dasayan05 / chirodiff Goto Github PK

Hey! I was trying to play with threeseqdel_classcond (or threeseqabs_classcond) however two problems came out.

1. preprocessing the directory into a .npz is not possible, i.g.

python data/qd.py /the/output/dir/cat threeseqdel_classcond

raises errors

Traceback (most recent call last):
  File "SOMEPATH/chirodiff_test/data/qd.py", line 281, in <module>
    dummy_sample = ds[0]
  File "SOMEPATH/chirodiff_test/data/qd.py", line 140, in __getitem__
    return self.represent(self.get_sketch(i))
  File "SOMEPATHchirodiff_test/data/qd.py", line 201, in represent
    label = torch.tensor(sketch.label, dtype=torch.int64)
TypeError: an integer is required (got type NoneType)

2. If i skip this step as suggested in README.md, and start the training. In the config.yml, I changed repr into threeseqdel_classcond. And for example, under the /the/output/dir/ I have two folders, cat and dog, seperately including some sketches, and therefore I setup num_classes: typing.Optional[int] = 2 in config.yml , as suggesed in ln 74 in main.py, and therefor I have root_dir in config.yml to be /the/output/dir/, and naturally the error becomes

SOMEPATH/pytorch_lightning/utilities/data.py:103: UserWarning: Total length of `CombinedLoader` across ranks is zero. Please make sure this was your intention.
  rank_zero_warn(
`Trainer.fit` stopped: No training batches.

I guess this could be easily fixed if you could remind some special settings/path selections specifically for the class condition?

Many thanks!

Thanks for you work! when i training follow your guidance, i have a error as follows, can you give me some suggestions? Thank you vey much.

Traceback (most recent call last):
File "/home/libj/LBJ/chirodiff2/main.py", line 692, in
cli = LightningCLI(SketchDiffusion, GenericDM, run=True,
File "/home/libj/.conda/envs/CONTROLNET2/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 515, in init
self.setup_parser(run, main_kwargs, subparser_kwargs)
File "/home/libj/.conda/envs/CONTROLNET2/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 551, in setup_parser
self._add_subcommands(self.parser, **subparser_kwargs)
File "/home/libj/.conda/envs/CONTROLNET2/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 624, in _add_subcommands
subcommand_parser = self._prepare_subcommand_parser(trainer_class, subcommand, **kwargs.get(subcommand, {}))
File "/home/libj/.conda/envs/CONTROLNET2/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 632, in _prepare_subcommand_parser
self._add_arguments(parser)
File "/home/libj/.conda/envs/CONTROLNET2/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 594, in _add_arguments
parser.add_lr_scheduler_args(LR_SCHEDULER_REGISTRY.classes)
File "/home/libj/.conda/envs/CONTROLNET2/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 213, in add_lr_scheduler_args
self.add_subclass_arguments(lr_scheduler_class, nested_key, **kwargs)
File "/home/libj/.conda/envs/CONTROLNET2/lib/python3.8/site-packages/jsonargparse/_signatures.py", line 503, in add_subclass_arguments
raise ValueError(f"Expected 'baseclass' argument to be a class or a tuple of classes: {baseclass}")
ValueError: Expected 'baseclass' argument to be a class or a tuple of classes: ()

Hello, I have the following problem while running the "python main.py fit --config config.yml --model.arch_layer 3 --model.noise_T 100 ..." command. Is this something to do with the jsonargparse version?

(M2021-YDY-chirodiff) M2021-YDY@hndx-R8424-G12:~/chirodiff-master$ python main.py fit --config config.yml --model.arch_layer 3 --model.noise_T 100 ...
Traceback (most recent call last):
  File "main.py", line 692, in <module>
    cli = LightningCLI(SketchDiffusion, GenericDM, run=True,
  File "/home/hndx/anaconda3/envs/M2021-YDY-chirodiff/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 515, in __init__
    self.setup_parser(run, main_kwargs, subparser_kwargs)
  File "/home/hndx/anaconda3/envs/M2021-YDY-chirodiff/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 551, in setup_parser
    self._add_subcommands(self.parser, **subparser_kwargs)
  File "/home/hndx/anaconda3/envs/M2021-YDY-chirodiff/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 624, in _add_subcommands
    subcommand_parser = self._prepare_subcommand_parser(trainer_class, subcommand, **kwargs.get(subcommand, {}))
  File "/home/hndx/anaconda3/envs/M2021-YDY-chirodiff/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 632, in _prepare_subcommand_parser
    self._add_arguments(parser)
  File "/home/hndx/anaconda3/envs/M2021-YDY-chirodiff/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 594, in _add_arguments
    parser.add_lr_scheduler_args(LR_SCHEDULER_REGISTRY.classes)
  File "/home/hndx/anaconda3/envs/M2021-YDY-chirodiff/lib/python3.8/site-packages/pytorch_lightning/utilities/cli.py", line 213, in add_lr_scheduler_args
    self.add_subclass_arguments(lr_scheduler_class, nested_key, **kwargs)
  File "/home/hndx/anaconda3/envs/M2021-YDY-chirodiff/lib/python3.8/site-packages/jsonargparse/signatures.py", line 477, in add_subclass_arguments
    doc_group = get_doc_short_description(baseclass[0], logger=self.logger)
IndexError: tuple index out of range

My version of jsonargparse is as followsjsonargparse 4.21.2

My Python version is 3.8.17 and pytorch-lightning version is 1.5.9

I get the following error

main.py: error: 'Configuration check failed :: No action for destination key "trainer.process_position" to check its value.'

on running python3.10 main.py --config config.yml fit --model.repr threeseqdel

My pytorch-lightning.__version__ == 1.5.9 and I believe trainer.process_position wasn't deprecated by then.