def with_LSTM():
dir = utils.set_dir('withLSTM')
conns = {(0, 1): circuit.SYNAPSE}
conns_opt = {(0, 1): circuit.get_syn_rand(True)}
dt = 0.5
t, i = datas.give_train(dt=dt)
i_1 = np.zeros(i.shape)
i_injs = np.stack([i, i_1], axis=2)
train = sim.simul(t, i_injs, [p, p], conns, n_out=[0, 1], show=False)
neurons = nr.Neurons([nr.BioNeuronTf(PyBioNeuron.get_random(), fixed=[], dt=dt), nr.BioNeuronTf(p, fixed='all', dt=dt)])
c = CircuitTf(neurons=neurons, synapses=conns_opt)
co = CircuitOpt(circuit=c)
co.optimize(dir, train=train, n_out=[0, 1], l_rate=(0.01, 9, 0.95))
def test_init(self):
dt = 0.5
p = nr.PyBioNeuron.get_random()
neurons = nr.Neurons([
nr.BioNeuronTf(init_p=[p for _ in range(2)], dt=dt),
nr.NeuronLSTM(dt=dt)
])
self.assertEqual(neurons.num, 3)
self.assertEqual(
neurons.init_state.all(),
np.stack([nr.PyBioNeuron.default_init_state for _ in range(3)],
axis=1).all())
with self.assertRaises(AttributeError):
neurons = nr.Neurons([
nr.BioNeuronTf(init_p=[p for _ in range(2)], dt=0.1),
nr.NeuronLSTM(dt=0.2)
])
def run():
name = sys.argv[1]
# plt.rcParams['figure.facecolor'] = 'Indigo'
# c = circuit.CircuitFix([p for _ in range(9)], synapses=syns, gaps=gaps, labels=labels)
# c.plot()
t, i = datas.full4(dt=dt, nb_neuron_zero=5)
i[:, :, :] = i[:, :, [0, 1, 4, 5, 6, 7, 8, 2, 3]]
_, itest = datas.full4_test(dt=dt, nb_neuron_zero=5)
itest[:, :, :] = itest[:, :, [0, 1, 4, 5, 6, 7, 8, 2, 3]]
dir = utils.set_dir('Tapwith_' + name)
n_out = [4, 5]
train = sim.simul(pars=[p for _ in range(9)],
t=t,
i_injs=i,
synapses=syns,
gaps=gaps,
n_out=n_out,
suffix='train',
labels=labels)
test = sim.simul(pars=[p for _ in range(9)],
t=t,
i_injs=itest,
synapses=syns,
gaps=gaps,
n_out=n_out,
labels=labels,
suffix='test')
# n = nr.BioNeuronTf([rand() for _ in range(9)], dt=dt)
n = nr.Neurons([
nr.NeuronLSTM(dt=dt),
nr.NeuronLSTM(dt=dt),
nr.BioNeuronTf([p for _ in range(5)], dt=dt),
nr.NeuronLSTM(dt=dt),
nr.NeuronLSTM(dt=dt)
])
ctf = CircuitTf(n,
synapses=syns_opt[0],
gaps=gaps_opt[0],
labels=labels,
commands={4, 5},
sensors={0, 1, 7, 8})
ctf.plot(save=True)
exit()
# ctf = CircuitTf.create_random(neurons = n, n_neuron=9, dt=dt, syn_keys={k: v['E']>-60 for k,v in syns.items()}, gap_keys=gaps.keys(), labels=labels, commands={4, 5},
# sensors={0, 1, 7, 8}, n_rand=n_parallel)
copt = CircuitOpt(circuit=ctf)
copt.optimize(subdir=dir,
train=train,
test=test,
n_out=[4, 5],
l_rate=(0.1, 9, 0.95))
def test(nb_neuron, conns, conns_opt, dir, t, i_injs, n_out=[1]):
pars = [p for _ in range(nb_neuron)]
dir = utils.set_dir(dir)
print("Feed with current of shape : ", i_injs.shape)
# train = sim.simul(t, i_injs, pars, conns, n_out=n_out, show=False)
n = nr.BioNeuronTf(init_p=pars, dt=t[1]-t[0])
cr = CircuitTf(n, synapses=conns_opt)
cr.plot(save=True);exit()
c = CircuitOpt(cr)
c.optimize(dir, n_out=n_out, train=train)
def test_settings(self):
pars = [p for _ in range(n_neuron)]
conns_opt = {
(0, 1): odynn.circuit.get_syn_rand(False),
(1, 0): odynn.circuit.get_syn_rand(False)
}
co = CircuitOpt(
cr.CircuitTf(nr.BioNeuronTf(pars, dt=dt), synapses=conns_opt))
train = [np.zeros(2), np.zeros(2), [None, None, np.zeros(4)]]
co.l_rate = (0.1, 0.1, 0.1)
co.n_batch = 3
w = (1., 0)
co.settings(w, train)
def test_init(self):
class opt(optim.Optimizer):
def _build_loss(self, w):
pass
nr = neuron.BioNeuronTf(n_rand=3)
op = opt(nr)
self.assertEqual(op._parallel, nr.num)
self.assertEqual(nr.num, 3)
c = circuit.CircuitTf.create_random(2, syn_keys={(0,1):True}, n_rand=7)
op = opt(c)
self.assertEqual(op._parallel, c.num)
self.assertEqual(c.num, 7)
def test_loss(self):
pars = [p for _ in range(n_neuron)]
conns_opt = {
(0, 1): odynn.circuit.get_syn_rand(False),
(1, 0): odynn.circuit.get_syn_rand(False)
}
co = CircuitOpt(
cr.CircuitTf(nr.BioNeuronTf(pars, dt=dt), synapses=conns_opt))
res = tf.zeros(
