_size[0]):
for k in range(conv_size[1]):
x1, y1 = fltr1 // np.sqrt(n_filters), fltr1 % np.sqrt(n_filters)
x2, y2 = fltr2 // np.sqrt(n_filters), fltr2 % np.sqrt(n_filters)
w[fltr1, j, k, fltr2, j, k] = max(-c_high, -c_low * np.sqrt(euclidean([x1, y1], [x2, y2])))
w = w.view(n_filters * conv_size[0] * conv_size[1], n_filters * conv_size[0] * conv_size[1])
network.connections['Y', 'Y'].w = w
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]], -1)
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples), open(os.path.join(curves_path, f), 'wb'))
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(params_path, '_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores), open(path, 'wb'))
best_accuracy = max([x[-1] for x in curves.values()])
# Assign labels to excitatory layer neurons.
assignments, proportions, rates = assign_labels(spike_record, current_labels, 10, rates)
# Compute ngram scores.
ngram_scores = update_ngram_scores(spike_record, current_labels, 10, 2, ngram_scores)
print()
# Get next input sample.
image = images[i % update_interval].contiguous().view(-1)
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
retries = 0
while spikes['Y'].get('s').sum() < 5 and retries < 3:
retries += 1
image *= 2
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
network.run(inpts=inpts, time=time)
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y'].get('s').t()
# Optionally plot various simulation information.
if plot:
_spikes = {
'X': spikes['X'].get('s').view(side_length ** 2, time),
'Y': spikes['Y'].get('s').view(n_filters * conv_prod, time)
}
spike_ims, spike_axes = plot_spikes(spikes=_spikes, ims=spike_ims, axes=spike_axes)
weights_im = plot_locally_connected_weights(
network.connections[('X', 'Y')].w, n_filters, kernel_size, conv_size, locations, side_length, im=weights_im
)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]], -1)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(params_path, '_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores), open(path, 'wb'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print('Average accuracies:\n')
for scheme in curves.keys():
print('\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save accuracy curves to disk.
to_write = ['train'] + params if train else ['test'] + params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save((curves, update_interval, n_examples), open(os.path.join(curves_path, f), 'wb'))
# Save results to disk.
results = [
np.mean(curves['all']), np.mean(curves['proportion']), np.mean(curves['ngram']),
np.max(curves['all']), np.max(curves['proportion']), np.max(curves['ngram'])
]
to_write = params + results if train else test_params + results
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write(
'random_seed,kernel_size,stride,n_filters,crop,lr,lr_decay,n_train,c_low,c_high,p_low,time,timestep,theta_plus,'
'theta_decay,intensity,norm,progress_interval,update_interval,mean_all_activity,'
'mean_proportion_weighting,mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n'
)
else:
f.write(
'random_seed,kernel_size,stride,n_filters,crop,lr,lr_decay,n_train,n_test,c_low,c_high,p_low,time,timestep,'
'theta_plus,theta_decay,intensity,norm,progress_interval,update_interval,mean_all_activity,'
'mean_proportion_weighting,mean_ngram,max_all_activity,max_proportion_weighting,max_ngram\n'
)
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat([labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusions = {}
for scheme in predictions:
confusions[scheme] = confusion_matrix(labels, predictions[scheme])
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusions, os.path.join(confusion_path, f))
def main(seed=0, n_train=60000, n_test=10000, inhib=100, kernel_size=(16,), stride=(2,), n_filters=25,
lr_decay=1, time=25, dt=1, theta_plus=0.05, theta_decay=1e-7, intensity=1, 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'
if len(kernel_size) == 1:
kernel_size = kernel_size[0]
else:
kernel_size = tuple(kernel_size)
if len(stride) == 1:
stride = stride[0]
else:
stride = tuple(stride)
params = [
seed, kernel_size, stride, n_filters, lr_decay, n_train, inhib, time, dt,
theta_plus, theta_decay, intensity, progress_interval, update_interval
]
model_name = '_'.join([str(x) for x in params])
if not train:
test_params = [
seed, kernel_size, stride, n_filters, lr_decay, n_train, n_test, inhib, time, dt,
theta_plus, theta_decay, intensity, progress_interval, update_interval
]
np.random.seed(seed)
if gpu:
torch.set_default_tensor_type('torch.cuda.FloatTensor')
torch.cuda.manual_seed_all(seed)
torch.manual_seed(seed)
