How to text_classifier_learner with multiple text input blocks?

fastai==2.1.6 (current master)

Input:

blocks = (
    TextBlock.from_df('a', seq_len=600, tok_text_col='a'),
    TextBlock.from_df('b', seq_len=500, tok_text_col='b'),
    TextBlock.from_df('c', seq_len=600, tok_text_col='c'),
    TextBlock.from_df('d', seq_len=1000, tok_text_col='d'),
    TextBlock.from_df('e', seq_len=1000, tok_text_col='e'),
    CategoryBlock
)
asin_clas = DataBlock(
    blocks=blocks,
    get_x=[
        ColReader('a'), 
        ColReader('b'), 
        ColReader('c'),
        ColReader('d'), 
        ColReader('e')
    ],
    get_y=ColReader('label'),
    splitter=RandomSplitter(seed=42)
)

dls = asin_clas.dataloaders(df, bs=128, verbose=True, do_setup=False)

Error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-19-99ae1f5d705e> in <module>
----> 1 learn.fine_tune(4, 1e-2)

/opt/conda/lib/python3.8/site-packages/fastai/callback/schedule.py in fine_tune(self, epochs, base_lr, freeze_epochs, lr_mult, pct_start, div, **kwargs)
    155     "Fine tune with `freeze` for `freeze_epochs` then with `unfreeze` from `epochs` using discriminative LR"
    156     self.freeze()
--> 157     self.fit_one_cycle(freeze_epochs, slice(base_lr), pct_start=0.99, **kwargs)
    158     base_lr /= 2
    159     self.unfreeze()

/opt/conda/lib/python3.8/site-packages/fastai/callback/schedule.py in fit_one_cycle(self, n_epoch, lr_max, div, div_final, pct_start, wd, moms, cbs, reset_opt)
    110     scheds = {'lr': combined_cos(pct_start, lr_max/div, lr_max, lr_max/div_final),
    111               'mom': combined_cos(pct_start, *(self.moms if moms is None else moms))}
--> 112     self.fit(n_epoch, cbs=ParamScheduler(scheds)+L(cbs), reset_opt=reset_opt, wd=wd)
    113 
    114 # Cell

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in fit(self, n_epoch, lr, wd, cbs, reset_opt)
    203             self.opt.set_hypers(lr=self.lr if lr is None else lr)
    204             self.n_epoch = n_epoch
--> 205             self._with_events(self._do_fit, 'fit', CancelFitException, self._end_cleanup)
    206 
    207     def _end_cleanup(self): self.dl,self.xb,self.yb,self.pred,self.loss = None,(None,),(None,),None,None

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    152 
    153     def _with_events(self, f, event_type, ex, final=noop):
--> 154         try:       self(f'before_{event_type}')       ;f()
    155         except ex: self(f'after_cancel_{event_type}')
    156         finally:   self(f'after_{event_type}')        ;final()

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _do_fit(self)
    194         for epoch in range(self.n_epoch):
    195             self.epoch=epoch
--> 196             self._with_events(self._do_epoch, 'epoch', CancelEpochException)
    197 
    198     def fit(self, n_epoch, lr=None, wd=None, cbs=None, reset_opt=False):

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    152 
    153     def _with_events(self, f, event_type, ex, final=noop):
--> 154         try:       self(f'before_{event_type}')       ;f()
    155         except ex: self(f'after_cancel_{event_type}')
    156         finally:   self(f'after_{event_type}')        ;final()

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _do_epoch(self)
    188 
    189     def _do_epoch(self):
--> 190         self._do_epoch_train()
    191         self._do_epoch_validate()
    192 

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _do_epoch_train(self)
    180     def _do_epoch_train(self):
    181         self.dl = self.dls.train
--> 182         self._with_events(self.all_batches, 'train', CancelTrainException)
    183 
    184     def _do_epoch_validate(self, ds_idx=1, dl=None):

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    152 
    153     def _with_events(self, f, event_type, ex, final=noop):
--> 154         try:       self(f'before_{event_type}')       ;f()
    155         except ex: self(f'after_cancel_{event_type}')
    156         finally:   self(f'after_{event_type}')        ;final()

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in all_batches(self)
    158     def all_batches(self):
    159         self.n_iter = len(self.dl)
--> 160         for o in enumerate(self.dl): self.one_batch(*o)
    161 
    162     def _do_one_batch(self):

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in one_batch(self, i, b)
    176         self.iter = i
    177         self._split(b)
--> 178         self._with_events(self._do_one_batch, 'batch', CancelBatchException)
    179 
    180     def _do_epoch_train(self):

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _with_events(self, f, event_type, ex, final)
    152 
    153     def _with_events(self, f, event_type, ex, final=noop):
--> 154         try:       self(f'before_{event_type}')       ;f()
    155         except ex: self(f'after_cancel_{event_type}')
    156         finally:   self(f'after_{event_type}')        ;final()

/opt/conda/lib/python3.8/site-packages/fastai/learner.py in _do_one_batch(self)
    161 
    162     def _do_one_batch(self):
--> 163         self.pred = self.model(*self.xb)
    164         self('after_pred')
    165         if len(self.yb): self.loss = self.loss_func(self.pred, *self.yb)

/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py in _call_impl(self, *input, **kwargs)
    725             result = self._slow_forward(*input, **kwargs)
    726         else:
--> 727             result = self.forward(*input, **kwargs)
    728         for hook in itertools.chain(
    729                 _global_forward_hooks.values(),

TypeError: forward() takes 2 positional arguments but 6 were given

To make this work you would probably need a custom model. Depending on the text data you might want either call the same encoder multiple times or to have several encoders. Then you’ll have to aggregate outputs of those encoders somehow to feed them to the classifier

1 Like

Got it. Which means I will have to create one more Architecture? Or AWD_LSTM can support this?

Sorry for naive question.

No need to create new architecture, AWD_LSTM may be used as arch for sentence encoder. You will have to define higher level model logic. See SentenceEncoder definition and get_text_classifier for reference. I believe there are some examples closer to your task. Try searching forums for “siamese sentence” or “siamese text”

1 Like

Awesome. Let me do that. I will update the thread once I find the solution. For the next person :slight_smile:

1 Like