def test_original_biased_nonlin_semi_nmf(self):
auv = sio.loadmat(mat_file)
u, v = auv['u'], auv['v']
a = relu(u @ v)
bias_v = np.vstack((v, np.ones((1, v.shape[1]))))
old_loss = np_frobenius_norm(a, u @ v)
a_ph = tf.placeholder(tf.float64, shape=a.shape)
u_ph = tf.placeholder(tf.float64, shape=u.shape)
bias_v_ph = tf.placeholder(tf.float64, shape=bias_v.shape)
tf_bias_u, tf_v = nonlin_semi_nmf(a_ph, u_ph, bias_v_ph, use_bias=True, use_tf=True, num_calc_v=0)
init = tf.global_variables_initializer()
with tf.Session() as sess:
init.run()
start_time = time.time()
_u, _bias_v = sess.run([tf_bias_u, tf_v], feed_dict={a_ph: a, u_ph: u, bias_v_ph: bias_v})
end_time = time.time()
duration = end_time - start_time
_bias_u = np.hstack((_u, np.ones((_u.shape[0], 1))))
new_loss = np_frobenius_norm(a, relu(_bias_u @ _bias_v))
assert a.shape == (_bias_u @ _bias_v).shape
assert new_loss < old_loss, "new loss should be less than old loss."
print_format('TensorFlow', 'biased Nonlinear semi-NMF(NOT CALC v)', a, _bias_u, _bias_v, old_loss, new_loss,
duration)
def test_np_not_calc_v_biased_nonlin_semi_nmf(self):
auv = sio.loadmat(mat_file)
a, u, v = auv['a'], auv['u'], auv['v']
old_loss = np_frobenius_norm(a, u @ v)
biased_u = np.hstack((u, np.ones((u.shape[0], 1))))
start_time = time.time()
biased_u, v = nonlin_semi_nmf(a,
biased_u,
v,
use_bias=True,
num_calc_v=0)
end_time = time.time()
duration = end_time - start_time
bias_v = np.vstack((v, np.ones((1, v.shape[1]))))
new_loss = np_frobenius_norm(a, relu(biased_u @ bias_v))
assert a.shape == (biased_u @ bias_v).shape
assert new_loss < old_loss, "new loss should be less than old loss."
print('\n[Numpy]Solve biased Nonlinear semi-NMF(NOT CALCULATE v)\n\t'
'old loss {0}\n\t'
'new loss {1}\n\t'
'process duration {2}'.format(old_loss, new_loss, duration))
def test_tf_not_calc_v_nonlin_semi_nmf(self):
auv = sio.loadmat(mat_file)
a, u, v = auv['a'], auv['u'], auv['v']
old_loss = np_frobenius_norm(a, u @ v)
# [1000, 500]
a_ph = tf.placeholder(tf.float64, shape=a.shape)
# [1000, 201]
u_ph = tf.placeholder(tf.float64, shape=u.shape)
# [200, 500]
v_ph = tf.placeholder(tf.float64, shape=v.shape)
tf_u, tf_v = nonlin_semi_nmf(a_ph, u_ph, v_ph, use_tf=True, use_bias=False, num_calc_v=0, num_calc_u=1)
tf_loss = frobenius_norm(a_ph, tf.nn.relu(tf.matmul(tf_u, tf_v)))
init = tf.global_variables_initializer()
with tf.Session() as sess:
init.run()
start_time = time.time()
_u, _v, new_loss = sess.run([tf_u, tf_v, tf_loss], feed_dict={a_ph: a, u_ph: u, v_ph: v})
end_time = time.time()
duration = end_time - start_time
assert a.shape == (_u @ _v).shape
assert new_loss < old_loss, "new loss should be less than old loss."
print_format('TensorFlow', 'Nonlinear semi-NMF(NOT CALCLATE v)', a, u, v, old_loss, new_loss, duration)
def _autoencoder(self):
updates = []
layers = self._layers[:-1]
for i, layer in enumerate(layers):
a = layer.output # [3000, 784]
u = self._layers[i + 1].output
kernel = layer.kernel
temporary_shape = utility.transpose_shape(kernel) # [1000, 784]
if layer.use_bias:
temporary_shape[0] += 1
kernel = tf.concat((kernel, layer.bias[None, ...]), axis=0)
temporary_kernel = tf.get_variable(
'temporal_{}'.format(i),
temporary_shape,
dtype=tf.float64,
initializer=tf.contrib.layers.xavier_initializer(),
trainable=False)
u, _ = mf.semi_nmf(
a=a,
u=u,
v=temporary_kernel,
use_tf=True,
use_bias=layer.use_bias,
num_iters=1,
first_nneg=True,
)
# Not use activation (ReLU)
if not layer.activation:
_, v = mf.semi_nmf(
a=u,
u=a,
v=kernel,
use_tf=True,
use_bias=layer.use_bias,
num_iters=1,
first_nneg=True,
)
# Use activation (ReLU)
# else utility.get_op_name(layer.activation) == 'Relu':
else:
_, v = mf.nonlin_semi_nmf(
a=u,
u=a,
v=kernel,
use_tf=True,
use_bias=layer.use_bias,
num_calc_v=0,
num_calc_u=1,
first_nneg=True,
)
if layer.use_bias:
v, bias = utility.split_v_bias(v)
updates.append(layer.bias.assign(bias))
updates.append(layer.kernel.assign(v))
return tf.group(*updates)
def minimize(self, loss=None):
"""Construct the control dependencies for calculating neural net optimized.
