def test_fixed_noise_gaussian_likelihood(self, cuda=False):
device = torch.device("cuda") if cuda else torch.device("cpu")
for dtype in (torch.float, torch.double):
noise = 0.1 + torch.rand(4, device=device, dtype=dtype)
lkhd = FixedNoiseGaussianLikelihood(noise=noise)
# test basics
self.assertIsInstance(lkhd.noise_covar, FixedGaussianNoise)
self.assertTrue(torch.equal(noise, lkhd.noise))
new_noise = 0.1 + torch.rand(4, device=device, dtype=dtype)
lkhd.noise = new_noise
self.assertTrue(torch.equal(lkhd.noise, new_noise))
# test __call__
mean = torch.zeros(4, device=device, dtype=dtype)
covar = DiagLazyTensor(torch.ones(4, device=device, dtype=dtype))
mvn = MultivariateNormal(mean, covar)
out = lkhd(mvn)
self.assertTrue(torch.allclose(out.variance, 1 + new_noise))
# things should break if dimensions mismatch
mean = torch.zeros(5, device=device, dtype=dtype)
covar = DiagLazyTensor(torch.ones(5, device=device, dtype=dtype))
mvn = MultivariateNormal(mean, covar)
with self.assertWarns(UserWarning):
lkhd(mvn)
# test __call__ w/ observation noise
obs_noise = 0.1 + torch.rand(5, device=device, dtype=dtype)
out = lkhd(mvn, noise=obs_noise)
self.assertTrue(torch.allclose(out.variance, 1 + obs_noise))
def test_posterior_latent_gp_and_likelihood_with_optimization(
self, cuda=False):
# This test throws a warning because the fixed noise likelihood gets the wrong input
warnings.simplefilter("ignore", GPInputWarning)
train_x, test_x, train_y, test_y = self._get_data(cuda=cuda)
# We're manually going to set the hyperparameters to something they shouldn't be
likelihood = FixedNoiseGaussianLikelihood(torch.ones(11) * 0.001)
gp_model = ExactGPModel(train_x, train_y, likelihood)
mll = gpytorch.ExactMarginalLogLikelihood(likelihood, gp_model)
gp_model.rbf_covar_module.initialize(lengthscale=exp(1))
gp_model.mean_module.initialize(constant=0)
if cuda:
gp_model.cuda()
likelihood.cuda()
# Find optimal model hyperparameters
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
with gpytorch.settings.debug(False):
for _ in range(75):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
optimizer.step()
# Test the model
gp_model.eval()
likelihood.eval()
test_function_predictions = likelihood(gp_model(test_x))
mean_abs_error = torch.mean(
torch.abs(test_y - test_function_predictions.mean))
self.assertLess(mean_abs_error.squeeze().item(), 0.05)
def setUp(self, batched=False, learnable=False):
torch.set_default_tensor_type(torch.DoubleTensor)
torch.random.manual_seed(10)
train_x = torch.rand(10, 2)
train_y = torch.sin(2 * train_x[:, 0] + 3 * train_x[:, 1]).unsqueeze(-1)
train_y_var = 0.1 * torch.ones_like(train_y)
if batched:
train_y = torch.cat(
(
train_y,
train_y + 0.3 * torch.randn_like(train_y),
train_y + 0.3 * torch.randn_like(train_y),
),
dim=1
)
train_y_var = train_y_var.repeat(1, 3)
model = FixedNoiseOnlineSKIGP(
train_inputs=train_x,
train_targets=train_y,
train_noise_term=train_y_var,
grid_bounds=torch.tensor([[0.0, 1.0], [0.0, 1.0]]),
grid_size=5,
learn_additional_noise=learnable
)
equivalent_model = SingleTaskGP(
train_X=train_x,
train_Y=train_y,
likelihood=FixedNoiseGaussianLikelihood(train_y_var.t(), learn_additional_noise=learnable),
covar_module = deepcopy(model.covar_module)
)
equivalent_model.mean_module = ZeroMean()
return model, equivalent_model, train_x, train_y
def create_model(self, fixed_noise=False):
data = TestExactGP.create_test_data(self)
likelihood, labels = TestExactGP.create_likelihood_and_labels(self)
if fixed_noise:
noise = 0.1 + 0.2 * torch.rand_like(labels)
likelihood = FixedNoiseGaussianLikelihood(noise)
return TestExactGP.create_model(self, data, labels, likelihood)
def test_fixed_noise_fantasy_updates_batch(self, cuda=False):
train_x, test_x, train_y, test_y = self._get_data(cuda=cuda)
noise = torch.full_like(train_y, 2e-4)
test_noise = torch.full_like(test_y, 3e-4)
likelihood = FixedNoiseGaussianLikelihood(noise)
gp_model = ExactGPModel(train_x, train_y, likelihood)
mll = gpytorch.ExactMarginalLogLikelihood(likelihood, gp_model)
gp_model.covar_module.base_kernel.initialize(lengthscale=exp(1))
gp_model.mean_module.initialize(constant=0)
if cuda:
gp_model.cuda()
likelihood.cuda()
# Find optimal model hyperparameters
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) + list(likelihood.parameters()), lr=0.15)
for _ in range(50):
optimizer.zero_grad()
with gpytorch.settings.debug(False):
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
optimizer.step()
with gpytorch.settings.fast_pred_var():
# Test the model
gp_model.eval()
likelihood.eval()
test_function_predictions = likelihood(gp_model(test_x), noise=test_noise)
# Cut data down, and then add back via the fantasy interface
gp_model.set_train_data(train_x[:5], train_y[:5], strict=False)
gp_model.likelihood.noise_covar = FixedGaussianNoise(noise=noise[:5])
likelihood(gp_model(test_x), noise=test_noise)
fantasy_x = train_x[5:].clone().unsqueeze(0).unsqueeze(-1).repeat(3, 1, 1).requires_grad_(True)
fantasy_y = train_y[5:].unsqueeze(0).repeat(3, 1)
fant_model = gp_model.get_fantasy_model(fantasy_x, fantasy_y, noise=noise[5:].unsqueeze(0).repeat(3, 1))
fant_function_predictions = likelihood(fant_model(test_x), noise=test_noise)
self.assertAllClose(test_function_predictions.mean, fant_function_predictions.mean[0], atol=1e-4)
fant_function_predictions.mean.sum().backward()
self.assertTrue(fantasy_x.grad is not None)
def test_kissgp_gp_fast_pred_var(self):
with gpytorch.settings.fast_pred_var(), gpytorch.settings.debug(False):
train_x, train_y, test_x, test_y = make_data()
likelihood = FixedNoiseGaussianLikelihood(torch.ones(100) * 0.001)
gp_model = GPRegressionModel(train_x, train_y, likelihood)
mll = gpytorch.mlls.ExactMarginalLogLikelihood(
likelihood, gp_model)
# Optimize the model
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
for _ in range(25):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
# Test the model
gp_model.eval()
likelihood.eval()
# Set the cache
test_function_predictions = likelihood(gp_model(train_x))
# Now bump up the likelihood to something huge
# This will make it easy to calculate the variance
likelihood.initialize(noise=3.)
test_function_predictions = likelihood(gp_model(train_x))
noise = likelihood.noise
var_diff = (test_function_predictions.variance - noise).abs()
self.assertLess(torch.max(var_diff / noise), 0.05)
def test_posterior_latent_gp_and_likelihood_without_optimization(self, cuda=False):
train_x, test_x, train_y, test_y = self._get_data(cuda=cuda)
with gpytorch.settings.debug(False):
# We're manually going to set the hyperparameters to be ridiculous
likelihood = FixedNoiseGaussianLikelihood(torch.ones(11) * 1e-8)
gp_model = ExactGPModel(train_x, train_y, likelihood)
# Update lengthscale prior to accommodate extreme parameters
gp_model.rbf_covar_module.initialize(lengthscale=exp(-6))
gp_model.mean_module.initialize(constant=0)
if cuda:
gp_model.cuda()
likelihood.cuda()
# Compute posterior distribution
gp_model.eval()
likelihood.eval()
