def test_weight_clipping(w_clip, optimizer):
opt_ng = optimizer(0.1, weight_clip_value=w_clip)
# Set up data placeholders
C = ng.make_axis(20)
N = ng.make_axis(32, name='N')
data = ng.placeholder([C, N])
target = ng.placeholder([N])
# params to be updated using optimizer to be tested
# make sure initial values are higher than clip values
np_W = 10 * w_clip * (2 * np.random.rand(C.length) - 1)
W = ng.variable([C], initial_value=np_W)
# double check generated initial W value
assert np.max(np_W) > w_clip
assert np.min(np_W) < -w_clip
# Set up op graph
cost = ng.sum(target - ng.dot(W, data), out_axis=())
updated_weights = ng.sequential([opt_ng(cost), W])
epsilon = w_clip * 1e-3
# Set up the computation and run the "train" loop
with ExecutorFactory() as ex:
opt_ng_comp = ex.transformer.computation(updated_weights, data, target)
mock_dataset = data_generator(20, C.length, N.length)
for x, y in mock_dataset:
ng_W = opt_ng_comp(x, y) # updated weights for ngraph optimizer
assert np.max(ng_W) < w_clip + epsilon
assert np.min(ng_W) > -w_clip - epsilon
def test_variable():
input_axes = ng.make_axes([ng.make_axis(10), ng.make_axis(3)])
var = ng.variable(axes=input_axes)
assign_val = np.random.rand(10, 3)
var_assign = ng.AssignOp(tensor=var, val=assign_val)
var_seq = ng.sequential([var_assign, var])
var_comp = ng.computation(var_seq, "all")
results = dict()
weight_saver = Saver()
with closing(ngt.make_transformer()) as transformer:
var_func = transformer.add_computation(var_comp)
weight_saver.setup_save(transformer=transformer, computation=var_comp)
results['saved'] = var_func().copy()
weight_saver.save(filename="test_variable")
reassign_val = np.random.rand(10, 3)
var_reassign = ng.AssignOp(tensor=var, val=reassign_val)
var_recomp = ng.computation(var_reassign, "all")
var_read = ng.computation(var, "all")
with closing(ngt.make_transformer()) as restore_transformer:
var_recompfunc = restore_transformer.add_computation(var_recomp)
weight_saver.setup_restore(transformer=restore_transformer,
computation=var_recomp,
filename="test_variable")
var_readfunc = restore_transformer.add_computation(var_read)
var_recompfunc()
results['reassigned'] = var_readfunc().copy()
weight_saver.restore()
results['restored'] = var_readfunc().copy()
os.remove("test_variable.npz")
assert np.allclose(results['saved'], assign_val, atol=0)
assert np.allclose(results['reassigned'], reassign_val, atol=0)
assert np.allclose(results['saved'], results['restored'], atol=0)
def compare_optimizer_variable_select(opt_ng, opt_ref):
# Set up data placeholders
C = ng.make_axis(20)
N = ng.make_axis(32, name='N')
data = ng.placeholder([C, N])
target = ng.placeholder([N])
# params to be updated using optimizer to be tested
np_W1 = np.random.rand(C.length)
np_W2 = np.random.rand(C.length)
W1 = ng.variable([C], initial_value=np_W1)
W2 = ng.variable([C], initial_value=np_W2)
# Set up op graph
cost = ng.sum(target - ng.dot(W1, data) - ng.dot(W2, data), out_axis=())
updated_weights = ng.sequential([opt_ng(cost, variables=[W1]), W1])
# Set up the computation and run the "train" loop
with ExecutorFactory() as ex:
opt_ng_comp = ex.transformer.computation([updated_weights, W2], data, target)
mock_dataset = data_generator(20, C.length, N.length)
for x, y in mock_dataset:
[ng_W1, ng_W2] = opt_ng_comp(x, y) # updated weights for ngraph optimizer
np_W1 = opt_ref(x, np_W1) # updated weights for reference optimizer
ng.testing.assert_allclose(np_W1, ng_W1, rtol=1e-3)
ng.testing.assert_allclose(np_W2, ng_W2, rtol=1e-3)
def test_modify_state():
with ExecutorFactory() as ex:
N = ng.make_axis(3, name='N')
x_np = np.ones((N.length)) * 4
x = ng.variable([N], initial_value=x_np).named('x')
val = ng.sequential([ng.assign(x, x + x), x])
f = ex.executor(val)
x_val = f()
assert np.allclose(x_np + x_np, x_val)
def __call__(self, *args, **kwargs):
if len(self.ops) == 0:
self.beta_1 = ng.constant(self.beta_1, dtype=np.float32)
self.beta_2 = ng.constant(self.beta_2, dtype=np.float32)
self.t = ng.persistent_tensor(axes=(), initial_value=0)
self.t = ng.sequential([ng.assign(self.t, self.t + 1), self.t])
self.ell = self.lrate * ng.sqrt(1 - self.beta_2 ** self.t) / (1 - self.beta_1 ** self.t)
return super(Adam, self).__call__(*args, **kwargs)
def variable_update(self, variable, grad, scale_factor, weight_clip_value):
grad = clip_gradient_value(grad, self.gradient_clip_value)
state = ng.persistent_tensor(axes=grad.axes, initial_value=0.)