Returns:
tf.no_op.
The import
"""
self._init(loss)
if self._use_autoencoder:
self._autoencoder()
a = self.labels
updates = []
# Reverse
layers = self._layers[::-1]
for i, layer in enumerate(layers):
_u = layer.output
v = layer.kernel
# Check whether u is a tensor or not.
# that is Recurrent output if it have dim more than 3.
if _u.shape.ndims >= 3 and not isinstance(layer.recurrent, tf.Variable):
u = _u[:, -1, :]
else:
u = _u
if isinstance(layer.recurrent, tf.Variable):
v = tf.concat((layer.kernel, layer.recurrent), axis=0)
if layer.use_bias:
v = tf.concat((v, layer.bias[None, ...]), axis=0)
# Not use activation (ReLU)
if not layer.activation:
u, v = mf.semi_nmf(a=a, u=u, v=v,
use_tf=True,
use_bias=layer.use_bias,
num_iters=1,
first_nneg=True,
)
# Use activation (ReLU)
else:
u, v = mf.nonlin_semi_nmf(a=a, u=u, v=v,
use_tf=True,
use_bias=layer.use_bias,
num_calc_v=1,
num_calc_u=1,
first_nneg=True,
)
if layer.use_bias:
v, bias = utility.split_v_bias(v)
updates.append(layer.bias.assign(bias))
updates.append(layer.kernel.assign(v))
a = tf.identity(_u)
return tf.group(*updates)
def minimize(self, loss=None):
"""Construct the control dependencies for calculating neural net optimized.
Returns:
tf.no_op.
The import
"""
self._init(loss)
if self._use_autoencoder:
self._autoencoder()
a = self.labels
updates = []
# Reverse
layers = self._layers[::-1]
for i, layer in enumerate(layers):
u = layer.output
v = layer.kernel
if layer.use_bias:
v = tf.concat((v, layer.bias[None, ...]), axis=0)
# Not use activation (ReLU)
if not layer.activation:
u, v = mf.semi_nmf(
a=a,
u=u,
v=v,
use_tf=True,
use_bias=layer.use_bias,
num_iters=1,
first_nneg=True,
)
# Use activation (ReLU)
else:
u, v = mf.nonlin_semi_nmf(
a=a,
u=u,
v=v,
use_tf=True,
use_bias=layer.use_bias,
num_calc_v=1,
num_calc_u=1,
first_nneg=True,
)
if layer.use_bias:
v, bias = utility.split_v_bias(v)
updates.append(layer.bias.assign(bias))
updates.append(layer.kernel.assign(v))
a = tf.identity(u)
return tf.group(*updates)
def test_np_not_calc_v_vanilla_nonlin_semi_nmf(self):
a = np.random.uniform(0., 1., size=(100, 100))
u = np.random.uniform(0., 1., size=(100, 300))
v = np.random.uniform(-1., 1., size=(300, 100))
old_loss = np_frobenius_norm(a, u @ v)
start_time = time.time()
u, v = nonlin_semi_nmf(a, u, v, use_bias=False, num_calc_v=0)
assert np.min(u) > 0, np.min(u)
end_time = time.time()
duration = end_time - start_time
new_loss = np_frobenius_norm(a, relu(u @ v))
assert a.shape == (u @ v).shape
assert new_loss < old_loss, "new loss should be less than old loss."
print_format('Numpy', 'Nonlinear semi-NMF(NOT CALCULATE v)', a, u, v, old_loss, new_loss, duration)
def test_np_not_calc_v_vanilla_nonlin_semi_nmf(self):
auv = sio.loadmat(mat_file)
a, u, v = auv['a'], auv['u'], auv['v']
old_loss = np_frobenius_norm(a, u @ v)
start_time = time.time()
u, v = nonlin_semi_nmf(a, u, v, use_bias=False, num_calc_v=0)
end_time = time.time()
duration = end_time - start_time
new_loss = np_frobenius_norm(a, relu(u @ v))
assert a.shape == (u @ v).shape
assert new_loss < old_loss, "new loss should be less than old loss."
