def run(train_data, test_data):
batch_size = 10
n_samples = np.array(train_data).shape[0]
n_batches = int(np.ceil(float(n_samples) / batch_size))
batch_slices = list(
gen_even_slices(n_batches * batch_size, n_batches, n_samples))
nodes = [50, 75, 100, 150]
for item in nodes:
errors = []
model = BernoulliRBM(n_components=item,
learning_rate=0.1,
batch_size=10,
n_iter=1,
random_state=None,
verbose=1)
for _ in range(20):
for batch_slice in batch_slices:
model.partial_fit(train_data[batch_slice])
errors.append(percent_error(model.gibbs(test_data), test_data))
plot.plot_points(errors)
plot.plot_heatmap(reformat_data(test_data[0]))
plot.plot_heatmap(reformat_data(model.gibbs(test_data)[0]))
if item == 50 or item == 100:
plot.plot_heatmap(model.__dict__['components_'].reshape(item, 784))
def train_rbm_pcd(x_train, x_val, n_hidden, lr, inftype, n_iter=1000):
assert n_iter > 100 # we checkpoint every 100 iterations
rbm = BernoulliRBM(
n_components=n_hidden,
learning_rate=lr,
batch_size=x_train.shape[0],
n_iter=n_iter,
verbose=0,
)
best_score, best_rbm = np.inf, None
for it in range(n_iter):
rbm.partial_fit(x_train)
if (it + 1) % 20 == 0: # checkpoint every 20
score = test_rbm_pcd(
x_val,
rbm.components_,
rbm.intercept_hidden_,
rbm.intercept_visible_,
inftype,
)
if score < best_score:
best_score = score
best_rbm = (
rbm.components_.copy(),
rbm.intercept_hidden_.copy(),
rbm.intercept_visible_.copy(),
)
return best_rbm, best_score
def test_small_sparse_partial_fit():
for sparse in [csc_matrix, csr_matrix]:
X_sparse = sparse(Xdigits[:100])
X = Xdigits[:100].copy()
rbm1 = BernoulliRBM(n_components=64, learning_rate=0.1, batch_size=10, random_state=9)
rbm2 = BernoulliRBM(n_components=64, learning_rate=0.1, batch_size=10, random_state=9)
rbm1.partial_fit(X_sparse)
rbm2.partial_fit(X)
assert_almost_equal(rbm1.score_samples(X).mean(), rbm2.score_samples(X).mean(), decimal=0)
def test_partial_fit():
X = Xdigits.copy()
rbm = BernoulliRBM(n_components=64, learning_rate=0.1, batch_size=20, random_state=9)
n_samples = X.shape[0]
n_batches = int(np.ceil(float(n_samples) / rbm.batch_size))
batch_slices = np.array_split(X, n_batches)
for i in range(7):
for batch in batch_slices:
rbm.partial_fit(batch)
assert_almost_equal(rbm.score_samples(X).mean(), -21.0, decimal=0)
assert_array_equal(X, Xdigits)
def test_partial_fit():
X = Xdigits.copy()
rbm = BernoulliRBM(n_components=64, learning_rate=0.1,
batch_size=20, random_state=9)
n_samples = X.shape[0]
n_batches = int(np.ceil(float(n_samples) / rbm.batch_size))
batch_slices = np.array_split(X, n_batches)
for i in range(7):
for batch in batch_slices:
rbm.partial_fit(batch)
assert_almost_equal(rbm.score_samples(X).mean(), -21., decimal=0)
assert_array_equal(X, Xdigits)
def test_small_sparse_partial_fit():
for sparse in [csc_matrix, csr_matrix]:
X_sparse = sparse(Xdigits[:100])
X = Xdigits[:100].copy()
rbm1 = BernoulliRBM(n_components=64, learning_rate=0.1,
batch_size=10, random_state=9)
rbm2 = BernoulliRBM(n_components=64, learning_rate=0.1,
batch_size=10, random_state=9)
rbm1.partial_fit(X_sparse)
rbm2.partial_fit(X)
assert_almost_equal(rbm1.score_samples(X).mean(),
rbm2.score_samples(X).mean(),
decimal=0)
learning_rate=0.01,
verbose=1,
n_iter=30)
RBM2 = BernoulliRBM(n_components=100,
batch_size=10,
learning_rate=0.01,
verbose=1,
n_iter=30)
for i, rev_theta in enumerate(np.linspace(0.1, 1, 10)):
theta = 1 - rev_theta
print "Preentrenando modelo para theta=", theta
print "Leyendo batch", i + 1
Xtr_ns = load_single_NORB_train_val(".", i + 1, onlyx=True)
Xtr_ns = scale_data(Xtr_ns)
RBM1.partial_fit(Xtr_ns)
Xtr_ns2 = RBM1.transform(Xtr_ns)
print "..."
Xtr_ns2 = scale_data(Xtr_ns2)
RBM2.partial_fit(Xtr_ns2)
del Xtr_ns, Xtr_ns2
print "..."
joblib.dump(RBM1, "2/RBM1_512_" + str(theta) + ".pkl")
joblib.dump(RBM2, "2/RBM2_512_" + str(theta) + ".pkl")
# Entrenar usando RBM
accuracies = []
activation = 'tanh'
for i, theta in enumerate(np.linspace(0.1, 1, 10)):
print "Analizando theta =", theta