# Let's see how our model does, conditioned with weird hyperparams
# The posterior should fit all the data
function_predictions = likelihood(gp_model(train_x))
self.assertLess(torch.norm(function_predictions.mean - train_y), 1e-3)
self.assertLess(torch.norm(function_predictions.variance), 5e-3)
# It shouldn't fit much else though
test_function_predictions = gp_model(torch.tensor([1.1]).type_as(test_x))
self.assertLess(torch.norm(test_function_predictions.mean - 0), 1e-4)
self.assertLess(torch.norm(test_function_predictions.variance - gp_model.covar_module.outputscale), 1e-4)
def test_kissgp_gp_mean_abs_error_cuda(self):
if not torch.cuda.is_available():
return
with least_used_cuda_device():
train_x, train_y, test_x, test_y = make_data(cuda=True)
likelihood = FixedNoiseGaussianLikelihood(torch.ones(100) *
0.001).cuda()
gp_model = GPRegressionModel(train_x, train_y, likelihood).cuda()
mll = gpytorch.mlls.ExactMarginalLogLikelihood(
likelihood, gp_model)
# Optimize the model
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
with gpytorch.settings.debug(False):
for _ in range(25):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
# Test the model
gp_model.eval()
likelihood.eval()
test_preds = likelihood(gp_model(test_x)).mean
mean_abs_error = torch.mean(torch.abs(test_y - test_preds))
self.assertLess(mean_abs_error.squeeze().item(), 0.02)
def test_kissgp_gp_mean_abs_error(self):
# This test throws a warning because the fixed noise likelihood gets the wrong input
warnings.simplefilter("ignore", GPInputWarning)
train_x, train_y, test_x, test_y = make_data()
likelihood = FixedNoiseGaussianLikelihood(torch.ones(100) * 0.001)
gp_model = GPRegressionModel(train_x, train_y, likelihood)
mll = gpytorch.mlls.ExactMarginalLogLikelihood(likelihood, gp_model)
# Optimize the model
gp_model.train()
likelihood.train()
optimizer = optim.Adam(list(gp_model.parameters()) +
list(likelihood.parameters()),
lr=0.1)
optimizer.n_iter = 0
with gpytorch.settings.debug(False):
for _ in range(25):
optimizer.zero_grad()
output = gp_model(train_x)
loss = -mll(output, train_y)
loss.backward()
optimizer.n_iter += 1
optimizer.step()
for param in gp_model.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
for param in likelihood.parameters():
self.assertTrue(param.grad is not None)
self.assertGreater(param.grad.norm().item(), 0)
# Test the model
gp_model.eval()
likelihood.eval()
test_preds = likelihood(gp_model(test_x)).mean
mean_abs_error = torch.mean(torch.abs(test_y - test_preds))
self.assertLess(mean_abs_error.squeeze().item(), 0.05)
def __init__(self, train_X: Tensor, train_Y: Tensor, options: dict, which_type: Optional[str] = "obj") -> None:
# Error checking:
assert train_Y.dim() == 1, "train_Y is required to be 1D"
self._validate_tensor_args(X=train_X, Y=train_Y[:,None]) # Only for this function, train_Y must be 2D (this must be a bug in botorch)
# Dimensionality of the input space:
self.dim = train_X.shape[-1]
# Model identity:
self.iden = "GP_model_{0:s}".format(which_type)
# Likelihood:
noise_std = options["noise_std_obj"]
lik = FixedNoiseGaussianLikelihood(noise=torch.full_like(train_Y, noise_std**2))
# Initialize parent class:
super().__init__(train_X, train_Y, lik)
# Obtain hyperprior for lengthscale and outputscale:
# NOTE: The mean (zero) and the model noise are fixed
lengthscale_prior, outputscale_prior = extract_prior(options,which_type)
# Initialize prior mean:
# self.mean_module = ConstantMean()
self.mean_module = ZeroMean()
