def test_nn():
p = 2
n = 1000
samples, cov = network.nn_network(p, n)
x = samples[:,0]
y = samples[:,1]
plot(x, y, 'o')
show()
def nn_lasso(r = 20):
fps = np.zeros(r)
fns = np.zeros(r)
norms = np.zeros(r)
for i in range(r):
samples, cov = network.nn_network()
t = 1e-1
fpr, fnr, fnorm = estimate_data(samples, cov, t)
fps[i] = fpr
fns[i] = fnr
norms[i] = fnorm
return fps.mean(), fns.mean(), norms.mean()
default="vgg13",
type=str)
ap.add_argument('--hidden_units',
type=int,
dest="hidden_units",
action="store",
default=120)
pa = ap.parse_args()
where = pa.data_dir
path = pa.save_dir
lr = pa.learning_rate
structure = pa.arch
dropout = pa.dropout
hidden_layer1 = pa.hidden_units
power = pa.gpu
epochs = pa.epochs
trainloader, v_loader, testloader, train_data = network.load_data(where)
model, optimizer, criterion = network.nn_network(structure, dropout,
hidden_layer1, lr, power)
network.train_network(model, optimizer, criterion, trainloader, v_loader,
epochs, 20, power)
network.save_checkpoint(model, train_data, path, structure, hidden_layer1,
dropout, lr)
print("All Set and Done. The Model is trained")
