NotImplementedError: Support for `validation_epoch_end` has been removed in v2.0.0. `DocFormer` implements this method

[Arun-purakkatt]

Ran into this issue while running sample notebook on colab ... https://github.com/shabie/docformer/blob/master/examples/docformer_pl/document_image_classification_on_rvl_cdip/4.Document-image-classification-with-docformer.ipynb

1 if __name__ == "__main__":
----> 2     main()

6 frames
[<ipython-input-25-82eba9431764>](https://localhost:8080/#) in main()
     29         deterministic=True
     30     )
---> 31     trainer.fit(docformer, datamodule)

[/usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/trainer.py](https://localhost:8080/#) in fit(self, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path)
    527         model = _maybe_unwrap_optimized(model)
    528         self.strategy._lightning_module = model
--> 529         call._call_and_handle_interrupt(
    530             self, self._fit_impl, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path
    531         )

[/usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/call.py](https://localhost:8080/#) in _call_and_handle_interrupt(trainer, trainer_fn, *args, **kwargs)
     40         if trainer.strategy.launcher is not None:
     41             return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs)
---> 42         return trainer_fn(*args, **kwargs)
     43 
     44     except _TunerExitException:

[/usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/trainer.py](https://localhost:8080/#) in _fit_impl(self, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path)
    566             model_connected=self.lightning_module is not None,
    567         )
--> 568         self._run(model, ckpt_path=ckpt_path)
    569 
    570         assert self.state.stopped

[/usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/trainer.py](https://localhost:8080/#) in _run(self, model, ckpt_path)
    919         self._callback_connector._attach_model_logging_functions()
    920 
--> 921         _verify_loop_configurations(self)
    922 
    923         # hook

[/usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/configuration_validator.py](https://localhost:8080/#) in _verify_loop_configurations(trainer)
     34         raise ValueError("Unexpected: Trainer state fn must be set before validating loop configuration.")
     35     if trainer.state.fn == TrainerFn.FITTING:
---> 36         __verify_train_val_loop_configuration(trainer, model)
     37         __verify_manual_optimization_support(trainer, model)
     38         __check_training_step_requires_dataloader_iter(model)

[/usr/local/lib/python3.10/dist-packages/pytorch_lightning/trainer/configuration_validator.py](https://localhost:8080/#) in __verify_train_val_loop_configuration(trainer, model)
     82         )
     83     if callable(getattr(model, "validation_epoch_end", None)):
---> 84         raise NotImplementedError(
     85             f"Support for `validation_epoch_end` has been removed in v2.0.0. `{type(model).__name__}` implements this"
     86             " method. You can use the `on_validation_epoch_end` hook instead. To access outputs, save them in-memory as"

NotImplementedError: Support for `validation_epoch_end` has been removed in v2.0.0. `DocFormer` implements this method. You can use the `on_validation_epoch_end` hook instead. To access outputs, save them in-memory as instance attributes. You can find migration examples in https://github.com/Lightning-AI/lightning/pull/16520.

[cnr0724]

As it's written on the error explanation, if you are using pytorch-lightning or lightning v2.0.0 or higher this code might not work appropriately.

Here's what you can do.

1. Check what lightning package version is installed in your environment by 'pip list | grep lightning' or 'conda list lightning' etc. (It's up to how you have built your environment.) You might get 'lightning-utilities' and 'pytorch-lightning' as a result. It means that you've followed the old method of installing lightning package. It is deprecated.
2. (Not recommended) If you want to run this code without changing some parts, I recommend you to install older lightning package like v1.9.0.
   (Note that 'pip install pytorch-lightning' has been deprecated and stopped being updated since June 2023. 'pip install lightning==[version]' might work, but I haven't tried that way.)
3. (Recommended) If you could change some codes, I recommend installing the recent version of lightning package. You might have to change some parts. Main things that have to be changed are listed below.

• 'import pytorch_lightning as pl' -> 'import lightning.pytorch as pl'
• function 'train_epoch_end', 'validation_epoch_end' -> function 'on_train_epoch_end', 'on_validation_epoch_end'
  (Find them from class DocFormer(pl.LightningModule))

You might need to look at lightning offical page. Please refer to the link below.
https://lightning.ai/docs/pytorch/stable/

[uakarsh]

Hi @Arun-purakkatt, if that's the case, I think here is what we can do

1. See how the validation_epoch_end is actually implemented for pytorch_lightning v2, and then just rename the functions accordingly
2. This should work

Cheers,
Akarsh