def test_ND():
"test various tensor size random"
TEST_INPUTS = [
[UniformCrossover1D, (2, 4), 0.5],
[UniformCrossover2D, (2, 4, 4), (0.5, 0.5)],
[UniformCrossover3D, (2, 4, 4, 4), (0.5, 0.5, 0.5)],
]
for inputs in TEST_INPUTS:
OP = inputs[0]
pop_shape = inputs[1]
mutations_probability = inputs[2]
population_fraction = 1
population = B.randint(0, 1024, pop_shape)
# eager
RM = OP(population_fraction=population_fraction,
mutations_probability=mutations_probability)
population = RM(population)
assert B.is_tensor(population)
assert population.shape == pop_shape
# graph
RM = OP(population_fraction=population_fraction,
mutations_probability=mutations_probability)
population = RM._call_from_graph(population)
assert B.is_tensor(population)
assert population.shape == pop_shape
def test_non_tensor_input():
shape = (2, 4)
population = [[1, 2, 3, 4], [1, 2, 3, 4]]
inputs = Input(shape)
inputs.assign(population)
res = inputs.get()
assert B.is_tensor(res)
def on_generation_end(self, generation, metrics, fitness_scores,
populations):
assert isinstance(generation, int)
assert isinstance(metrics, dict)
assert isinstance(fitness_scores, dict)
assert isinstance(populations, list)
for pop in populations:
assert B.is_tensor(pop)
def test_ND():
"test various tensor size random"
TEST_INPUTS = [
[RandomMutations1D, (2, 4), 0.5],
[RandomMutations2D, (2, 4, 4), (0.5, 0.5)],
[RandomMutations3D, (2, 4, 4, 4), (0.5, 0.5, 0.5)],
]
for inputs in TEST_INPUTS:
OP = inputs[0]
pop_shape = inputs[1]
mutations_probability = inputs[2]
max_gene_value = 10
min_gene_value = 0
population_fraction = 1
min_mutation_value = 1
max_mutation_value = 1
population = randint_population(pop_shape, max_gene_value)
# eager
RM = OP(population_fraction=population_fraction,
mutations_probability=mutations_probability,
min_gene_value=min_gene_value,
max_gene_value=max_gene_value,
min_mutation_value=min_mutation_value,
max_mutation_value=max_mutation_value)
population = RM(population)
assert B.is_tensor(population)
assert population.shape == pop_shape
# graph
RM = OP(population_fraction=population_fraction,
mutations_probability=mutations_probability,
min_gene_value=min_gene_value,
max_gene_value=max_gene_value,
min_mutation_value=min_mutation_value,
max_mutation_value=max_mutation_value)
population = RM._call_from_graph(population)
assert B.is_tensor(population)
assert population.shape == pop_shape
def test_shuffle():
SHAPES = [(2, 4), (2, 4, 4), (2, 4, 4, 4)]
for shape in SHAPES:
population = randint_population(shape, max_value=255)
previous_population = B.copy(population)
population = Shuffle(1, debug=True)(population)
diff = B.clip(abs(population - previous_population), 0, 1)
assert B.is_tensor(population)
assert population.shape == shape
sum_diff = B.sum(diff)
shape_size = int(B.prod(shape) / 2)
assert sum_diff >= shape_size
def test_mutation2d_eager():
pop_shape = (10, 4, 4)
max_gene_value = 10
min_gene_value = 0
population_fraction = 1
mutations_probability = (0.5, 0.5)
min_mutation_value = 1
max_mutation_value = 1
population = randint_population(pop_shape, max_gene_value)
# save original
original_population = B.copy(population)
cprint('[Initial genepool]', 'blue')
cprint(original_population, 'blue')
for _ in range(3):
RM = RandomMutations2D(population_fraction=population_fraction,
mutations_probability=mutations_probability,
min_gene_value=min_gene_value,
max_gene_value=max_gene_value,
min_mutation_value=min_mutation_value,
max_mutation_value=max_mutation_value,
debug=True)
population = RM(population)
cprint('\n[Mutated genepool]', 'yellow')
cprint(population, 'yellow')
cprint('\n[Diff]', 'magenta')
diff = population - original_population
cprint(diff, 'magenta')
assert B.is_tensor(population)
assert population.shape == pop_shape
assert B.max(diff) <= max_mutation_value
ok = 0
for chromosome in diff:
if B.sum(chromosome) >= 2:
ok += 1
if (ok / len(diff)) > 0.5:
break
assert (ok / len(diff)) > 0.5
def __call__(self, ops):
# boxing inputs if needed
ops = box(ops)
# graph computation or eager?
if self.debug:
input_types = [type(op) for op in ops]
self.print_debug('inputs type:%s' % (input_types))
if issubclass(type(ops[0]), OP):
# graph mode
self.print_debug('graph mode')
input_shapes = []
for op in ops:
assert issubclass(type(op), OP)
self.input_ops.append(op)
input_shapes.append(op.get_output_shapes())
self.compute_output_shape(input_shapes)
return self
else:
# eager mode
self.print_debug('eager mode')
# check inputs are valis
for op in ops:
if not B.is_tensor(op):
raise ValueError("Expecting list(tensors) or a tensor")
# input shapes
input_shapes = []
for op in ops:
input_shapes.append(op.shape)
self.compute_output_shape(input_shapes)
# compute concrete results - dispatch iterate through populations.
return unbox(self.dispatch(ops, self.EAGER))
def test_mutation2d_graph_mode():
"make sure the boxing / unboxing works in graph mode"
pop_shape = (2, 4, 4)
max_gene_value = 10
min_gene_value = 0
population_fraction = 1
mutations_probability = (0.5, 0.5)
min_mutation_value = 1
max_mutation_value = 1
population = B.randint(0, max_gene_value, pop_shape)
RM = RandomMutations2D(population_fraction=population_fraction,
mutations_probability=mutations_probability,
min_gene_value=min_gene_value,
max_gene_value=max_gene_value,
min_mutation_value=min_mutation_value,
max_mutation_value=max_mutation_value,
debug=True)
population = RM._call_from_graph(population)
assert B.is_tensor(population)
assert population.shape == pop_shape
def on_evolution_end(self, populations):
assert isinstance(populations, list)
for pop in populations:
assert B.is_tensor(pop)