# Initialize covariance function:
# base_kernel = RBFKernel(ard_num_dims=train_X.shape[-1],lengthscale_prior=GammaPrior(3.0, 6.0)) # original
# self.covar_module = ScaleKernel(base_kernel=base_kernel,outputscale_prior=GammaPrior(2.0, 0.15)) # original
base_kernel = RBFKernel(ard_num_dims=self.dim,lengthscale_prior=lengthscale_prior,lengthscale_constraint=GreaterThan(1e-2))
self.covar_module = ScaleKernel(base_kernel=base_kernel,outputscale_prior=outputscale_prior)
# Make sure we're on the right device/dtype
self.to(train_X)
# Instantiate the gradient model:
self.model_grad = GPmodelWithGrad(dim=self.dim)
def create_likelihood(self):
noise = 0.1 + torch.rand(2, 3, 5)
return FixedNoiseGaussianLikelihood(noise=noise)
def run(obs, params_true, device='cpu'):
device = safe_cast(torch.device, device)
dx, NX = PARAM_DX, PARAM_MESH_RES_SPACE
ts = torch.arange(PARAM_MESH_RES_TIME, device=device)
priors_uniform = priors()
y = torch.tensor(obs['Ss'], device=device)
def simulate(params):
_theta = {'a':params[0], 'b':params[1], 'k':params[2]}
sim_pde = LandauCahnHilliard(
params = _theta,
M = PARAM_DT,
dx = dx,
device = device
)
loss_fn = Evaluator(sim_pde, loss)
return loss_fn
pgd = lhs(3, samples=PARAM_INIT_EVAL) # calculate initial samples from latin hypercube
xs, ys = [],[]
for j in range(PARAM_INIT_EVAL):
xk = torch.stack(
[(priors_uniform[k][1]-priors_uniform[k][0])*torch.tensor(pgd[j,i], device=device, dtype=torch.float32) + priors_uniform[k][0] for i,k in enumerate(('a','b','k'))],
0
)
xs.append(xk)
# ell, params = simulate(params)
phi0 = (0.2 * torch.rand((NX, NX), device=device)).view(-1,1,NX,NX)
with torch.no_grad():
for j in range(PARAM_INIT_EVAL):
params = xs[j]
loss_fn = simulate(params)
ys.append(loss_fn(phi0, ts, y, dx))
x_init, y_init = torch.stack(xs), torch.stack(ys)
print(y_init)
N = PARAM_SEARCH_RES
x_eval = torch.cat([x.reshape(-1,1) for x in torch.meshgrid(
*[torch.linspace(priors_uniform[k][0], priors_uniform[k][1], N)\
for k in priors_uniform]
)],1)
x_train = x_init
y_train = y_init
for i in range(PARAM_MAX_EVAL - PARAM_INIT_EVAL):
for ntry in range(5):
model = ExactGPModel(
x_train, y_train,
FixedNoiseGaussianLikelihood(
noise=1e-2*torch.ones(len(x_train))
)
)
try:
optimise(model, method='adam', max_iter=1000)
break
except Exception as err:
print('attempt %d failed' % ntry)
if ntry == 4:
raise err
u = acq(y_train.min(), model, x_eval)
xn = x_eval[u.argmax(),:]
x_eval = torch.cat([x_eval[0:u.argmax(),:], x_eval[u.argmax()+1:,:]])
# print(x_eval.shape)
loss_fn = simulate(xn)
yn = loss_fn(phi0, ts, y, dx)
x_train = torch.cat([x_train, xn.reshape(1,-1)])
y_train = torch.stack([*y_train, yn.detach()])
print(i)
return (x_train, y_train)
def __init__(self,
dim: int,
train_X: Tensor,
train_Y: Tensor,
options: dict,
which_type: Optional[str] = "obj") -> None:
self.dim = dim
if len(train_Y) == 0: # No data case
train_X = None
train_Y = None
else:
# Error checking:
assert train_Y.dim() == 1, "train_Y is required to be 1D"
self._validate_tensor_args(
X=train_X, Y=train_Y[:, None]
) # Only for this function, train_Y must be 2D (this must be a bug in botorch)
print("\n")
logger.info("### Initializing GP model for objective f(x) ###")
# Likelihood:
noise_std = options.hyperpars.noise_std.value
if train_Y is not None:
lik = FixedNoiseGaussianLikelihood(
noise=torch.full_like(train_Y, noise_std**2))
else:
lik = FixedNoiseGaussianLikelihood(
noise=torch.tensor([noise_std**2], device=device, dtype=dtype))
# Initialize parent class:
super().__init__(train_X, train_Y, lik)