n_examples = n_train if train else n_test
n_classes = 10
# Build network.
if train:
network = LocallyConnectedNetwork(
n_inpt=784, input_shape=[28, 28], kernel_size=kernel_size, stride=stride, n_filters=n_filters, inh=inhib,
dt=dt, nu=[0, (350 / time) * 1e-2], theta_plus=theta_plus, theta_decay=theta_decay, wmin=0.0,
wmax=1.0, norm=0.2
)
else:
network = load_network(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 = 0
network.layers['Y'].theta_plus = 0
conv_size = network.connections[('X', 'Y')].conv_size
locations = network.connections[('X', 'Y')].locations
conv_prod = int(np.prod(conv_size))
n_neurons = n_filters * conv_prod
# Voltage recording for excitatory and inhibitory layers.
voltage_monitor = Monitor(network.layers['Y'], ['v'], time=time)
network.add_monitor(voltage_monitor, name='output_voltage')
# Load MNIST data.
dataset = MNIST(data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images *= intensity
# Record spikes during the simulation.
spike_record = torch.zeros(update_interval, time, n_neurons)
# Neuron assignments and spike proportions.
if train:
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))
ngram_scores = {}
else:
path = os.path.join(params_path, '_'.join(['auxiliary', model_name]) + '.pt')
assignments, proportions, rates, ngram_scores = torch.load(open(path, 'rb'))
# Accuracy curves recording.
curves = {'all': [], 'proportion': [], 'ngram': []}
predictions = {
scheme: torch.Tensor().long() for scheme in curves.keys()
}
if train:
best_accuracy = 0
spikes = {}
for layer in set(network.layers):
spikes[layer] = Monitor(network.layers[layer], state_vars=['s'], time=time)
network.add_monitor(spikes[layer], name=f'{layer}_spikes')
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
spike_ims = None
spike_axes = None
weights_im = 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 % update_interval == 0 and i > 0:
if train:
network.connections['X', 'Y'].update_rule.nu[1] *= lr_decay
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, preds = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]], -1)
# Save accuracies to disk
to_write = ['train'] + params if train else ['test'] + params
to_write = [str(x) for x in to_write]
f = '_'.join(to_write) + '.pt'
torch.save((curves, update_interval, n_examples), open(os.path.join(curves_path, f), 'wb'))
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(params_path, '_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores), open(path, 'wb'))
best_accuracy = max([x[-1] for x in curves.values()])
# Assign labels to excitatory layer neurons.
assignments, proportions, rates = assign_labels(spike_record, current_labels, n_classes, rates)
# Compute ngram scores.
ngram_scores = update_ngram_scores(spike_record, current_labels, n_classes, 2, ngram_scores)
print()
# Get next input sample.
image = images[i].view(-1)
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X': sample}
# Run the network on the input.
network.run(inpts=inpts, time=time)
retries = 0
while spikes['Y'].get('s').sum() < 5 and retries < 3:
retries += 1
image *= 2
sample = poisson(datum=image, time=time, dt=dt)
inpts = {'X' : sample}
network.run(inpts=inpts, time=time)
# Add to spikes recording.
spike_record[i % update_interval] = spikes['Y'].get('s').t()
