Example #1
0
# --- Run model in Nengo
presentation_time = 0.2

model = nengo.Network()
with model:
    u = nengo.Node(nengo.processes.PresentInput(X_test, presentation_time))
    seq = SequentialNetwork(kmodel, synapse=nengo.synapses.Alpha(0.005))
    nengo.Connection(u, seq.input, synapse=None)

    input_p = nengo.Probe(u)
    output_p = nengo.Probe(seq.output)

    # --- image display
    image_shape = kmodel.input_shape[1:]
    display_f = image_display_function(image_shape)
    display_node = nengo.Node(display_f, size_in=u.size_out)
    nengo.Connection(u, display_node, synapse=None)

    # --- output spa display
    vocab_names = ['ZERO', 'ONE', 'TWO', 'THREE', 'FOUR',
                   'FIVE', 'SIX', 'SEVEN', 'EIGHT', 'NINE']
    vocab_vectors = np.eye(len(vocab_names))

    vocab = nengo.spa.Vocabulary(len(vocab_names))
    for name, vector in zip(vocab_names, vocab_vectors):
        vocab.add(name, vector)

    config = nengo.Config(nengo.Ensemble)
    config[nengo.Ensemble].neuron_type = nengo.Direct()
    with config:
# solver = nengo.solvers.LstsqL2(reg=0.0001)

presentation_time = 0.1

with nengo.Network(seed=3) as model:
    u = nengo.Node(nengo.processes.PresentInput(X_test, presentation_time))
    a = nengo.Ensemble(n_hid, n_vis, **ens_params)
    v = nengo.Node(size_in=n_out)
    nengo.Connection(u, a, synapse=None)
    conn = nengo.Connection(
        a, v, synapse=None,
        eval_points=X_train, function=train_targets, solver=solver)

    # --- image display
    image_shape = (1, 28, 28)
    display_f = image_display_function(image_shape, offset=1, scale=128)
    display_node = nengo.Node(display_f, size_in=u.size_out)
    nengo.Connection(u, display_node, synapse=None)

    # --- output spa display
    vocab_names = ['ZERO', 'ONE', 'TWO', 'THREE', 'FOUR',
                   'FIVE', 'SIX', 'SEVEN', 'EIGHT', 'NINE']
    vocab_vectors = np.eye(len(vocab_names))

    vocab = nengo.spa.Vocabulary(len(vocab_names))
    for name, vector in zip(vocab_names, vocab_vectors):
        vocab.add(name, vector)

    config = nengo.Config(nengo.Ensemble)
    config[nengo.Ensemble].neuron_type = nengo.Direct()
    with config:
Example #3
0
                               dimensions=env_iface.n_actions,
                               radius=actor_radius)

    sensor_conn = nengo.Connection(sensor, sensor_net)

    sensor_srf_conn = nengo.Connection(sensor_net.neurons,
                                       srf_net.exc.neurons,
                                       synapse=nengo.Lowpass(tau),
                                       transform=np.eye(n_input) *
                                       srf_params['w_input'])

    srf_actor_conn = nengo.Connection(
        srf_net.output.neurons,
        actor_net.neurons,
        synapse=nengo.Lowpass(tau),
        transform=np.eye(n_actor, n_place) * srf_params['w_actor'],
        learning_rule_type=HSP(learning_rate=2e-4))

    step_node = nengo.Node(env_iface.step, size_in=env_iface.n_actions)

    nengo.Connection(actor_net, step_node, synapse=fast_tau)

    display_func = image_display_function(image_shape)
    display_node = nengo.Node(display_func, size_in=sensor.size_out)
    nengo.Connection(sensor, display_node, synapse=None)

#dt = 0.01
#t_end = 10
#with nengo.Simulator(model, optimize=True, dt=dt, progress_bar=TerminalProgressBar()) as sim:
#    sim.run(np.max(t_end))

# --- Run model in Nengo
presentation_time = 0.2

model = nengo.Network()
with model:
    u = nengo.Node(nengo.processes.PresentInput(X_test, presentation_time))
    ccnet = CudaConvnetNetwork(cc_model, synapse=nengo.synapses.Alpha(0.001))
    nengo.Connection(u, ccnet.inputs['data'], synapse=None)

    # input_p = nengo.Probe(u)
    output_p = nengo.Probe(ccnet.output)

    # --- image display
    display_f = image_display_function(image_shape, scale=1., offset=data_mean)
    display_node = nengo.Node(display_f, size_in=u.size_out)
    nengo.Connection(u, display_node, synapse=None)

    # --- output spa display
    vocab_names = spasafe_names(label_names)
    vocab_vectors = np.eye(len(vocab_names))

    vocab = nengo.spa.Vocabulary(len(vocab_names))
    for name, vector in zip(vocab_names, vocab_vectors):
        vocab.add(name, vector)

    config = nengo.Config(nengo.Ensemble)
    config[nengo.Ensemble].neuron_type = nengo.Direct()
    with config:
        output = nengo.spa.State(len(vocab_names), subdimensions=10, vocab=vocab)
Example #5
0
cc_model = load_model_pickle('ilsvrc2012-lif-48.pkl')

# --- Run model in Nengo
presentation_time = 0.2

model = nengo.Network()
with model:
    u = nengo.Node(nengo.processes.PresentInput(X_test, presentation_time))
    ccnet = CudaConvnetNetwork(cc_model, synapse=nengo.synapses.Alpha(0.001))
    nengo.Connection(u, ccnet.inputs['data'], synapse=None)

    # input_p = nengo.Probe(u)
    output_p = nengo.Probe(ccnet.output)

    # --- image display
    display_f = image_display_function(image_shape, scale=1., offset=data_mean)
    display_node = nengo.Node(display_f, size_in=u.size_out)
    nengo.Connection(u, display_node, synapse=None)

    # --- output spa display
    vocab_names = spasafe_names(label_names)
    vocab_vectors = np.eye(len(vocab_names))

    vocab = nengo.spa.Vocabulary(len(vocab_names))
    for name, vector in zip(vocab_names, vocab_vectors):
        vocab.add(name, vector)

    config = nengo.Config(nengo.Ensemble)
    config[nengo.Ensemble].neuron_type = nengo.Direct()
    with config:
        output = nengo.spa.State(len(vocab_names),