# # Obtain hyperprior for lengthscale and outputscale:
# # NOTE: The mean (zero) and the model noise are fixed
# lengthscale_prior, outputscale_prior = extract_prior(options.hyperpriors)
# Initialize hyperpriors using scipy because gpytorch's gamma and beta distributions do not have the inverse CDF
hyperpriors = dict(
lengthscales=eval(options.hyperpars.lenthscales.prior),
outputscale=eval(options.hyperpars.outputscale.prior))
# Index hyperparameters:
self.idx_hyperpars = dict(lengthscales=list(range(0, self.dim)),
outputscale=[self.dim])
self.dim_hyperpars = sum(
[len(val) for val in self.idx_hyperpars.values()])
# Get bounds:
self.hyperpars_bounds = self._get_hyperparameters_bounds(hyperpriors)
logger.info("hyperpars_bounds:" + str(self.hyperpars_bounds))
# Initialize prior mean:
# self.mean_module = ConstantMean()
self.mean_module = ZeroMean()
# Initialize covariance function:
# base_kernel = RBFKernel(ard_num_dims=train_X.shape[-1],lengthscale_prior=GammaPrior(3.0, 6.0)) # original
# self.covar_module = ScaleKernel(base_kernel=base_kernel,outputscale_prior=GammaPrior(2.0, 0.15)) # original
# base_kernel = RBFKernel(ard_num_dims=self.dim,lengthscale_prior=lengthscale_prior,lengthscale_constraint=GreaterThan(1e-2))
base_kernel = MaternKernel(nu=2.5,
ard_num_dims=self.dim,
lengthscale=0.1 * torch.ones(self.dim))
self.covar_module = ScaleKernel(base_kernel=base_kernel)
self.disp_info_scipy_opti = True
# self.method = "L-BFGS-B"
self.method = "LN_BOBYQA"
# self.method = 'trust-constr'
# Get a hyperparameter sample within bounds (not the same as sampling from the corresponding priors):
hyperpars_sample = self._sample_hyperparameters_within_bounds(
Nsamples=1).squeeze(0)
self.covar_module.outputscale = hyperpars_sample[
self.idx_hyperpars["outputscale"]]
self.covar_module.base_kernel.lengthscale = hyperpars_sample[
self.idx_hyperpars["lengthscales"]]
self.noise_std = options.hyperpars.noise_std.value # The evaluation noise is fixed, and given by the user
# Initialize marginal log likelihood for the GPCR model.
# mll_objective is callable
# MLLGPCR can internally modify the model hyperparameters, and will do so throughout the optimization routine
self.mll_objective = MLLGP(model_gp=self,
likelihood_gp=self.likelihood,
hyperpriors=hyperpriors)
# Define nlopt optimizer:
self.opti_hyperpars = OptimizationNonLinear(
dim=self.dim_hyperpars,
fun_obj=self.mll_objective,
algo_str=self.method,
tol_x=1e-4,
Neval_max_local_optis=options.hyperpars.optimization.Nmax_evals,
bounds=self.hyperpars_bounds,
what2optimize_str="GP hyperparameters")
# Make sure we're on the right device/dtype
if train_Y is not None:
self.to(train_X)
self.Nrestarts = options.hyperpars.optimization.Nrestarts
self._update_hyperparameters()
self.eval()
def main(args):
if args.cuda and torch.cuda.is_available():
device = torch.device("cuda:0")
else:
device = torch.device("cpu")
init_dict, train_dict, test_dict = prepare_data(args.data_loc,
args.num_init,
args.num_total,
test_is_year=False,
seed=args.seed)
init_x, init_y, init_y_var = (
init_dict["x"].to(device),
init_dict["y"].to(device),
init_dict["y_var"].to(device),
)
train_x, train_y, train_y_var = (
train_dict["x"].to(device),
train_dict["y"].to(device),
train_dict["y_var"].to(device),
)
test_x, test_y, test_y_var = (
test_dict["x"].to(device),
test_dict["y"].to(device),
test_dict["y_var"].to(device),
)
likelihood = FixedNoiseGaussianLikelihood(noise=init_y_var)
grid_pts = create_grid(grid_sizes=[30, 30],
grid_bounds=torch.tensor([[0., 1.], [0., 1.]]))
