‘lmo_test' is empty

[RainYQ]

Run evaluation sample

./core/gdrn_modeling/test_gdrn.sh configs/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e.py 0 output/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e/gdrn_lmo_real_pbr.pth

got error like:

[07/08 11:08:34 fvcore.common.checkpoint]: [Checkpointer] Loading from output/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e/gdrn_lmo_real_pbr.pth ...
[0708_110834 core.gdrn_modeling.gdrn_custom_evaluator@98]: eval precision: False
[0708_110834 core.gdrn_modeling.datasets.lm_dataset_d2@97]: loading dataset dicts: lmo_test
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1214/1214 [00:00<00:00, 13442.86it/s]
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  8.74it/s]
[0708_110835 core.gdrn_modeling.datasets.lm_dataset_d2@219]: loaded 0 dataset dicts, using 0.12068194802850485s
[0708_110835 core.gdrn_modeling.datasets.lm_dataset_d2@223]: Dumped dataset_dicts to /home/rainyq/GDR-Net/.cache/dataset_dicts_lmo_test_f1f941cbcce3a9bc511361b5064d58cf.pkl
Traceback (most recent call last):
  File "core/gdrn_modeling/main_gdrn.py", line 153, in <module>
    launch(
  File "/home/rainyq/.local/lib/python3.8/site-packages/detectron2/engine/launch.py", line 82, in launch
    main_func(*args)
  File "core/gdrn_modeling/main_gdrn.py", line 114, in main
    return do_test(cfg, model)
  File "/home/rainyq/GDR-Net/core/gdrn_modeling/../../core/gdrn_modeling/engine.py", line 127, in do_test
    data_loader = build_gdrn_test_loader(cfg, dataset_name, train_objs=evaluator.train_objs)
  File "/home/rainyq/GDR-Net/core/gdrn_modeling/../../core/gdrn_modeling/data_loader.py", line 721, in build_gdrn_test_loader
    dataset_dicts = get_detection_dataset_dicts(
  File "/home/rainyq/.local/lib/python3.8/site-packages/detectron2/data/build.py", line 229, in get_detection_dataset_dicts
    assert len(dicts), "Dataset '{}' is empty!".format(dataset_name)
AssertionError: Dataset 'lmo_test' is empty!

It looks like that 'lmo_test' dataset was not successfully registered. What should me do?

[wangg12]

Perhaps you didn't prepare the dataset correctly. I cannot tell what the problem is given the limited information.

[Hsuweehou]

I got this same error. have you solved it?

[Hsuweehou]

Run evaluation sample

./core/gdrn_modeling/test_gdrn.sh configs/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e.py 0 output/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e/gdrn_lmo_real_pbr.pth

got error like:

[07/08 11:08:34 fvcore.common.checkpoint]: [Checkpointer] Loading from output/gdrn/lmo/a6_cPnP_AugAAETrunc_BG0.5_lmo_real_pbr0.1_40e/gdrn_lmo_real_pbr.pth ...
[0708_110834 core.gdrn_modeling.gdrn_custom_evaluator@98]: eval precision: False
[0708_110834 core.gdrn_modeling.datasets.lm_dataset_d2@97]: loading dataset dicts: lmo_test
100%|███████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1214/1214 [00:00<00:00, 13442.86it/s]
100%|████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1/1 [00:00<00:00,  8.74it/s]
[0708_110835 core.gdrn_modeling.datasets.lm_dataset_d2@219]: loaded 0 dataset dicts, using 0.12068194802850485s
[0708_110835 core.gdrn_modeling.datasets.lm_dataset_d2@223]: Dumped dataset_dicts to /home/rainyq/GDR-Net/.cache/dataset_dicts_lmo_test_f1f941cbcce3a9bc511361b5064d58cf.pkl
Traceback (most recent call last):
  File "core/gdrn_modeling/main_gdrn.py", line 153, in <module>
    launch(
  File "/home/rainyq/.local/lib/python3.8/site-packages/detectron2/engine/launch.py", line 82, in launch
    main_func(*args)
  File "core/gdrn_modeling/main_gdrn.py", line 114, in main
    return do_test(cfg, model)
  File "/home/rainyq/GDR-Net/core/gdrn_modeling/../../core/gdrn_modeling/engine.py", line 127, in do_test
    data_loader = build_gdrn_test_loader(cfg, dataset_name, train_objs=evaluator.train_objs)
  File "/home/rainyq/GDR-Net/core/gdrn_modeling/../../core/gdrn_modeling/data_loader.py", line 721, in build_gdrn_test_loader
    dataset_dicts = get_detection_dataset_dicts(
  File "/home/rainyq/.local/lib/python3.8/site-packages/detectron2/data/build.py", line 229, in get_detection_dataset_dicts
    assert len(dicts), "Dataset '{}' is empty!".format(dataset_name)
AssertionError: Dataset 'lmo_test' is empty!

It looks like that 'lmo_test' dataset was not successfully registered. What should me do?

iVE got an exact same error, any idea?have you resolved it?

[RainYQ]

No ......

[saintrealchoi]

I have the same problem. And I solve it. I have an error for building lmo_test dataset. because I didnt download lmo dataset. you should lmo dataset.

when i download LM dataset,

export SRC=https://bop.felk.cvut.cz/media/data/bop_datasets
wget $SRC/lm_base.zip         # Base archive with dataset info, camera parameters, etc.
wget $SRC/lm_models.zip       # 3D object models.
wget $SRC/lm_test_all.zip     # All test images ("_bop19" for a subset used in the BOP Challenge 2019/2020).
wget $SRC/lm_train_pbr.zip    # PBR training images (rendered with BlenderProc4BOP).

unzip lm_base.zip             # Contains folder "lm".
unzip lm_models.zip -d lm     # Unpacks to "lm".
unzip lm_test_all.zip -d lm   # Unpacks to "lm".
unzip lm_train_pbr.zip -d lm  # Unpacks to "lm".

and I DONOT download lmo dataset. If you command wget lmo_base.zip. you will download lmo dataset.

and it will be fixed