Test the pretrained model with own point cloud data

[harris56]

Hi!
I tried to use my own test ply data(All renamed as the shown format) uploaded to the directory dataset/scannetv2/test to run the test with pretrained model. And I met some bugs when I run test.py. More information is listed below:

CUDA_VISIBLE_DEVICES=0 python test.py --config config/hais_run1_scannet.yaml --pretrain ~/HAIS/HAIS/pretrain/hais_ckpt.pth
/home/harris_huang/HAIS/HAIS/util/config.py:22: YAMLLoadWarning: calling yaml.load() without Loader=... is deprecated, as the default Loader is unsafe. Please read https://msg.pyyaml.org/load for full details.
config = yaml.load(f)
[2022-07-08 13:12:37,754 INFO log.py line 39 8284] ************************ Start Logging ************************
[2022-07-08 13:12:37,768 INFO test.py line 27 8284] Namespace(TEST_NMS_THRESH=0.3, TEST_NPOINT_THRESH=100, TEST_SCORE_THRESH=0.09, batch_size=4, bg_thresh=0.0, block_reps=2, block_residual=True, cal_iou_based_on_mask=True, cal_iou_based_on_mask_start_epoch=200, classes=20, cluster_shift_meanActive=300, config='config/hais_run1_scannet.yaml', data_root='dataset', dataset='scannetv2', dataset_dir='data/scannetv2_inst.py', dist=False, epochs=500, eval=False, exp_path='exp/scannetv2/hais/hais_run1_scannet', fg_thresh=1.0, filename_suffix='_inst_nostuff.pth', fix_module=[], full_scale=[128, 512], ignore_label=-100, input_channel=3, local_rank=0, loss_weight=[1.0, 1.0, 1.0, 1.0], lr=0.001, manual_seed=123, mask_filter_score_feature_thre=0.5, max_npoint=250000, max_proposal_num=200, mode=4, model_dir='model/hais/hais.py', model_name='hais', momentum=0.9, multiplier=0.5, optim='Adam', point_aggr_radius=0.03, prepare_epochs=100, pretrain='/home/harris_huang/HAIS/HAIS/pretrain/hais_ckpt.pth', pretrain_module=[], pretrain_path=None, save_dir='exp', save_freq=16, save_instance=True, save_pt_offsets=False, save_semantic=False, scale=50, score_fullscale=20, score_mode=4, score_scale=50, split='test', step_epoch=200, task='test', test_epoch=500, test_mask_score_thre=-0.5, test_seed=567, test_workers=16, train_workers=8, use_coords=True, use_mask_filter_score_feature=True, use_mask_filter_score_feature_start_epoch=200, using_NMS=False, using_set_aggr_in_testing=True, using_set_aggr_in_training=False, weight_decay=0.0001, width=32)
[2022-07-08 13:12:37,769 INFO test.py line 242 8284] => creating model ...
[2022-07-08 13:12:37,769 INFO test.py line 243 8284] Classes: 20
[2022-07-08 13:12:38,722 INFO test.py line 255 8284] cuda available: True
[2022-07-08 13:12:42,480 INFO test.py line 259 8284] #classifier parameters (model): 30837785
[2022-07-08 13:12:42,563 INFO utils.py line 67 8284] Restore from /home/harris_huang/HAIS/HAIS/pretrain/hais_ckpt.pth
[2022-07-08 13:12:42,825 INFO test.py line 36 8284] >>>>>>>>>>>>>>>> Start Evaluation >>>>>>>>>>>>>>>>
[2022-07-08 13:12:42,882 INFO scannetv2_inst.py line 95 8284] Testing samples (test): 0
Traceback (most recent call last):
File "test.py", line 268, in
test(model, model_fn, data_name, cfg.test_epoch)
File "test.py", line 179, in test
logger.info("whole set inference time: {:.2f}s, latency per frame: {:.2f}ms".format(total_end1, total_end1 / len(dataloader) * 1000))
ZeroDivisionError: float division by zero

It seems like no test data is loaded, how can I solve this issue? thanks!