def setUp(self):
super().setUp()
self._solver_cls = deep_evolution_solver.MutationPredictorSolver
tf.enable_eager_execution()
self.problem = simple_ising_model.AlternatingChainIsingModel(
length=20, vocab_size=4)
self.vocab_size = self.problem.domain.vocab_size
self.length = self.problem.domain.length
def test_alternating_chain_model_optima(self):
model = simple_ising_model.AlternatingChainIsingModel(
length=4, vocab_size=2)
actual_optima = model._get_global_optima()
expected_optima = [[0, 1, 0, 1], [1, 0, 1, 0]]
self.assertAllClose(actual_optima, expected_optima)
model = simple_ising_model.AlternatingChainIsingModel(
length=5, vocab_size=2)
actual_optima = model._get_global_optima()
expected_optima = [[0, 1, 0, 1, 0], [1, 0, 1, 0, 1]]
self.assertAllClose(actual_optima, expected_optima)
model = simple_ising_model.AlternatingChainIsingModel(
length=4, vocab_size=4)
actual_optima = model._get_global_optima()
expected_optima = [[0, 1, 0, 1], [1, 0, 1, 0], [2, 3, 2, 3], [3, 2, 3, 2]]
self.assertAllClose(actual_optima, expected_optima)
def test_solve(self):
problem = simple_ising_model.AlternatingChainIsingModel(length=8,
vocab_size=4)
solver = deep_evolution_solver.MutationPredictorSolver(
domain=problem.domain)
controller.run(problem, solver, num_rounds=20, batch_size=10)
def test_alternating_chain_model_energy(self):
model = simple_ising_model.AlternatingChainIsingModel(
length=4, vocab_size=2)
inputs = np.array([[0, 1, 0, 1], [1, 0, 1, 0], [1, 0, 1, 1]])
energy = model(inputs)
self.assertAllClose(energy, [3., 3., 2.])