Mark trainer.data_connector as protected (#10031)

Co-authored-by: tchaton <[email protected]>

Author: daniellepintz

pytorch_lightning/loops/dataloader/evaluation_loop.py

@@ -101,7 +101,7 @@ def advance(self, *args: Any, **kwargs: Any) -> None:
 
         dataloader_idx: int = self.current_dataloader_idx
         dataloader = self.trainer.training_type_plugin.process_dataloader(self.current_dataloader)
-        dataloader = self.trainer.data_connector.get_profiled_dataloader(dataloader, dataloader_idx=dataloader_idx)
+        dataloader = self.trainer._data_connector.get_profiled_dataloader(dataloader, dataloader_idx=dataloader_idx)
         dl_max_batches = self._max_batches[dataloader_idx]
 
         dl_outputs = self.epoch_loop.run(dataloader, dataloader_idx, dl_max_batches, self.num_dataloaders)

pytorch_lightning/loops/epoch/evaluation_epoch_loop.py

@@ -107,7 +107,7 @@ def advance(
         if batch is None:
             raise StopIteration
 
-        if not self.trainer.data_connector.evaluation_data_fetcher.store_on_device:
+        if not self.trainer._data_connector.evaluation_data_fetcher.store_on_device:
             with self.trainer.profiler.profile("evaluation_batch_to_device"):
                 batch = self.trainer.accelerator.batch_to_device(batch, dataloader_idx=dataloader_idx)
 

pytorch_lightning/loops/epoch/training_epoch_loop.py

@@ -147,7 +147,7 @@ def advance(self, *args: Any, **kwargs: Any) -> None:
 
         batch_idx, (batch, self.batch_progress.is_last_batch) = next(self._dataloader_iter)
 
-        if not self.trainer.data_connector.train_data_fetcher.store_on_device:
+        if not self.trainer._data_connector.train_data_fetcher.store_on_device:
             with self.trainer.profiler.profile("training_batch_to_device"):
                 batch = self.trainer.accelerator.batch_to_device(batch)
 

pytorch_lightning/loops/fit_loop.py

@@ -212,7 +212,7 @@ def on_advance_start(self) -> None:
     def advance(self) -> None:
         """Runs one whole epoch."""
         dataloader = self.trainer.training_type_plugin.process_dataloader(self.trainer.train_dataloader)
-        data_fetcher = self.trainer.data_connector.get_profiled_dataloader(dataloader)
+        data_fetcher = self.trainer._data_connector.get_profiled_dataloader(dataloader)
 
         with self.trainer.profiler.profile("run_training_epoch"):
             self.epoch_loop.run(data_fetcher)

pytorch_lightning/plugins/training_type/deepspeed.py

@@ -623,7 +623,7 @@ def _auto_select_batch_size(self):
         # train_micro_batch_size_per_gpu is used for throughput logging purposes
         # by default we try to use the batch size of the loader
         batch_size = 1
-        train_dl_source = self.lightning_module.trainer.data_connector._train_dataloader_source
+        train_dl_source = self.lightning_module.trainer._data_connector._train_dataloader_source
         if train_dl_source.is_defined():
             train_dataloader = train_dl_source.dataloader()
             if hasattr(train_dataloader, "batch_sampler"):

pytorch_lightning/plugins/training_type/tpu_spawn.py

@@ -95,7 +95,7 @@ def _validate_dataloader(dataloaders: Union[List[DataLoader], DataLoader]) -> No
     @staticmethod
     def _validate_patched_dataloaders(model: "pl.LightningModule") -> None:
         """Validate and fail fast if the dataloaders were passed directly to fit."""
-        connector: DataConnector = model.trainer.data_connector
+        connector: DataConnector = model.trainer._data_connector
         sources = (
             connector._train_dataloader_source,
             connector._val_dataloader_source,

