search

lcosmo / DGM_pytorch

49 stars 16 forks source link

DataLoader Error #4

Open Juanfma12 opened 1 year ago

Juanfma12 commented 1 year ago

Hey, so i'm gonna use the Differentiable Graph Module in a project and i cant get it to work with the default settings. When i run the train.py, i get an error (after some epochs run succesfully) stating the following:

ValueError: An invalid dataloader was passed to Trainer.test(dataloaders=...). Either pass the dataloader to the .test() method OR implement def test_dataloader(self): in your LightningModule/LightningDataModule.

However, i didn't change anything in the train.py, left it as is. Im using windows 11 (No keops) and using the latest versions of pytorch, pytorch-lightning, sparse and scatter, since i was having errors regarding cuda and methods that were deprecated with the versions in the current readme (pytorch 1.8.1, cuda 10.1, scatter 2.0.8, sparse 0.6.12).

With-the-sun commented 1 year ago

hi, Maybe windows just doesn't work(Maybe the author is using linux ) @Juanfma12

ZeinabRahbar commented 1 year ago

Traceback (most recent call last): File "/content/DGM_pytorch/train.py", line 13, in import pytorch_lightning as pl File "/usr/local/lib/python3.10/site-packages/pytorch_lightning/init.py", line 20, in from pytorch_lightning import metrics # noqa: E402 File "/usr/local/lib/python3.10/site-packages/pytorch_lightning/metrics/init.py", line 15, in from pytorch_lightning.metrics.classification import ( # noqa: F401 File "/usr/local/lib/python3.10/site-packages/pytorch_lightning/metrics/classification/init.py", line 14, in from pytorch_lightning.metrics.classification.accuracy import Accuracy # noqa: F401 File "/usr/local/lib/python3.10/site-packages/pytorch_lightning/metrics/classification/accuracy.py", line 16, in from torchmetrics import Accuracy as _Accuracy File "/usr/local/lib/python3.10/site-packages/torchmetrics/init.py", line 14, in from torchmetrics import functional # noqa: E402 File "/usr/local/lib/python3.10/site-packages/torchmetrics/functional/init.py", line 60, in from torchmetrics.functional.text.bert import bert_score File "/usr/local/lib/python3.10/site-packages/torchmetrics/functional/text/bert.py", line 247, in def _get_progress_bar(dataloader: DataLoader, verbose: bool = False) -> Union[DataLoader, tqdm.auto.tqdm]: AttributeError: module 'tqdm' has no attribute 'auto'

ZeinabRahbar commented 6 months ago

you can see version that i ran on colab if you need help message me @Juanfma12