Open lpy29 opened 4 weeks ago
Could you run your script with HYDRA_FULL_ERROR=1 as recommended by the error message? That will help us trace your bug.
Error executing job with overrides: [] Traceback (most recent call last): File "/opt/conda/lib/python3.7/site-packages/hydra/_internal/utils.py", line 644, in _locate obj = getattr(obj, part) AttributeError: module 'models' has no attribute 'Mask3D'
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/site-packages/hydra/_internal/utils.py", line 650, in _locate
obj = import_module(mod)
File "/opt/conda/lib/python3.7/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "
The above exception was the direct cause of the following exception:
Traceback (most recent call last): File "/opt/conda/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 134, in _resolve_target target = _locate(target) File "/opt/conda/lib/python3.7/site-packages/hydra/_internal/utils.py", line 656, in _locate ) from exc_import ImportError: Error loading 'models.Mask3D': ModuleNotFoundError("No module named 'models.Mask3D'") Are you sure that 'Mask3D' is importable from module 'models'?
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "main_instance_segmentation.py", line 118, in
During handling of the above exception, another exception occurred:
Traceback (most recent call last):
File "/opt/conda/lib/python3.7/site-packages/hydra/_internal/utils.py", line 650, in _locate
obj = import_module(mod)
File "/opt/conda/lib/python3.7/importlib/init.py", line 127, in import_module
return _bootstrap._gcd_import(name[level:], package, level)
File "
The above exception was the direct cause of the following exception:
Traceback (most recent call last): File "/opt/conda/lib/python3.7/site-packages/hydra/_internal/instantiate/_instantiate2.py", line 134, in _resolve_target target = _locate(target) File "/opt/conda/lib/python3.7/site-packages/hydra/_internal/utils.py", line 656, in _locate ) from exc_import ImportError: Error loading 'models.Mask3D': ModuleNotFoundError("No module named 'models.Mask3D'") Are you sure that 'Mask3D' is importable from module 'models'?
The above exception was the direct cause of the following exception:
Traceback (most recent call last):
File "main_instance_segmentation.py", line 118, in
Hey @lpy29,
you are right, there were indeed incorrect import paths in the code after refactoring. Could you please pull the latest commits and run it again? Additionally, I also added a docker container where reproducing the code could be easier now.
Hope this helps! Cheers, David
Thank you for your reply!But I I get another error when running run. scripts/mask3d_DINO_CSC_self_train.sh: Traceback (most recent call last): File "main_instance_segmentation.py", line 112, in main train(cfg) File "/opt/conda/lib/python3.7/site-packages/hydra/main.py", line 83, in decorated_main return task_function(cfg_passthrough) File "main_instance_segmentation.py", line 79, in train cfg, model, loggers = get_parameters(cfg) File "main_instance_segmentation.py", line 64, in get_parameters cfg, model = load_checkpoint_with_missing_or_exsessive_keys(cfg, model) File "/home/Unscene3D/utils/utils.py", line 96, in load_checkpoint_with_missing_or_exsessive_keys state_dict = torch.load(cfg.general.checkpoint)["state_dict"] File "/opt/conda/lib/python3.7/site-packages/torch/serialization.py", line 594, in load with _open_file_like(f, 'rb') as opened_file: File "/opt/conda/lib/python3.7/site-packages/torch/serialization.py", line 230, in _open_file_like return _open_file(name_or_buffer, mode) File "/opt/conda/lib/python3.7/site-packages/torch/serialization.py", line 211, in init super(_open_file, self).init(open(name, mode)) FileNotFoundError: [Errno 2] No such file or directory: 'data/self_train/DINO_CSC_self_train'. Are the results of DINO_CSC_self_train available?
you are missing the first stage of training with standard parameters. you'd need to run:
. scripts/unsupervised/train_unscene3d.sh "DINO_CSC_self_train" ""
in your parent folder. Also please dont forget the change the paths in the preprocessed datasets to your local setup.
I have tried to run:. scripts/unsupervised/train_unscene3d.sh "DINO_CSC_self_train" "",but i got new error: Epoch 0: 0%| | 0/300 [00:00<?, ?it/s]Could not load self training data for scene0582_02 Could not load self training data for scene0114_02 Could not load self training data for scene0035_01 it seems like missing the code that saving these masks as an extension to the original pseudo dataset?
You are still missing the self training inputs where the model expects to load from the given directories. Please check the available configurations parameters here or start the standard, non-pretraining setup first with:
. scripts/unsupervised/train_unscene3d_dino_csc.sh
Hello! When I run. scripts/mask3d_DINO_CSC_self_train.sh,I get an error:
Error locating target 'models.Mask3D', set env var HYDRA_FULL_ERROR=1 to see chained exception. full_key: model AttributeError: module 'models' has no attribute 'Mask3D' During handling of the above exception, another exception occurred: ModuleNotFoundError: No module named 'models.Mask3D'
Could you help me fix this error?