updates = ng.sequential([
ng.assign(state, state + ng.square(grad)),
ng.assign(variable,
clip_weight_value(variable - (scale_factor * self.lrate * grad) /
(ng.sqrt(state + self.epsilon)), weight_clip_value))
])
return updates
def test_sequential(N):
x = ng.variable([N], initial_value=0)
x0 = x + x
x1 = x + x
p = ng.sequential([x0, ng.assign(x, 2), x1, x0])
with ExecutorFactory() as ex:
x0_val, x1_val, p_val = ex.executor([x0, x1, p])()
assert x0_val == 0
assert x1_val == 4
assert p_val == 0
def test_sequential_side(M):
x1_np = 2
x2_np = 3
b_np = 1
x_np = np.array([1, 2, 3], dtype=np.float32)
x = ng.variable([M], initial_value=x_np)
x1 = ng.persistent_tensor(axes=(), initial_value=x1_np)
x2 = ng.persistent_tensor(axes=(), initial_value=x2_np)
x1_vo = ng.value_of(x1)
x2_vo = ng.value_of(x2)
b = ng.persistent_tensor(axes=(), initial_value=b_np)
y = ng.sequential([
x1_vo, x2_vo,
ng.assign(x1,
ng.sum(x, out_axes=()) + x1 * b + (1 - b)),
ng.assign(x2,
ng.mean(x, out_axes=()) + x2 * b + (1 - b)), x * 2
])
with ExecutorFactory() as ex:
main_effect = ex.executor((y, x1_vo, x2_vo, x1, x2))
current_values = ex.executor((x1, x2))
# Run main path #1
y_val, x1_init_val, x2_init_val, x1_final_val, x2_final_val = main_effect(
)
y_np = x_np * 2
assert np.allclose(y_val, y_np)
assert np.allclose(x1_init_val, x1_np)
assert np.allclose(x2_init_val, x2_np)
x1_np = np.sum(x_np) + x1_np * b_np + (1 - b_np)
x2_np = np.mean(x_np) + x2_np * b_np + (1 - b_np)
assert np.allclose(x1_final_val, x1_np)
assert np.allclose(x2_final_val, x2_np)
x1_val, x2_val = current_values()
assert np.allclose(x1_val, x1_np)
assert np.allclose(x2_val, x2_np)
# Run main path #2 (Should be the same as before)
y_val, x1_init_val, x2_init_val, x1_final_val, x2_final_val = main_effect(
)
y_np = x_np * 2
assert np.allclose(y_val, y_np)
assert np.allclose(x1_init_val, x1_np)
assert np.allclose(x2_init_val, x2_np)
x1_np = np.sum(x_np) + x1_np * b_np + (1 - b_np)
x2_np = np.mean(x_np) + x2_np * b_np + (1 - b_np)
assert np.allclose(x1_final_val, x1_np)
assert np.allclose(x2_final_val, x2_np)
def variable_update(self, variable, grad, scale_factor, weight_clip_value):
m = ng.persistent_tensor(axes=grad.axes, initial_value=0.)
v = ng.persistent_tensor(axes=grad.axes, initial_value=0.)