# Optionally plot various simulation information.
if plot:
_spikes = {'X': spikes['X'].get('s').view(28 ** 2, time),
'Y': spikes['Y'].get('s').view(n_filters * conv_prod, time)}
spike_ims, spike_axes = plot_spikes(spikes=_spikes, ims=spike_ims, axes=spike_axes)
weights_im = plot_locally_connected_weights(
network.connections[('X', 'Y')].w, n_filters, kernel_size, conv_size, locations, 28, im=weights_im
)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
i += 1
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
# Update and print accuracy evaluations.
curves, predictions = update_curves(
curves, current_labels, n_classes, spike_record=spike_record, assignments=assignments,
proportions=proportions, ngram_scores=ngram_scores, n=2
)
print_results(curves)
for scheme in preds:
predictions[scheme] = torch.cat([predictions[scheme], preds[scheme]], -1)
if train:
if any([x[-1] > best_accuracy for x in curves.values()]):
print('New best accuracy! Saving network parameters to disk.')
# Save network to disk.
network.save(os.path.join(params_path, model_name + '.pt'))
path = os.path.join(params_path, '_'.join(['auxiliary', model_name]) + '.pt')
torch.save((assignments, proportions, rates, ngram_scores), open(path, 'wb'))
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
print('Average accuracies:\n')
for scheme in curves.keys():
print('\t%s: %.2f' % (scheme, float(np.mean(curves[scheme]))))
# Save accuracies to disk
to_write = ['train'] + params if train else ['test'] + params
to_write = [str(x) for x in to_write]
f = '_'.join(to_write) + '.pt'
torch.save((curves, update_interval, n_examples), open(os.path.join(curves_path, f), 'wb'))
# Save results to disk.
results = [
np.mean(curves['all']), np.mean(curves['proportion']), np.mean(curves['ngram']),
np.max(curves['all']), np.max(curves['proportion']), np.max(curves['ngram'])
]
to_write = params + results if train else test_params + results
to_write = [str(x) for x in to_write]
name = 'train.csv' if train else 'test.csv'
if not os.path.isfile(os.path.join(results_path, name)):
with open(os.path.join(results_path, name), 'w') as f:
if train:
f.write('random_seed,kernel_size,stride,n_filters,'
'n_train,inhib,time,timestep,'
'theta_plus,theta_decay,intensity,'
'progress_interval,update_interval,mean_all_activity,'
'mean_proportion_weighting,mean_ngram,max_all_activity,'
'max_proportion_weighting,max_ngram\n')
else:
f.write('random_seed,kernel_size,stride,n_filters,'
'n_train,n_test,inhib,time,timestep,'
'theta_plus,theta_decay,intensity,'
'progress_interval,update_interval,mean_all_activity,'
'mean_proportion_weighting,mean_ngram,max_all_activity,'
'max_proportion_weighting,max_ngram\n')
with open(os.path.join(results_path, name), 'a') as f:
f.write(','.join(to_write) + '\n')
if labels.numel() > n_examples:
labels = labels[:n_examples]
else:
while labels.numel() < n_examples:
if 2 * labels.numel() > n_examples:
labels = torch.cat([labels, labels[:n_examples - labels.numel()]])
else:
labels = torch.cat([labels, labels])
# Compute confusion matrices and save them to disk.
confusions = {}
for scheme in predictions:
confusions[scheme] = confusion_matrix(labels, predictions[scheme])
to_write = ['train'] + params if train else ['test'] + test_params
f = '_'.join([str(x) for x in to_write]) + '.pt'
torch.save(confusions, os.path.join(confusion_path, f))
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
]
test_params = [
seed, n_neurons, n_train, n_test, 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_sqrt = int(np.ceil(np.sqrt(n_neurons)))
