def generate_and_validate_sequence(node: RandomNumberNode) -> bool:
results = []
for i in range(STEPS):
node.step()
output_id = RandomNumberNodeAccessor.get_output_id(node)
results.append(output_id)
for i in range(STEPS):
if results[i] != SEQUENCE[i]:
return False
return True
def test_rnd_node_accessor_return_type(device):
lower_bound = 50
upper_bound = 100
node = RandomNumberNode(lower_bound=lower_bound, upper_bound=upper_bound)
node.allocate_memory_blocks(AllocatingCreator(device=device))
node._step()
random_number = RandomNumberNodeAccessor.get_output_id(node)
assert type(random_number) is int
assert lower_bound <= random_number < upper_bound
def get_baseline_output_id_for(self, layer_id: int) -> int:
return RandomNumberNodeAccessor.get_output_id(
self._baselines[layer_id])
def get_random_baseline_output_id_for_labels(self) -> int:
"""Returns index of 1 in the one-hot vector generated by the baseline which predicts the class labels."""
return RandomNumberNodeAccessor.get_output_id(
self._random_label_baseline)
def clone_random_baseline_output_tensor_for_labels(self) -> torch.Tensor:
return RandomNumberNodeAccessor.get_output_tensor(
self._random_label_baseline).clone()
def get_output_id(self):
return RandomNumberNodeAccessor.get_output_id(self._node)
def get_baseline_output_id(self) -> int:
return RandomNumberNodeAccessor.get_output_id(self._baseline)