class TestMultiDatasetAlphabetNode:
@pytest.mark.parametrize('params, should_pass', [
(DatasetAlphabetParams(
symbols="abcd",
sequence_probs=DatasetAlphabetSequenceProbsModeParams(seqs=['abc'])
), True),
(DatasetAlphabetParams(
symbols="abcd",
sequence_probs=DatasetAlphabetSequenceProbsModeParams(seqs=['abc', 'ae'])
), False)
])
def test_validate_params_sequence_probs_validate_throws(self, params, should_pass):
node = MultiDatasetAlphabetNode(params)
if should_pass:
node.validate()
else:
with raises(NodeValidationException):
node.validate()
def test_create_node(self, device):
unit = DatasetAlphabetUnit(
AllocatingCreator(device),
DatasetAlphabetParams(
symbols="abcd",
sequence_probs=DatasetAlphabetSequenceProbsModeParams(
seqs=['abcd'])))
assert [4, 7, 5] == list(unit.all_symbols.shape)
assert [7, 5] == list(unit.output_data.shape)
def test_mode_sequence_probs(self, device):
unit = DatasetAlphabetUnit(
AllocatingCreator(device),
DatasetAlphabetParams(
symbols="abcd",
sequence_probs=DatasetAlphabetSequenceProbsModeParams(
seqs=['abc'])))
generator = self.label_generator(unit)
result = [next(generator) for _ in range(7)]
assert [0, 1, 2, 0, 1, 2, 0] == result
def __init__(self):
super().__init__(device = 'cuda')
dataset_params = DatasetAlphabetParams(symbols="abcd123456789", padding_right=1,
sequence_probs=DatasetAlphabetSequenceProbsModeParams(
seqs=['abc', '123', '456'],
))
dataset = MultiDatasetAlphabetNode(dataset_params, n_worlds=4)
self.add_node(dataset)
def create_node_dataset(self):
def generate_sequence(symbols: str, count: int, skip: int):
"""Generate sequence of length `count` and stride `skip` from `symbols` - symbols are repeated when needed"""
repeating_symbols = itertools.cycle(symbols)
result = []
for i in range(count):
result.append(next(repeating_symbols))
for s in range(skip):
next(repeating_symbols)
return ''.join(result)
def count_unique_symbols(sequences: List[str]) -> int:
symbols = set()
for seq in sequences:
for symbol in seq:
symbols.add(symbol)
return len(symbols)
seqs = [
str(
generate_sequence(self._params.symbols,
self._params.seq_length, i))
for i in range(self._params.seq_count)
]
# duplicate sequences
for s in list(seqs):
seqs.append(s)
# make sequences longer (repeat)
seqs = [s * self._params.seq_repeat for s in seqs]
dataset_params = DatasetAlphabetParams(
symbols=self._params.symbols,
padding_right=1,
sequence_probs=DatasetAlphabetSequenceProbsModeParams(seqs=seqs))
return MultiDatasetAlphabetNode(dataset_params,
n_worlds=self._params.flock_size)
def test_create_node(self, device):
unit = MultiDatasetAlphabetUnit(AllocatingCreator(device), DatasetAlphabetParams(
symbols="abcd",
sequence_probs=DatasetAlphabetSequenceProbsModeParams(seqs=['abcd'])
), n_worlds=self.n_worlds)
assert [self.n_worlds, 7, 5] == list(unit.output_data.shape)
def toploogy_dataset_test(self):
dataset_params = DatasetAlphabetParams(
symbols="abcd123456789",
padding_right=1,
sequence_probs=DatasetAlphabetSequenceProbsModeParams(
seqs=['abc', '123', '456789', '468'],
# transition_probs=[[0.7, 0.3], [0.3, 0.7], ]
))
dataset_node = DatasetAlphabetNode(dataset_params)
flock_size = 1
# parent_cluster_centers = len(dataset_params.sequence_probs.seqs)
parent_cluster_centers = 20 # len(dataset_params.sequence_probs.seqs)
unsqueeze_node_child = UnsqueezeNode(0)
unsqueeze_node_sequence_id = UnsqueezeNode(0)
expand_node_child = ExpandNode(0, flock_size)
expand_node_sequence_id = ExpandNode(0, flock_size)
child_cluster_centers = len(dataset_params.symbols) - 1
expert_node_child = ExpertFlockNode(
ExpertParams(flock_size=flock_size,
n_cluster_centers=child_cluster_centers,
spatial=SpatialPoolerParams(),
temporal=TemporalPoolerParams(
incoming_context_size=parent_cluster_centers,
n_providers=2,
n_frequent_seqs=50,
seq_length=3,
seq_lookahead=1)))
expert_node_parent = ExpertFlockNode(
ExpertParams(flock_size=flock_size,
n_cluster_centers=parent_cluster_centers,
spatial=SpatialPoolerParams(),
temporal=TemporalPoolerParams(incoming_context_size=4,
n_frequent_seqs=50,
seq_length=3,
seq_lookahead=1)))
expert_node_sequence_id = ExpertFlockNode(
ExpertParams(flock_size=flock_size,
n_cluster_centers=2,
spatial=SpatialPoolerParams()))
self.add_node(dataset_node)
self.add_node(unsqueeze_node_child)
# self.add_node(unsqueeze_node_sequence_id)
self.add_node(expand_node_child)
# self.add_node(expand_node_sequence_id)
self.add_node(expert_node_child)
self.add_node(expert_node_parent)
# self.add_node(expert_node_sequence_id)
Connector.connect(dataset_node.outputs.output,
unsqueeze_node_child.inputs.input)
Connector.connect(unsqueeze_node_child.outputs.output,
expand_node_child.inputs.input)
Connector.connect(expand_node_child.outputs.output,
expert_node_child.inputs.sp.data_input)
# Connector.connect(dataset_node.outputs.sequence_id, unsqueeze_node_sequence_id.inputs.input)
# Connector.connect(unsqueeze_node_sequence_id.outputs.output, expand_node_sequence_id.inputs.input)
# Connector.connect(expand_node_sequence_id.outputs.output, expert_node_sequence_id.inputs.sp.data_input)
Connector.connect(expert_node_child.outputs.tp.projection_outputs,
expert_node_parent.inputs.sp.data_input)
# Parent context
Connector.connect(expert_node_parent.outputs.output_context,
expert_node_child.inputs.tp.context_input,
is_backward=True)