induc_points = torch.cat(
[x.reshape(-1, 1) for x in torch.meshgrid(grid_pts)], dim=-1)
model = VariationalGPModel(
inducing_points=induc_points,
mean_module=gpytorch.means.ZeroMean(),
covar_module=ScaleKernel(
MaternKernel(
ard_num_dims=2,
nu=0.5,
lengthscale_prior=GammaPrior(3.0, 6.0),
),
outputscale_prior=GammaPrior(2.0, 0.15),
),
streaming=True,
likelihood=likelihood,
beta=args.beta,
learn_inducing_locations=args.learn_inducing,
).to(device)
mll = VariationalELBO(model.likelihood,
model,
beta=args.beta,
num_data=args.num_init)
print("---- Fitting initial model ----")
start = time.time()
model.train()
model.zero_grad()
optimizer = torch.optim.Adam(model.parameters(), lr=10 * args.lr_init)
model, loss = fit_variational_model(mll,
model,
optimizer,
init_x,
init_y,
maxiter=1000)
end = time.time()
print("Elapsed fitting time: ", end - start)
print("--- Now computing initial RMSE")
model.eval()
with gpytorch.settings.skip_posterior_variances(True):
test_pred = model(test_x)
pred_rmse = ((test_pred.mean - test_y)**2).mean().sqrt()
print("---- Initial RMSE: ", pred_rmse.item())
all_outputs = []
start_ind = init_x.shape[0]
end_ind = int(start_ind + args.batch_size)
current_x = init_x
current_y = init_y
current_y_var = init_y_var
for step in range(args.num_steps):
if step > 0 and step % 25 == 0:
print("Beginning step ", step)
total_time_step_start = time.time()
if step > 0:
print("---- Fitting model ----")
start = time.time()
model.train()
model.zero_grad()
model.likelihood = FixedNoiseGaussianLikelihood(current_y_var)
mll = VariationalELBO(model.likelihood,
model,
beta=args.beta,
num_data=args.num_init)
optimizer = torch.optim.Adam(model.parameters(),
lr=args.lr_init * 0.99**step)
model, loss = fit_variational_model(mll,
model,
optimizer,
current_x,
current_y,
maxiter=300)
model.zero_grad()
end = time.time()
print("Elapsed fitting time: ", end - start)
# print("Named parameters: ", list(model.named_parameters()))
if args.acqf == "max_post_var" and not args.random:
candidates, acq_value = generate_candidates(model,
args.batch_size,
device,
maxiter=300)
elif args.acqf == "max_test_var" and not args.random:
model.eval()
vals, inds = model(test_x).variance.sort()
acq_value = vals[-args.batch_size:].mean().detach()
candidates = test_x[inds[-args.batch_size:]]
else:
candidates = torch.rand(args.batch_size,
train_x.shape[-1],
device=device,
dtype=train_x.dtype)
acq_value = torch.zeros(1)
model.eval()
_ = model(test_x[:10]) # to init caches
print("---- Finished optimizing; now querying dataset ---- ")
with torch.no_grad():
covar_dists = model.covar_module(candidates, train_x)
nearest_points = covar_dists.evaluate().argmax(dim=-1)
new_x = train_x[nearest_points]
new_y = train_y[nearest_points]
new_y_var = train_y_var[nearest_points]
todrop = torch.tensor(
[x in nearest_points for x in range(train_x.shape[0])])
train_x, train_y, train_y_var = train_x[~todrop], train_y[
~todrop], train_y_var[~todrop]
print("New train_x shape", train_x.shape)
print("--- Now updating model with simulator ----")
current_x = torch.cat((current_x, new_x), dim=0)
current_y = torch.cat((current_y, new_y), dim=0)
current_y_var = torch.cat((current_y_var, new_y_var), dim=0)
print("--- Now computing updated RMSE")
model.eval()
test_pred = model(test_x)
pred_rmse = ((test_pred.mean.view(-1) -
test_y.view(-1))**2).mean().sqrt()
pred_avg_variance = test_pred.variance.mean()
total_time_step_elapsed_time = time.time() - total_time_step_start
step_output_list = [
total_time_step_elapsed_time,
acq_value.item(),
pred_rmse.item(),
pred_avg_variance.item(),
loss.item()
]
print("Step RMSE: ", pred_rmse)
all_outputs.append(step_output_list)
start_ind = end_ind
end_ind = int(end_ind + args.batch_size)
output_dict = {
"model_state_dict": model.cpu().state_dict(),
"queried_points": {
'x': current_x,
'y': current_y
},
"results": DataFrame(all_outputs)
}
torch.save(output_dict, args.output)