(len(t), len(nr.PyBioNeuron.default_init_state), 3, n_neuron))
ys_ = [
tf.placeholder(
shape=(len(t), 3, n_neuron), dtype=tf.float32, name="test")
] + [
tf.placeholder(
shape=(len(t), 3, n_neuron), dtype=tf.float32, name="test")
for _ in nr.PyBioNeuron.ions.items()
]
w = [1] + [1 for _ in nr.PyBioNeuron.ions.items()]
co.n_out = list(range(n_neuron))
co._build_loss(res, ys_, w)
import numpy as np from odynn import utils, nsimul, neuron, noptim #This file defines the model we will use from odynn.models import cfg_model dt = 1. folder = 'Example' # Function to call to set the target directories for plots and saved files dir = utils.set_dir(folder) #Definition of time and 2 input currents t = np.arange(0., 1200., dt) i_inj1 = 10. * ((t > 200) & (t < 600)) + 20. * ((t > 800) & (t < 1000)) i_inj2 = 5. * ((t > 200) & (t < 300)) + 30. * ((t > 500) & (t < 1000)) i_injs = np.stack([i_inj1, i_inj2], axis=-1) #10 random initial parameters params = [cfg_model.NEURON_MODEL.get_random() for _ in range(10)] neuron = neuron.BioNeuronTf(params, dt=dt) #This function will take the default parameters of the used model if none is given train = nsimul.simul(t=t, i_inj=i_injs, show=True) #Optimization optimizer = noptim.NeuronOpt(neuron) optimizer.optimize(dir=dir, train=train)
def test_opt_circuits(self):
print('one target'.center(40, '#'))
n_out = [1]
train = csim.simul(t=t,
i_injs=i_injs,
pars=pars,
synapses=conns,
n_out=n_out,
show=False)
co = CircuitOpt(
cr.CircuitTf(nr.BioNeuronTf(pars, dt=dt), synapses=conns_opt))
co.optimize(dir, n_out=n_out, train=train, epochs=1, plot=plot)
optim.get_best_result(dir)
self.assertEqual(co._loss.shape, ())
print('one target parallel'.center(40, '#'))
co = CircuitOpt(
cr.CircuitTf(nr.BioNeuronTf(n_rand=n_neuron, dt=dt),
synapses=conns_opt_parallel))
co.optimize(dir,
n_out=n_out,
train=train,
test=train,
epochs=1,
plot=plot,
evol_var=evol_var)
self.assertEqual(co._loss.shape, (10, ))
print('several targets'.center(40, '#'))
n_out = [0, 1]
train = csim.simul(t=t,
i_injs=i_injs,
pars=pars,
synapses=conns,
n_out=n_out,
show=False)
co = CircuitOpt(
cr.CircuitTf(nr.BioNeuronTf(pars, dt=dt), synapses=conns_opt))
co.optimize(dir,
n_out=n_out,
train=train,
epochs=1,
w_n=(1, 2),
plot=plot,
evol_var=evol_var)
self.assertEqual(co._loss.shape, ())
print('several targets parallel'.center(40, '#'))
co = CircuitOpt(
cr.CircuitTf.create_random(
n_neuron=2, syn_keys={k: False
for k in conns.keys()}, dt=dt))
co.optimize(dir,
n_out=n_out,
train=train,
epochs=1,
w_n=(1., 0.2),
plot=plot,
evol_var=evol_var)
self.assertEqual(co._loss.shape, (10, ))
print('1 LSTM'.center(40, '#'))
neurons = nr.Neurons(
[nr.NeuronLSTM(dt=dt),
nr.BioNeuronTf(p, fixed='all', dt=dt)])
c = cr.CircuitTf(neurons=neurons, synapses=conns_opt)
co = CircuitOpt(circuit=c)
co.optimize(dir,
train=train,
n_out=[0, 1],
l_rate=(0.01, 9, 0.95),
epochs=1,
plot=plot,
evol_var=evol_var)
print('2 LSTM'.center(40, '#'))
neurons = nr.Neurons([nr.NeuronLSTM(dt=dt), nr.NeuronLSTM(dt=dt)])
c = cr.CircuitTf(neurons=neurons, synapses=conns_opt)
co = CircuitOpt(circuit=c)
co.optimize(dir,
train=train,
n_out=[0, 1],
l_rate=(0.01, 9, 0.95),
epochs=1,
plot=plot,
evol_var=evol_var)
conns_opt[(0, 2)] = odynn.circuit.get_syn_rand()
with self.assertRaises(AttributeError):
c = cr.CircuitTf(neurons=neurons, synapses=conns_opt)
co = CircuitOpt(circuit=c)
co.optimize(dir,
train=train,
n_out=[0, 1],
l_rate=(0.01, 9, 0.95),
epochs=1,
plot=plot,
evol_var=evol_var)
print('2 bio + 1 LSTM'.center(40, '#'))
neurons = nr.Neurons([
nr.BioNeuronTf(init_p=[p for _ in range(2)], dt=dt),
nr.NeuronLSTM(dt=dt)
])
c = cr.CircuitTf(neurons=neurons, synapses=conns_opt)
co = CircuitOpt(circuit=c)
train[1] = i_injs3
co.optimize(dir,
train=train,
n_out=[0, 1],
l_rate=(0.01, 9, 0.95),
epochs=1,
plot=plot,
evol_var=evol_var)