updates = ng.sequential([
ng.assign(m, m * self.beta_1 + (1 - self.beta_1) * grad),
ng.assign(v, v * self.beta_2 + (1 - self.beta_2) * grad * grad),
ng.assign(variable,
clip_weight_value(variable - (scale_factor * self.ell * m) /
(ng.sqrt(v) + self.epsilon), weight_clip_value))
])
return updates
def __call__(self, in_obj):
if not self.initialized:
w_axis = ng.make_axis()
self.weight = ng.variable(axes=[w_axis],
initial_value=2,
metadata={"label": LABELS["weight"]},
name="W")
self.side_effect = ng.persistent_tensor(axes=[w_axis],
initial_value=0)
return ng.sequential([ng.assign(self.side_effect, self.weight),
self.weight * in_obj])
def __call__(self, cost_func, variables=None, subgraph=None, warning=False):
"""
Arguments:
cost_func (Op): The cost function to optimize
variables (list of variables): List of variables to optimize
subgraph (SubGraph): A subgraph instance containing all variables to optimize
warning (bool): If True displays warning message if any variables
specified do not participate in batch cost computation
.. Note::
If subgraph is provided, the variables to optimize will be taken from it.
Otherwise, they can be provided explicitly by passing a list as `variables`.
If neither `subgraph` nor `variables` is provided, the variables to optimize will be
all trainable variables on which `cost` depends.
"""
all_updates = []
batch_cost = ng.sum(cost_func, out_axes=())
if cost_func.axes.batch_axis() is None:
batch_size = 1
else:
batch_size = cost_func.axes.batch_axis().length
# determine variables to optimize
if subgraph is not None:
if variables is not None:
raise ValueError("variables and subgraph cannot both be specified.")
variables = list(subgraph.variables.values())
if variables is None:
variables = batch_cost.variables()
elif variables is not None and warning is True:
all_variables = batch_cost.variables()
selected_variables = all_variables & set(variables)
if len(selected_variables) < len(variables):
logger.warn("not all selected variables participate in cost computation")
# gradients
grads = [ng.deriv(batch_cost, v) / batch_size for v in variables]
scale_factor = clip_gradient_norm(grads, self.gradient_clip_norm)
# updates
for variable, grad in zip(variables, grads):
updates = self.variable_update(variable, grad, scale_factor, self.weight_clip_value)
all_updates.append(updates)
updates = ng.doall(all_updates)
# grads = ng.doall(grads)
# clips = ng.doall([ng.assign(variable,
# clip_weight_value(variable, self.weight_clip_value))
# for variable in variables])
# return ng.sequential([grads, updates, clips, 0])
# return ng.sequential([grads, updates, 0])
return ng.sequential([updates, 0])
def test_scope_ops(input_placeholder):
"""
Test scope_ops creates a subgraph with correct attributes
"""
with scope_ops(name="foo") as subgraph:
w = ng.variable(ng.make_axis(), initial_value=1, name="W")
y = w * input_placeholder
z = y + 4
v1 = ng.persistent_tensor(w.axes, initial_value=0, name="effect1")
v2 = ng.persistent_tensor(w.axes, initial_value=0, name="effect2")
ng.sequential([ng.assign(v1, w), ng.assign(v2, w), z.named("output")])
assert len(subgraph.inputs) == 1
assert input_placeholder.unscoped_name in subgraph.inputs
assert len(subgraph.variables) == 1
assert "W" in subgraph.variables
assert len(subgraph.outputs) == 1
assert "output" in subgraph.outputs
assert len(subgraph.side_effects) == 2
def variable_update(self, variable, grad, scale_factor, weight_clip_value):
epsilon, decay = (self.epsilon, self.decay_rate)
grad = clip_gradient_value(grad, self.gradient_clip_value)
state = ng.persistent_tensor(axes=variable.axes, initial_value=1.)
