Error in Example: Please provide the bounding box and words or pass the argument "use_ocr" = True

[bbalaji-ucsd]

Ran into this error while running the example notebook.

---------------------------------------------------------------------------
Exception                                 Traceback (most recent call last)
/tmp/ipykernel_33283/863471981.py in <cell line: 2>()
      1 ## Using a single batch for the forward propagation
----> 2 features = next(iter(train_data_loader))
      3 img,token,x_feat,y_feat, labels = features

~/anaconda3/envs/python3/lib/python3.8/site-packages/torch/utils/data/dataloader.py in __next__(self)
    679                 # TODO(https://github.com/pytorch/pytorch/issues/76750)
    680                 self._reset()  # type: ignore[call-arg]
--> 681             data = self._next_data()
    682             self._num_yielded += 1
    683             if self._dataset_kind == _DatasetKind.Iterable and \

~/anaconda3/envs/python3/lib/python3.8/site-packages/torch/utils/data/dataloader.py in _next_data(self)
    719     def _next_data(self):
    720         index = self._next_index()  # may raise StopIteration
--> 721         data = self._dataset_fetcher.fetch(index)  # may raise StopIteration
    722         if self._pin_memory:
    723             data = _utils.pin_memory.pin_memory(data, self._pin_memory_device)

~/anaconda3/envs/python3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py in fetch(self, possibly_batched_index)
     47     def fetch(self, possibly_batched_index):
     48         if self.auto_collation:
---> 49             data = [self.dataset[idx] for idx in possibly_batched_index]
     50         else:
     51             data = self.dataset[possibly_batched_index]

~/anaconda3/envs/python3/lib/python3.8/site-packages/torch/utils/data/_utils/fetch.py in <listcomp>(.0)
     47     def fetch(self, possibly_batched_index):
     48         if self.auto_collation:
---> 49             data = [self.dataset[idx] for idx in possibly_batched_index]
     50         else:
     51             data = self.dataset[possibly_batched_index]

/tmp/ipykernel_33283/2543102337.py in __getitem__(self, index)
     22         If labels are not None, then labels also
     23         '''
---> 24         encoding = create_features(self.entries[index],self.tokenizer, apply_mask_for_mlm=self.use_mlm)
     25 
     26         if self.labels==None:

~/docformer/examples/../src/docformer/dataset.py in create_features(image, tokenizer, add_batch_dim, target_size, max_seq_length, path_to_save, save_to_disk, apply_mask_for_mlm, extras_for_debugging, use_ocr, bounding_box, words)
    190 
    191     if (use_ocr == False) and (bounding_box == None or words == None):
--> 192         raise Exception('Please provide the bounding box and words or pass the argument "use_ocr" = True')
    193 
    194     if use_ocr == True:

Exception: Please provide the bounding box and words or pass the argument "use_ocr" = True

[uakarsh]

Hi @bbalaji-ucsd, actually while using the create_features function, if you are not explicitly providing the bounding box, you have to pass the argument use_ocr =True, currently it is False, and hence the error arises.

Hope this helps

Regards, Akarsh