################################## # Change model parameters for test ################################## # Change parameters for the test here. For example, you can stop augmenting the input data. config.global_fet = False config.validation_size = 200 config.input_threads = 16 config.n_frames = 4 config.n_test_frames = 4 #it should be smaller than config.n_frames if config.n_frames < config.n_test_frames: config.n_frames = config.n_test_frames config.big_gpu = True config.dataset_task = '4d_panoptic' #config.sampling = 'density' config.sampling = 'importance' config.decay_sampling = 'None' config.stride = 1 config.first_subsampling_dl = 0.061 ############## # Prepare Data ############## print() print('Data Preparation') print('****************') if on_val:
print('\nModel Preparation') print('*****************') # Define network model t1 = time.time() if config.dataset_task == 'classification': net = KPCNN(config) elif config.dataset_task in ['cloud_segmentation', 'slam_segmentation']: net = KPFCNN(config, test_dataset.label_values, test_dataset.ignored_labels) else: raise ValueError('Unsupported dataset_task for testing: ' + config.dataset_task) # Define a visualizer class tester = ModelTester(net, chkp_path=chosen_chkp) print('Done in {:.1f}s\n'.format(time.time() - t1)) print('\nStart test') print('**********\n') # Training config.dataset_task = "rellis_segmentation" if config.dataset_task == 'classification': tester.classification_test(net, test_loader, config) elif config.dataset_task == 'cloud_segmentation': tester.cloud_segmentation_test(net, test_loader, config) elif config.dataset_task == 'slam_segmentation': tester.slam_segmentation_test(net, test_loader, config) elif config.dataset_task == "rellis_segmentation": tester.rellis_segmentation_test(net, test_loader, config,num_votes=100) else: raise ValueError('Unsupported dataset_task for testing: ' + config.dataset_task)