def test_record_good():
"""
Tests that when we record a sequence of events, then
repeat it exactly, the Record class:
1) Records it correctly
2) Does not raise any errors
"""
# Record a sequence of events
output = StringIO()
recorder = Record(file_object=output, replay=False)
num_lines = 10
for i in range(num_lines):
recorder.handle_line(str(i) + '\n')
# Make sure they were recorded correctly
output_value = output.getvalue()
assert output_value == ''.join(str(i) + '\n' for i in range(num_lines))
# Make sure that the playback functionality doesn't raise any errors
# when we repeat them
output = StringIO(output_value)
playback_checker = Record(file_object=output, replay=True)
for i in range(num_lines):
playback_checker.handle_line(str(i) + '\n')
def test_record_bad():
"""
Tests that when we record a sequence of events, then
do something different on playback, the Record class catches it.
"""
# Record a sequence of events
output = StringIO()
recorder = Record(file_object=output, replay=False)
num_lines = 10
for i in range(num_lines):
recorder.handle_line(str(i) + '\n')
# Make sure that the playback functionality doesn't raise any errors
# when we repeat some of them
output_value = output.getvalue()
output = StringIO(output_value)
playback_checker = Record(file_object=output, replay=True)
for i in range(num_lines // 2):
playback_checker.handle_line(str(i) + '\n')
# Make sure it raises an error when we deviate from the recorded sequence
try:
playback_checker.handle_line('0\n')
except MismatchError:
return
raise AssertionError("Failed to detect mismatch between recorded sequence "
" and repetition of it.")
def test_record_mode_bad():
"""
Like test_record_bad, but some events are recorded by the
theano RecordMode, as is the event that triggers the mismatch
error.
"""
# Record a sequence of events
output = StringIO()
recorder = Record(file_object=output, replay=False)
record_mode = RecordMode(recorder)
i = iscalar()
f = function([i], i, mode=record_mode, name='f')
num_lines = 10
for i in range(num_lines):
recorder.handle_line(str(i) + '\n')
f(i)
# Make sure that the playback functionality doesn't raise any errors
# when we repeat them
output_value = output.getvalue()
output = StringIO(output_value)
playback_checker = Record(file_object=output, replay=True)
playback_mode = RecordMode(playback_checker)
i = iscalar()
f = function([i], i, mode=playback_mode, name='f')
for i in range(num_lines // 2):
playback_checker.handle_line(str(i) + '\n')
f(i)
# Make sure a wrong event causes a MismatchError
try:
f(0)
except MismatchError:
return
raise AssertionError("Failed to detect a mismatch.")
def run(replay, log=None):
if not replay:
log = StringIO()
else:
log = StringIO(log)
record = Record(replay=replay, file_object=log)
disturb_mem.disturb_mem()
mode = RecordMode(record=record)
b = sharedX(np.zeros((2, )), name='b')
channels = OrderedDict()
disturb_mem.disturb_mem()
v_max = b.max(axis=0)
v_min = b.min(axis=0)
v_range = v_max - v_min
updates = []
for i, val in enumerate([
v_max.max(),
v_max.min(),
v_range.max(),
]):
disturb_mem.disturb_mem()
s = sharedX(0., name='s_' + str(i))
updates.append((s, val))
for var in theano.gof.graph.ancestors(update for _, update in updates):
if var.name is not None and var.name is not 'b':
if var.name[0] != 's' or len(var.name) != 2:
var.name = None
for key in channels:
updates.append((s, channels[key]))
f = theano.function([],
mode=mode,
updates=updates,
on_unused_input='ignore',
name='f')
for output in f.maker.fgraph.outputs:
mode.record.handle_line(var_descriptor(output) + '\n')
disturb_mem.disturb_mem()
f()
mode.record.f.flush()
if not replay:
return log.getvalue()
def test_record_mode_good():
"""
Like test_record_good, but some events are recorded by the
theano RecordMode. We don't attempt to check the
exact string value of the record in this case.