n_classes = 10
# Build network.
if train:
network = Network(dt=dt)
input_layer = RealInput(n=784, traces=True, trace_tc=5e-2)
network.add_layer(input_layer, name='X')
output_layer = DiehlAndCookNodes(
n=n_neurons, traces=True, rest=0, reset=1, thresh=1, refrac=0,
decay=1e-2, trace_tc=5e-2, theta_plus=theta_plus, theta_decay=theta_decay
)
network.add_layer(output_layer, name='Y')
readout = IFNodes(n=n_classes, reset=0, thresh=1)
network.add_layer(readout, name='Z')
w = torch.rand(784, n_neurons)
input_connection = Connection(
source=input_layer, target=output_layer, w=w,
update_rule=MSTDP, nu=lr, wmin=0, wmax=1, norm=78.4
)
network.add_connection(input_connection, source='X', target='Y')
w = -inhib * (torch.ones(n_neurons, n_neurons) - torch.diag(torch.ones(n_neurons)))
recurrent_connection = Connection(
source=output_layer, target=output_layer, w=w, wmin=-inhib, wmax=0
)
network.add_connection(recurrent_connection, source='Y', target='Y')
readout_connection = Connection(
source=network.layers['Y'], target=readout, w=torch.rand(n_neurons, n_classes), norm=10
)
network.add_connection(readout_connection, source='Y', target='Z')
else:
network = load_network(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 = 0
network.layers['Y'].theta_plus = 0
# Load MNIST data.
dataset = MNIST(path=data_path, download=True)
if train:
images, labels = dataset.get_train()
else:
images, labels = dataset.get_test()
images = images.view(-1, 784)
labels = labels.long()
spikes = {}
for layer in set(network.layers) - {'X'}:
spikes[layer] = Monitor(network.layers[layer], state_vars=['s'], time=time)
network.add_monitor(spikes[layer], name='%s_spikes' % layer)
# Train the network.
if train:
print('\nBegin training.\n')
else:
print('\nBegin test.\n')
inpt_axes = None
inpt_ims = None
spike_ims = None
spike_axes = None
weights_im = None
weights2_im = None
assigns_im = None
perf_ax = None
predictions = torch.zeros(update_interval).long()
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
# Get next input sample.
image = images[i % len(images)]
# Run the network on the input.
for j in range(time):
readout = network.layers['Z'].s
if readout[labels[i % len(labels)]]:
network.run(inpts={'X': image.unsqueeze(0)}, time=1, reward=1, a_minus=0, a_plus=1)
else:
network.run(inpts={'X': image.unsqueeze(0)}, time=1, reward=0)
label = spikes['Z'].get('s').sum(1).argmax()
predictions[i % update_interval] = label.long()
if i > 0 and i % update_interval == 0:
if i % len(labels) == 0:
current_labels = labels[-update_interval:]
else:
current_labels = labels[i % len(images) - update_interval:i % len(images)]
accuracy = 100 * (predictions == current_labels).float().mean().item()
print(f'Accuracy over last {update_interval} examples: {accuracy}')
# Optionally plot various simulation information.
if plot:
_spikes = {layer: spikes[layer].get('s') for layer in spikes}
input_exc_weights = network.connections['X', 'Y'].w
square_weights = get_square_weights(input_exc_weights.view(784, n_neurons), n_sqrt, 28)
exc_readout_weights = network.connections['Y', 'Z'].w
# _input = image.view(28, 28)
# reconstruction = inpts['X'].view(time, 784).sum(0).view(28, 28)
# square_assignments = get_square_assignments(assignments, n_sqrt)
spike_ims, spike_axes = plot_spikes(_spikes, ims=spike_ims, axes=spike_axes)
weights_im = plot_weights(square_weights, im=weights_im)
weights2_im = plot_weights(exc_readout_weights, im=weights2_im)
# inpt_axes, inpt_ims = plot_input(_input, reconstruction, label=labels[i], axes=inpt_axes, ims=inpt_ims)
# assigns_im = plot_assignments(square_assignments, im=assigns_im)
# perf_ax = plot_performance(curves, ax=perf_ax)
plt.pause(1e-8)
network.reset_() # Reset state variables.
print(f'Progress: {n_examples} / {n_examples} ({t() - start:.4f} seconds)')
if train:
print('\nTraining complete.\n')
else:
print('\nTest complete.\n')
