incomplete captions generated!

[Monikshah]

I ran your test.py file, and printed the gen (generated caption), there are so many captions that are incomplete sentences such as:

• "a desk with two computer monitors and a laptop on a"
• "a traffic light in front of a building with a"

I am not sure if this is the case. Cam you please let me know why I am getting many incomplete sentences as generated caption using this model?

Thank you!

[thalapandi]

Type of dataset attribute: <class 'main.PairedDataset'> collate_fn is callable. Length of train dataloader: 35403 Length of validation dataloader: 1563 Length of test dataloader: 313 Is collate_fn callable? True

TypeError Traceback (most recent call last) in <cell line: 74>() 72 print("Is collate_fn callable?", callable(dataloader_train.dataset.collate_fn)) 73 ---> 74 for it, (images, captions) in enumerate(dataloader_train): 75 try: 76 print("Iteration:", it)

2 frames /usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py in next(self) 629 # TODO(https://github.com/pytorch/pytorch/issues/76750) 630 self._reset() # type: ignore[call-arg] --> 631 data = self._next_data() 632 self._num_yielded += 1 633 if self._dataset_kind == _DatasetKind.Iterable and \

/usr/local/lib/python3.10/dist-packages/torch/utils/data/dataloader.py in _next_data(self) 673 def _next_data(self): 674 index = self._next_index() # may raise StopIteration --> 675 data = self._dataset_fetcher.fetch(index) # may raise StopIteration 676 if self._pin_memory: 677 data = _utils.pin_memory.pin_memory(data, self._pin_memory_device)

/usr/local/lib/python3.10/dist-packages/torch/utils/data/_utils/fetch.py in fetch(self, possibly_batched_index) 47 if self.auto_collation: 48 if hasattr(self.dataset, "getitems") and self.dataset.getitems: ---> 49 data = self.dataset.getitems(possibly_batched_index) 50 else: 51 data = [self.dataset[idx] for idx in possibly_batched_index]

TypeError: 'generator' object is not callable