num_steps_per_sample=L,
step_size=step_size,
burn=burn,
tau_priors=tau_priors,
tau_likes=tau_likes,
device=device,
n_params_single=n_params_single,
pde=pde,
pinns=pinns,
epochs=epochs)
pred_list, log_prob_list = util.predict_model_bpinns(
nets,
params_hmc,
data_val,
model_loss=model_loss,
tau_priors=tau_priors,
tau_likes=tau_likes,
n_params_single=n_params_single,
pde=pde)
print('\nExpected validation log probability: {:.3f}'.format(
torch.stack(log_prob_list).mean()))
print('\nThe exact values of single parameters: {}'.format(exact_single))
params_single = torch.stack(params_hmc)[:, :n_params_single].cpu().numpy()
print('The means of single parameters: {}'.format(
np.exp(params_single).mean(0)))
print('The variances of single parameters: {}'.format(
np.exp(params_single).std(0)))
params_init_val = None
params_hmc = util.sample_model_bpinns(nets,
data,
model_loss=model_loss,
step_size=step_size,
device=device,
pde=True,
pinns=True,
epochs=epochs,
params_init_val=params_init_val)
pred_list, log_prob_list = util.predict_model_bpinns(nets,
params_hmc,
data_val,
model_loss=model_loss,
pde=True)
print('\nExpected validation log probability: {:.3f}'.format(
torch.stack(log_prob_list).mean()))
pred_list_u = pred_list[0].cpu().numpy()
pred_list_U = pred_list[1].cpu().numpy()
pred_list_A = pred_list[2].cpu().numpy()
pred_list_Y = pred_list[3].cpu().numpy()
# plot
wxi = data_val['wxi'].cpu().numpy()
x = data_val['x'].cpu().numpy()