OV API2.0

[paularamo]

Description

• Refactoring OpenVINO API 1.0 to API 2.0. Also including model caching and config argument for changing model precision in the OpenVINO inferencer.

• Fixes # (issue)

Changes

• Bug fix (non-breaking change which fixes an issue)
• Refactor (non-breaking change which refactors the code base)
• New feature (non-breaking change which adds functionality)
• Breaking change (fix or feature that would cause existing functionality to not work as expected)
• This change requires a documentation update

Checklist

• My code follows the pre-commit style and check guidelines of this project.
• I have performed a self-review of my code
• I have commented my code, particularly in hard-to-understand areas
• I have made corresponding changes to the documentation
• My changes generate no new warnings
• I have added tests that prove my fix is effective or that my feature works
• New and existing tests pass locally with my changes
• I have added a summary of my changes to the CHANGELOG (not for minor changes, docs and tests).

[paularamo]

@samet-akcay Running NNCF Notebook, I see this error:

C:\Users\paularam\Intel\tests\anomalib_env\lib\site-packages\torchmetrics\utilities\prints.py:36: UserWarning: Metric PrecisionRecallCurve will save all targets and predictions in buffer. For large datasets this may lead to large memory footprint.
warnings.warn(*args, **kwargs)
FeatureExtractor is deprecated. Use TimmFeatureExtractor instead. Both FeatureExtractor and TimmFeatureExtractor will be removed in a future release.
C:\Users\paularam\Intel\tests\anomalib_env\lib\site-packages\openvino\offline_transformations_init_.py:10: FutureWarning: The module is private and following namespace offline_transformations will be removed in the future, use openvino.runtime.passes instead!
warnings.warn(
INFO:nncf:NNCF initialized successfully. Supported frameworks detected: torch, onnx, openvino
WARNING:nncf:NNCF provides best results with torch==1.13.1, while current torch version is 2.0.1+cpu. If you encounter issues, consider switching to torch==1.13.1
GPU available: False, used: False
TPU available: False, using: 0 TPU cores
IPU available: False, using: 0 IPUs
HPU available: False, using: 0 HPUs
Trainer(limit_train_batches=1.0) was configured so 100% of the batches per epoch will be used..
Trainer(limit_val_batches=1.0) was configured so 100% of the batches will be used..
Trainer(limit_test_batches=1.0) was configured so 100% of the batches will be used..
Trainer(limit_predict_batches=1.0) was configured so 100% of the batches will be used..
Trainer(val_check_interval=1.0) was configured so validation will run at the end of the training epoch..

TypeError Traceback (most recent call last)
Cell In[10], line 7
5 # start training
6 trainer = Trainer(**config.trainer, callbacks=callbacks)
----> 7 trainer.fit(model=model, datamodule=datamodule)
8 int8_results = trainer.test(model=model, datamodule=datamodule)

File ~\Intel\tests\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py:608, in Trainer.fit(self, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path)
606 model = self._maybe_unwrap_optimized(model)
607 self.strategy._lightning_module = model
--> 608 call._call_and_handle_interrupt(
609 self, self._fit_impl, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path
610 )

File ~\Intel\tests\anomalib_env\lib\site-packages\pytorch_lightning\trainer\call.py:38, in _call_and_handle_interrupt(trainer, trainer_fn, *args, **kwargs)
36 return trainer.strategy.launcher.launch(trainer_fn, *args, trainer=trainer, **kwargs)
37 else:
---> 38 return trainer_fn(*args, **kwargs)
40 except _TunerExitException:
41 trainer._call_teardown_hook()

File ~\Intel\tests\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py:650, in Trainer._fit_impl(self, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path)
643 ckpt_path = ckpt_path or self.resume_from_checkpoint
644 self._ckpt_path = self._checkpoint_connector._set_ckpt_path(
645 self.state.fn,
646 ckpt_path, # type: ignore[arg-type]
647 model_provided=True,
648 model_connected=self.lightning_module is not None,
649 )
--> 650 self._run(model, ckpt_path=self.ckpt_path)
652 assert self.state.stopped
653 self.training = False

File ~\Intel\tests\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py:1051, in Trainer._run(self, model, ckpt_path)
1048 self.strategy.setup_environment()
1049 self.__setup_profiler()
-> 1051 self._call_setup_hook() # allow user to setup lightning_module in accelerator environment
1053 # check if we should delay restoring checkpoint till later
1054 if not self.strategy.restore_checkpoint_after_setup:

File ~\Intel\tests\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py:1299, in Trainer._call_setup_hook(self)
1297 if self.datamodule is not None:
1298 self._call_lightning_datamodule_hook("setup", stage=fn)
-> 1299 self._call_callback_hooks("setup", stage=fn)
1300 self._call_lightning_module_hook("setup", stage=fn)
1302 self.strategy.barrier("post_setup")

File ~\Intel\tests\anomalib_env\lib\site-packages\pytorch_lightning\trainer\trainer.py:1394, in Trainer._call_callback_hooks(self, hook_name, *args, **kwargs)
1392 if callable(fn):
1393 with self.profiler.profile(f"[Callback]{callback.state_key}.{hook_name}"):
-> 1394 fn(self, self.lightning_module, *args, **kwargs)
1396 if pl_module:
1397 # restore current_fx when nested context
1398 pl_module._current_fx_name = prev_fx_name

File ~\Intel\tests\anomalib_env\lib\site-packages\anomalib\utils\callbacks\nncf\callback.py:54, in NNCFCallback.setup(failed resolving arguments)
51 init_loader = InitLoader(trainer.datamodule.val_dataloader()) # type: ignore
52 config = register_default_init_args(self.config, init_loader)
---> 54 self.nncf_ctrl, pl_module.model = wrap_nncf_model(
55 model=pl_module.model, config=config, dataloader=trainer.datamodule.train_dataloader() # type: ignore
56 )

TypeError: wrap_nncf_model() missing 1 required positional argument: 'init_state_dict'

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[paularamo]

@samet-akcay @dmatveev @ashwinvaidya17 Could you please take a look of this we need to test it out in Hugging Face Space. If this issue is not solved I cannot test it. Thanks for your helping.

[ashwinvaidya17]

metadata_path is not defined. Did you mean to use metadata?