"""
# Record a sequence of events
output = StringIO()
recorder = Record(file_object=output, replay=False)
record_mode = RecordMode(recorder)
i = iscalar()
f = function([i], i, mode=record_mode, name='f')
num_lines = 10
for i in range(num_lines):
recorder.handle_line(str(i) + '\n')
f(i)
# Make sure that the playback functionality doesn't raise any errors
# when we repeat them
output_value = output.getvalue()
output = StringIO(output_value)
playback_checker = Record(file_object=output, replay=True)
playback_mode = RecordMode(playback_checker)
i = iscalar()
f = function([i], i, mode=playback_mode, name='f')
for i in range(num_lines):
playback_checker.handle_line(str(i) + '\n')
f(i)
def test_determinism_2():
"""
A more aggressive determinism test. Tests that apply nodes are all passed
inputs with the same md5sums, apply nodes are run in same order, etc. Uses
disturb_mem to try to cause dictionaries to iterate in different orders,
etc.
"""
def run_sgd(mode):
# Must be seeded the same both times run_sgd is called
disturb_mem.disturb_mem()
rng = np.random.RandomState([2012, 11, 27])
batch_size = 5
train_batches = 3
valid_batches = 4
num_features = 2
# Synthesize dataset with a linear decision boundary
w = rng.randn(num_features)
def make_dataset(num_batches):
disturb_mem.disturb_mem()
m = num_batches * batch_size
X = rng.randn(m, num_features)
y = np.zeros((m, 1))
y[:, 0] = np.dot(X, w) > 0.
rval = DenseDesignMatrix(X=X, y=y)
rval.yaml_src = "" # suppress no yaml_src warning
X = rval.get_batch_design(batch_size)
assert X.shape == (batch_size, num_features)
return rval
train = make_dataset(train_batches)
valid = make_dataset(valid_batches)
num_chunks = 10
chunk_width = 2
class ManyParamsModel(Model):
"""
Make a model with lots of parameters, so that there are many
opportunities for their updates to get accidentally re-ordered
non-deterministically. This makes non-determinism bugs manifest
more frequently.
"""
def __init__(self):
super(ManyParamsModel, self).__init__()
self.W1 = [
sharedX(rng.randn(num_features, chunk_width))
for i in xrange(num_chunks)
]
disturb_mem.disturb_mem()
self.W2 = [
sharedX(rng.randn(chunk_width)) for i in xrange(num_chunks)
]
self._params = safe_union(self.W1, self.W2)
self.input_space = VectorSpace(num_features)
self.output_space = VectorSpace(1)
disturb_mem.disturb_mem()
model = ManyParamsModel()
disturb_mem.disturb_mem()
class LotsOfSummingCost(Cost):
"""
Make a cost whose gradient on the parameters involves summing many
terms together, so that T.grad is more likely to sum things in a
random order.
"""
supervised = True
def expr(self, model, data, **kwargs):
self.get_data_specs(model)[0].validate(data)
X, Y = data
disturb_mem.disturb_mem()
def mlp_pred(non_linearity):
Z = [T.dot(X, W) for W in model.W1]
H = map(non_linearity, Z)
Z = [T.dot(h, W) for h, W in safe_izip(H, model.W2)]
pred = sum(Z)
return pred
nonlinearity_predictions = map(
mlp_pred, [T.nnet.sigmoid, T.nnet.softplus, T.sqr, T.sin])
pred = sum(nonlinearity_predictions)
disturb_mem.disturb_mem()
return abs(pred - Y[:, 0]).sum()
def get_data_specs(self, model):
data = CompositeSpace(
(model.get_input_space(), model.get_output_space()))
source = (model.get_input_source(), model.get_target_source())
return (data, source)
cost = LotsOfSummingCost()
disturb_mem.disturb_mem()
algorithm = SGD(
cost=cost,
batch_size=batch_size,
learning_rule=Momentum(.5),
learning_rate=1e-3,
monitoring_dataset={
'train': train,
'valid': valid
},
update_callbacks=[ExponentialDecay(decay_factor=2., min_lr=.0001)],
termination_criterion=EpochCounter(max_epochs=5))
disturb_mem.disturb_mem()
train_object = Train(dataset=train,
model=model,
algorithm=algorithm,
extensions=[
PolyakAveraging(start=0),
MomentumAdjustor(final_momentum=.9,
start=1,
saturate=5),
],
save_freq=0)
disturb_mem.disturb_mem()
train_object.main_loop()
output = cStringIO.StringIO()
record = Record(file_object=output, replay=False)
record_mode = RecordMode(record)
run_sgd(record_mode)
output = cStringIO.StringIO(output.getvalue())
playback = Record(file_object=output, replay=True)
playback_mode = RecordMode(playback)
run_sgd(playback_mode)