pytorch_lightning/trainer/configuration_validator.py

@@ -65,7 +65,7 @@ def __verify_train_loop_configuration(trainer: "pl.Trainer", model: "pl.Lightnin
     # -----------------------------------
     # verify model has a train dataloader
     # -----------------------------------
-    has_train_dataloader = trainer.data_connector._train_dataloader_source.is_defined()
+    has_train_dataloader = trainer._data_connector._train_dataloader_source.is_defined()
     if not has_train_dataloader:
         raise MisconfigurationException(
             "No `train_dataloader()` method defined. Lightning `Trainer` expects as minimum a"
@@ -176,7 +176,7 @@ def __verify_eval_loop_configuration(model: "pl.LightningModule", stage: str) ->
 
 
 def __verify_predict_loop_configuration(trainer: "pl.Trainer", model: "pl.LightningModule") -> None:
-    has_predict_dataloader = trainer.data_connector._predict_dataloader_source.is_defined()
+    has_predict_dataloader = trainer._data_connector._predict_dataloader_source.is_defined()
     if not has_predict_dataloader:
         raise MisconfigurationException("Dataloader not found for `Trainer.predict`")
     # ----------------------------------------------

pytorch_lightning/trainer/data_loading.py

@@ -343,7 +343,7 @@ def reset_train_dataloader(self, model: Optional["pl.LightningModule"] = None) -
             apply_to_collection(self.train_dataloader, DataLoader, self._add_sampler_metadata_collate)
 
         # wrap the sequence of train loaders to a CombinedLoader object for computing the num_training_batches
-        self.train_dataloader = CombinedLoader(self.train_dataloader, self.data_connector.multiple_trainloader_mode)
+        self.train_dataloader = CombinedLoader(self.train_dataloader, self._data_connector.multiple_trainloader_mode)
 
         self.num_training_batches = len(self.train_dataloader) if has_len(self.train_dataloader) else float("inf")
 
@@ -488,7 +488,7 @@ def reset_val_dataloader(self, model: Optional["pl.LightningModule"] = None) ->
         Args:
             model: The `LightningModule` if called outside of the trainer scope.
         """
-        source = self.data_connector._val_dataloader_source
+        source = self._data_connector._val_dataloader_source
         pl_module = self.lightning_module or model
         has_step = is_overridden("validation_step", pl_module)
         if source.is_defined() and has_step:
@@ -502,7 +502,7 @@ def reset_test_dataloader(self, model: Optional["pl.LightningModule"] = None) ->
         Args:
             model: The `LightningModule` if called outside of the trainer scope.
         """
-        source = self.data_connector._test_dataloader_source
+        source = self._data_connector._test_dataloader_source
         pl_module = self.lightning_module or model
         has_step = is_overridden("test_step", pl_module)
         if source.is_defined() and has_step:
@@ -516,7 +516,7 @@ def reset_predict_dataloader(self, model: Optional["pl.LightningModule"] = None)
         Args:
             model: The `LightningModule` if called outside of the trainer scope.
         """
-        source = self.data_connector._predict_dataloader_source
+        source = self._data_connector._predict_dataloader_source
         pl_module = self.lightning_module or model
         if source.is_defined():
             self.num_predict_batches, self.predict_dataloaders = self._reset_eval_dataloader(
@@ -545,7 +545,7 @@ def request_dataloader(
         Returns:
             The requested dataloader
         """
-        source = getattr(self.data_connector, f"_{stage.dataloader_prefix}_dataloader_source")
+        source = getattr(self._data_connector, f"_{stage.dataloader_prefix}_dataloader_source")
 
         hook = f"{stage.dataloader_prefix}_dataloader"
         self.call_hook("on_" + hook, pl_module=model)

pytorch_lightning/trainer/trainer.py

@@ -424,7 +424,7 @@ def __init__(
         gpu_ids, tpu_cores = self._parse_devices(gpus, auto_select_gpus, tpu_cores)
 
         # init connectors
-        self.data_connector = DataConnector(self, multiple_trainloader_mode)
+        self._data_connector = DataConnector(self, multiple_trainloader_mode)
         self.optimizer_connector = OptimizerConnector(self)
 
         self.accelerator_connector = AcceleratorConnector(
@@ -514,7 +514,7 @@ def __init__(
         self.optimizer_connector.on_trainer_init()
 