print('\n[Numpy]Solve Nonlinear semi-NMF(NOT CALCULATE v)\n\t'
'old loss {0}\n\t'
'new loss {1}\n\t'
'process duration {2}'.format(old_loss, new_loss, duration))
def test_np_not_calc_v_biased_nonlin_semi_nmf(self):
a = np.random.uniform(0., 1., size=(100, 100))
u = np.random.uniform(0., 1., size=(100, 300))
v = np.random.uniform(-1., 1., size=(300, 100))
old_loss = np_frobenius_norm(a, u @ v)
bias_v = np.vstack((v, np.ones((1, v.shape[1]))))
start_time = time.time()
u, bias_v = nonlin_semi_nmf(a, u, bias_v, use_bias=True, num_calc_v=0)
assert np.min(u) > 0, np.min(u)
end_time = time.time()
duration = end_time - start_time
bias_u = np.hstack((u, np.ones((u.shape[0], 1))))
new_loss = np_frobenius_norm(a, relu(bias_u @ bias_v))
assert a.shape == (bias_u @ bias_v).shape
assert new_loss < old_loss, "new loss should be less than old loss."
print_format('Numpy', 'biased Nonlinear semi-NMF(NOT CALC v)', a, bias_u, bias_v, old_loss, new_loss, duration)
def test_tf_not_calc_v_biased_nonlin_semi_nmf(self):
auv = sio.loadmat(mat_file)
a, u, v = auv['a'], auv['u'], auv['v']
bias_u = np.hstack((u, np.ones((u.shape[0], 1))))
old_loss = np_frobenius_norm(a, u @ v)
a_ph = tf.placeholder(tf.float64, shape=a.shape)
bias_u_ph = tf.placeholder(tf.float64, shape=bias_u.shape)
v_ph = tf.placeholder(tf.float64, shape=v.shape)
tf_bias_u, tf_v = nonlin_semi_nmf(a_ph,
bias_u_ph,
v_ph,
num_calc_v=0,
use_bias=True,
use_tf=True)
init = tf.global_variables_initializer()
with tf.Session() as sess:
init.run()
start_time = time.time()
_bias_u, _v = sess.run([tf_bias_u, tf_v],
feed_dict={
a_ph: a,
bias_u_ph: bias_u,
v_ph: v
})
end_time = time.time()
duration = end_time - start_time
_bias_v = np.vstack((_v, np.ones((1, v.shape[1]))))
new_loss = np_frobenius_norm(a, relu(_bias_u @ _bias_v))
assert a.shape == (_bias_u @ _bias_v).shape
assert new_loss < old_loss, "new loss should be less than old loss."
print(
'\n[TensorFlow]Solve biased Nonlinear semi-NMF(NOT CALCULATE v)\n\t'
'old loss {0}\n\t'
'new loss {1}\n\t'
'process duration {2}'.format(old_loss, new_loss, duration))
def minimize(self, loss=None, pretrain=False):
"""Construct the control dependencies for calculating neural net optimized.
Returns:
tf.no_op.
The import
"""
self._init(loss)
# pre-train with auto encoder.
pretrain_op = self._autoencoder() if pretrain else tf.no_op()
a = self.labels
updates = []
# Reverse
layers = self._layers[::-1]
for i, layer in enumerate(layers):
u = layer.output
v = layer.kernel
if layer.use_bias:
v = tf.concat((v, layer.bias[None, ...]), axis=0)
# Not use activation (ReLU)
if not layer.activation:
u, v = mf.semi_nmf(
a=a,
u=u,
v=v,
use_tf=True,
use_bias=layer.use_bias,
num_iters=1,
first_nneg=True,
)
# Use activation (ReLU)
elif utility.get_op_name(layer.activation) == 'Relu':
u, v = mf.nonlin_semi_nmf(
a=a,
u=u,
v=v,
use_tf=True,
use_bias=layer.use_bias,
num_calc_v=1,
num_calc_u=1,
first_nneg=True,
)
# Use Softmax
elif utility.get_op_name(layer.activation) == 'Softmax':
print('used softmax!!')
u, v = mf.softmax_nmf(
a=a,
u=u,
v=v,
use_tf=True,
use_bias=layer.use_bias,
)
if layer.use_bias:
v, bias = utility.split_v_bias(v)
updates.append(layer.bias.assign(bias))
updates.append(layer.kernel.assign(v))
a = tf.identity(u)
return AttrDict(ae=pretrain_op, nmf=tf.group(*updates))
