TypeError: 'function' object is not iterable

[chriswangky]

TypeError                                 Traceback (most recent call last)
<ipython-input-9-303af62577c3> in <module>
     65           n=30, d_model=50,
     66           stage1_med_dim=50, stage1_out_dim=100, stage2_out_dim=200,
---> 67           epoch=10
     68           )

<ipython-input-9-303af62577c3> in train_mct(config, n, d_model, stage1_med_dim, stage1_out_dim, stage2_out_dim, epoch)
     49     trainer = Trainer(**kwargs)
     50     trainer.fit(model, train_dataloaders=train_dataloader,
---> 51                 val_dataloaders=val_dataloader)
     52 
     53 

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in fit(self, model, train_dataloaders, val_dataloaders, datamodule, train_dataloader, ckpt_path)
    739             train_dataloaders = train_dataloader
    740         self._call_and_handle_interrupt(
--> 741             self._fit_impl, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path
    742         )
    743 

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in _call_and_handle_interrupt(self, trainer_fn, *args, **kwargs)
    683         """
    684         try:
--> 685             return trainer_fn(*args, **kwargs)
    686         # TODO: treat KeyboardInterrupt as BaseException (delete the code below) in v1.7
    687         except KeyboardInterrupt as exception:

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in _fit_impl(self, model, train_dataloaders, val_dataloaders, datamodule, ckpt_path)
    775         # TODO: ckpt_path only in v1.7
    776         ckpt_path = ckpt_path or self.resume_from_checkpoint
--> 777         self._run(model, ckpt_path=ckpt_path)
    778 
    779         assert self.state.stopped

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in _run(self, model, ckpt_path)
   1197 
   1198         # dispatch `start_training` or `start_evaluating` or `start_predicting`
-> 1199         self._dispatch()
   1200 
   1201         # plugin will finalized fitting (e.g. ddp_spawn will load trained model)

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in _dispatch(self)
   1277             self.training_type_plugin.start_predicting(self)
   1278         else:
-> 1279             self.training_type_plugin.start_training(self)
   1280 
   1281     def run_stage(self):

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\plugins\training_type\training_type_plugin.py in start_training(self, trainer)
    200     def start_training(self, trainer: "pl.Trainer") -> None:
    201         # double dispatch to initiate the training loop
--> 202         self._results = trainer.run_stage()
    203 
    204     def start_evaluating(self, trainer: "pl.Trainer") -> None:

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in run_stage(self)
   1287         if self.predicting:
   1288             return self._run_predict()
-> 1289         return self._run_train()
   1290 
   1291     def _pre_training_routine(self):

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in _run_train(self)
   1309             self.progress_bar_callback.disable()
   1310 
-> 1311         self._run_sanity_check(self.lightning_module)
   1312 
   1313         # enable train mode

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\trainer\trainer.py in _run_sanity_check(self, ref_model)
   1373             # run eval step
   1374             with torch.no_grad():
-> 1375                 self._evaluation_loop.run()
   1376 
   1377             self.call_hook("on_sanity_check_end")

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\loops\base.py in run(self, *args, **kwargs)
    143             try:
    144                 self.on_advance_start(*args, **kwargs)
--> 145                 self.advance(*args, **kwargs)
    146                 self.on_advance_end()
    147                 self.restarting = False

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\loops\dataloader\evaluation_loop.py in advance(self, *args, **kwargs)
    108         dl_max_batches = self._max_batches[dataloader_idx]
    109 
--> 110         dl_outputs = self.epoch_loop.run(dataloader, dataloader_idx, dl_max_batches, self.num_dataloaders)
    111 
    112         # store batch level output per dataloader

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\loops\base.py in run(self, *args, **kwargs)
    138         self.reset()
    139 
--> 140         self.on_run_start(*args, **kwargs)
    141 
    142         while not self.done:

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\loops\epoch\evaluation_epoch_loop.py in on_run_start(self, data_fetcher, dataloader_idx, dl_max_batches, num_dataloaders)
     84 
     85         self._reload_dataloader_state_dict(data_fetcher)
---> 86         self._dataloader_iter = _update_dataloader_iter(data_fetcher, self.batch_progress.current.ready)
     87 
     88     def advance(

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\loops\utilities.py in _update_dataloader_iter(data_fetcher, batch_idx)
    119     if not isinstance(data_fetcher, DataLoaderIterDataFetcher):
    120         # restore iteration
--> 121         dataloader_iter = enumerate(data_fetcher, batch_idx)
    122     else:
    123         dataloader_iter = iter(data_fetcher)

~\AppData\Local\Programs\Python\Python36\lib\site-packages\pytorch_lightning\utilities\fetching.py in __iter__(self)
    195             raise MisconfigurationException("The iterate hasn't been provided. HINT: Did you call setup function ?.")
    196         self.reset()
--> 197         self.dataloader_iter = iter(self.dataloader)
    198         self._apply_patch()
    199         self.prefetching(self.prefetch_batches)

And here is my code.

def train_mct(config, epoch):
    # prepare dir for model path

    # seed everything
    seed_everything(seed=9876, workers=True)

    def train_dataloader(self):
        # expect to get train folder
        dataset = load_train_data(df)
        dataloader = DataLoader(dataset, batch_size=32, num_workers=0, persistent_workers=True,
                                collate_fn=dataset_collate_function, shuffle=True)

        return dataloader

    def val_dataloader(self):
        # expect to get validation folder
        dataset = load_train_data(df)
        dataloader = DataLoader(dataset, num_workers=0, persistent_workers=True,
                                collate_fn=dataset_collate_function, shuffle=False)

        return dataloader

    model = MCT(config=config).float()

    kwargs = {
        "max_epochs": epoch,
        "enable_progress_bar": False,
        "val_check_interval": 1.0,
        "callbacks": [
            EarlyStopping(
                monitor='training_loss',
                patience=20, mode='min',
                check_on_train_epoch_end=True)
        ]
    }

    trainer = Trainer(**kwargs)
    trainer.fit(model, train_dataloaders=train_dataloader,
                val_dataloaders=val_dataloader)

config = {
    "n_layers_s1": 3,
    "n_layers_s2": 3,
    "n_heads": 5,
    "d_ff": 1024,
    "lr": 0.01,
    "app_weight": 4,
    "signal_length": 1500,
    "res_s0": True
}
train_mct(config, epoch=10)

And advice on what happpend.
Thank you!

[rohitgr7]

update

trainer.fit(model, train_dataloaders=train_dataloader,
                val_dataloaders=val_dataloader)

to

trainer.fit(model, train_dataloaders=train_dataloader(),
                val_dataloaders=val_dataloader())

since train_dataloader/val_dataloader is a function in your case.