         # init data flags
-        self.data_connector.on_trainer_init(
+        self._data_connector.on_trainer_init(
             check_val_every_n_epoch,
             reload_dataloaders_every_n_epochs,
             reload_dataloaders_every_epoch,
@@ -663,7 +663,7 @@ def _fit_impl(
             )
 
         # links data to the trainer
-        self.data_connector.attach_data(
+        self._data_connector.attach_data(
             model, train_dataloaders=train_dataloaders, val_dataloaders=val_dataloaders, datamodule=datamodule
         )
 
@@ -747,7 +747,7 @@ def _validate_impl(
             )
 
         # links data to the trainer
-        self.data_connector.attach_data(model, val_dataloaders=dataloaders, datamodule=datamodule)
+        self._data_connector.attach_data(model, val_dataloaders=dataloaders, datamodule=datamodule)
 
         self.validated_ckpt_path = self.__set_ckpt_path(
             ckpt_path, model_provided=model_provided, model_connected=self.lightning_module is not None
@@ -837,7 +837,7 @@ def _test_impl(
             )
 
         # links data to the trainer
-        self.data_connector.attach_data(model, test_dataloaders=dataloaders, datamodule=datamodule)
+        self._data_connector.attach_data(model, test_dataloaders=dataloaders, datamodule=datamodule)
 
         self.tested_ckpt_path = self.__set_ckpt_path(
             ckpt_path, model_provided=model_provided, model_connected=self.lightning_module is not None
@@ -921,7 +921,7 @@ def _predict_impl(
             )
 
         # links data to the trainer
-        self.data_connector.attach_data(model, predict_dataloaders=dataloaders, datamodule=datamodule)
+        self._data_connector.attach_data(model, predict_dataloaders=dataloaders, datamodule=datamodule)
 
         self.predicted_ckpt_path = self.__set_ckpt_path(
             ckpt_path, model_provided=model_provided, model_connected=self.lightning_module is not None
@@ -985,7 +985,7 @@ def tune(
             )
 
         # links data to the trainer
-        self.data_connector.attach_data(
+        self._data_connector.attach_data(
             model, train_dataloaders=train_dataloaders, val_dataloaders=val_dataloaders, datamodule=datamodule
         )
 
@@ -1027,7 +1027,7 @@ def _run(self, model: "pl.LightningModule") -> Optional[Union[_EVALUATE_OUTPUT,
         self.training_type_plugin.connect(model)
 
         # hook
-        self.data_connector.prepare_data()
+        self._data_connector.prepare_data()
         self.callback_connector._attach_model_callbacks()
 
         if self._ckpt_path and not self.training_type_plugin.restore_checkpoint_after_pre_dispatch:
@@ -1171,7 +1171,7 @@ def _post_dispatch(self):
         # these `teardown` calls are here instead of in `_call_teardown_hook` since they are internal teardowns
         # which need to happen before.
         self.accelerator.teardown()
-        self.data_connector.teardown()
+        self._data_connector.teardown()
         self._active_loop.teardown()
         self.logger_connector.teardown()
 
@@ -1258,7 +1258,7 @@ def _run_predict(self) -> Optional[_PREDICT_OUTPUT]:
             return self.predict_loop.run()
 
     def _run_sanity_check(self, ref_model):
-        using_val_step = self.data_connector._val_dataloader_source.is_defined() and is_overridden(
+        using_val_step = self._data_connector._val_dataloader_source.is_defined() and is_overridden(
             "validation_step", ref_model
         )
         should_sanity_check = using_val_step and self.num_sanity_val_steps > 0 and self.limit_val_batches > 0

pytorch_lightning/tuner/batch_size_scaling.py

@@ -51,7 +51,7 @@ def scale_batch_size(
             " If this is not the intended behavior, please remove either one."
         )
 
-    if not trainer.data_connector._train_dataloader_source.is_module():
+    if not trainer._data_connector._train_dataloader_source.is_module():
         raise MisconfigurationException(
             "The batch scaling feature cannot be used with dataloaders passed directly to `.fit()`."
             " Please disable the feature or incorporate the dataloader into the model."