if __name__ == '__main__':
# if torch.cuda.is_available():
# pyprob.set_cuda(True)
pyprob.set_verbosity(1)
tests = []
# tests.append('MVNWithUnknownMeanTestCase')
tests.append('GaussianWithUnknownMeanTestCase')
# tests.append('GaussianWithUnknownMeanMarsagliaTestCase')
# tests.append('HiddenMarkovModelTestCase')
time_start = time.time()
success = unittest.main(defaultTest=tests, verbosity=2,
exit=False).result.wasSuccessful()
print('\nDuration : {}'.format(
util.days_hours_mins_secs_str(time.time() - time_start)))
print('Models run : {}'.format(' '.join(tests)))
print('Samples : {}'.format(samples))
print('Training traces : {}\n'.format(training_traces))
print('\nTotal inference performance scores\n')
print(colored('Importance sampling : ', 'yellow', attrs=['bold']), end='')
print(
colored('{:+.6e}'.format(perf_score_importance_sampling),
'white',
attrs=['bold']))
print(colored('Inference compilation: ', 'yellow', attrs=['bold']), end='')
print(
colored('{:+.6e}\n'.format(perf_score_inference_compilation),
'white',
attrs=['bold']))
sys.exit(0 if success else 1)
self.assertLess(kl_divergence, 0.75)
if __name__ == '__main__':
# pyprob.seed(123)
pyprob.set_verbosity(1)
tests = []
tests.append('GaussianWithUnknownMeanTestCase')
tests.append('GaussianWithUnknownMeanMarsagliaWithReplacementTestCase')
tests.append('HiddenMarkovModelTestCase')
tests.append('BranchingTestCase')
time_start = time.time()
success = unittest.main(defaultTest=tests, verbosity=2, exit=False).result.wasSuccessful()
print('\nDuration : {}'.format(util.days_hours_mins_secs_str(time.time() - time_start)))
print('Models run : {}'.format(' '.join(tests)))
print('\nTotal inference performance:\n')
print(colored(' Samples KL divergence Duration (s) ', 'yellow', attrs=['bold']))
print(colored('Importance sampling : ', 'yellow', attrs=['bold']), end='')
print(colored('{:+.6e} {:+.6e} {:+.6e}'.format(importance_sampling_samples, importance_sampling_kl_divergence, importance_sampling_duration), 'white', attrs=['bold']))
print(colored('Importance sampling w/ inference net.: ', 'yellow', attrs=['bold']), end='')
print(colored('{:+.6e} {:+.6e} {:+.6e}'.format(importance_sampling_with_inference_network_samples, importance_sampling_with_inference_network_kl_divergence, importance_sampling_with_inference_network_duration), 'white', attrs=['bold']))
print(colored('Lightweight Metropolis Hastings : ', 'yellow', attrs=['bold']), end='')
print(colored('{:+.6e} {:+.6e} {:+.6e}'.format(lightweight_metropolis_hastings_samples, lightweight_metropolis_hastings_kl_divergence, lightweight_metropolis_hastings_duration), 'white', attrs=['bold']))
print(colored('Random-walk Metropolis Hastings : ', 'yellow', attrs=['bold']), end='')
print(colored('{:+.6e} {:+.6e} {:+.6e}\n'.format(random_walk_metropolis_hastings_samples, random_walk_metropolis_hastings_kl_divergence, random_walk_metropolis_hastings_duration), 'white', attrs=['bold']))
# for container in docker_containers:
# print('Killing Docker container {}'.format(container.name))
# container.kill()