velocity = ng.persistent_tensor(axes=variable.axes,
initial_value=0.).named(variable.name + '_vel')
updates = ng.sequential([
ng.assign(state, decay * state + (1.0 - decay) * ng.square(grad)),
ng.assign(velocity, velocity * self.momentum +
(self.lrate * scale_factor * grad / ng.sqrt(state + epsilon)) +
self.lrate * self.wdecay * variable),
ng.assign(variable, clip_weight_value(variable - velocity, weight_clip_value))
])
return updates
def test_sequential_reduce(M):
x = ng.variable([M], initial_value=1)
x0 = x + x
x1 = ng.sum(x0, out_axes=())
x2 = ng.sum(x0, out_axes=()) + x0
p = ng.sequential([x0, x1, x2])
with ExecutorFactory() as ex:
x0_val, x1_val, x2_val, p_val, x_val = ex.executor([x0, x1, x2, p,
x])()
x0_np = x_val + x_val
x1_np = np.sum(x0_np)
x2_np = x1_np + x0_np
assert np.allclose(x0_val, x0_np)
assert np.allclose(x1_val, x1_np)
assert np.allclose(x2_val, x2_np)
assert np.allclose(p_val, x2_np)
def variable_update(self, variable, grad, scale_factor, weight_clip_value):
updates = []
"""
for op in ng.Op.ordered_ops([grad]):
op_var = ng.persistent_tensor(axes=op.tensor.axes,
initial_value=0.).named(variable.name + '_' + op.name)
updates.append(ng.assign(op_var, op))
"""
velocity = ng.persistent_tensor(axes=variable.axes,
initial_value=0.).named(variable.name + '_vel')
clip_grad = clip_gradient_value(grad, self.gradient_clip_value)
lr = - self.lrate * (scale_factor * clip_grad + self.wdecay * variable)
updates.append(ng.assign(velocity, velocity * self.momentum_coef + lr))
if self.nesterov:
delta = (self.momentum_coef * velocity + lr)
else:
delta = velocity
updates.append(ng.assign(variable, clip_weight_value(variable + delta, weight_clip_value)))
return ng.sequential(updates)
def test_logreg():
# xs: (C, N), y: (N,)
xs = np.array([[0.52, 0.88, 0.52, 0.74], [1.12, -1.08, 0.06, -2.49],
[0.77, 0.15, -1.3, 1.39]])
ys = np.array([1, 1, 0, 1])
max_iter = 10
alpha = 0.1
thetas = np.array([0., 0., 0.])
np_logreg = NumpyLogreg(xs, ys, thetas)
C, N = ng.make_axis(length=3), ng.make_axis(length=4)
# input tensors
xs_v = ng.placeholder((C, N))
ys_v = ng.placeholder([N])
alpha_v = ng.placeholder(())
thetas_var = ng.variable([C], initial_value=thetas)
# define ops
ys_pred = ng.sigmoid(ng.dot(thetas_var, xs_v))
log_likelihoods = ng.log(ys_pred) * ys_v + ng.log(1 - ys_pred) * (1 - ys_v)
loss = -ng.sum(log_likelihoods, reduction_axes=[N])
grad_comp = ng.deriv(loss, thetas_var)
weight_update = ng.sequential(
[ng.assign(thetas_var, thetas_var - alpha_v * grad_comp), thetas_var])
# transformer
with ExecutorFactory() as ex:
train_eval_func = ex.executor([grad_comp, loss, weight_update], xs_v,
ys_v, alpha_v)
# evaluate
for i in range(max_iter):
grad_np, loss_np, thetas_np = np_logreg.optimize(alpha)
grad_ng, loss_ng, thetas_ng = train_eval_func(xs, ys, alpha)
ng.testing.assert_allclose(loss_np, loss_ng, rtol=1e-05, atol=1e-05, \
transformer_overwrite=False)
ng.testing.assert_allclose(grad_np, grad_ng, rtol=1e-05, atol=1e-05, \
transformer_overwrite=False)
ng.testing.assert_allclose(thetas_np, thetas_ng, rtol=1e-05, atol=1e-05, \
transformer_overwrite=False)
lr_schedule = {
'name': 'schedule',
'base_lr': 0.01,
'gamma': (1 / 250.)**(1 / 3.),
'schedule': [22, 44, 65]
}
optimizer = GradientDescentMomentum(lr_schedule,
0.0,
wdecay=0.0005,
iteration=inputs['iteration'])
train_prob = seq1(inputs['image'])
train_loss = ng.cross_entropy_multi(train_prob,
ng.one_hot(inputs['label'], axis=ax.Y))
batch_cost = ng.sequential(
[optimizer(train_loss),
ng.mean(train_loss, out_axes=())])
train_outputs = dict(batch_cost=batch_cost)
with closing(ngt.make_transformer()) as transformer:
train_computation = make_bound_computation(transformer, train_outputs,
inputs)
cbs = make_default_callbacks(transformer=transformer,
output_file=args.output_file,
frequency=args.iter_interval,
train_computation=train_computation,
total_iterations=args.num_iterations,
use_progress_bar=args.progress_bar)
loop_train(train_set, cbs)
