training_dataset = []
# for the number of specified training samples
for i in range(training_samples):
# randomly select a training sample
# rand_sample = random.randint(0,n_classes-1)
# provide an even number of training samples
rand_sample = i % n_classes
# add the sample to the list of training samples
training_dataset.append(imgs[rand_sample])
# initialize the encoder
encoder = BernoulliEncoder(time=time, dt=dt)
# list of encoded images for random selection during training
encoded_train_inputs = []
# loop through encode each image type and store into a list of encoded images
for sample in training_dataset:
# encode the image
encoded_img = encoder(torch.flatten(sample["Image"]))
# encoded image input for the network
encoded_img_input = {input_layer_name: encoded_img}
# encoded image label
encoded_img_label = sample["Label"]
update_rule=MSTDPET,
nu=2e-2,
norm=0.15 * middle.n,
)
# Add all layers and connections to the network.
network.add_layer(inpt, name="X")
network.add_layer(middle, name="Y")
network.add_layer(out, name="Z")
network.add_connection(inpt_middle, source="X", target="Y")
network.add_connection(middle_out, source="Y", target="Z")
# Load SpaceInvaders environment.
environment = GymEnvironment(
"SpaceInvaders-v0",
BernoulliEncoder(time=int(network.dt), dt=network.dt),
history_length=2,
delta=4,
)
environment.reset()
# Plotting configuration.
plot_config = {
"data_step": 1,
"data_length": 10,
"reward_eps": 1,
"reward_window": 10,
"volts_type": "line"
}
# Build pipeline from specified components.
network.add_layer(layers[layer], name=layer)
network.add_connection(input_exc_conn, source="X", target="E")
network.add_connection(exc_readout_conn, source="E", target="R")
# Add all monitors to the network.
for layer in layers:
network.add_monitor(spikes[layer], name="%s_spikes" % layer)
if layer in voltages:
network.add_monitor(voltages[layer], name="%s_voltages" % layer)
# Load SpaceInvaders environment.
environment = GymEnvironment(
"SpaceInvaders-v0",
BernoulliEncoder(time=1, dt=network.dt),
history_length=2,
delta=4,
)
environment.reset()
# Build pipeline from specified components.
pipeline = EnvironmentPipeline(
network,
environment,
action_function=select_multinomial,
output="R",
plot_interval=plot_interval,
print_interval=print_interval,
render_interval=render_interval,
)