def __getitem__(self, idx):
sample_info = self.annotation_db[idx]
sample_info = self.preprocess_sample_info(sample_info)
current_sample = Sample()
processed_text = self.text_processor({"text": sample_info["text"]})
current_sample.text = processed_text["text"]
if "input_ids" in processed_text:
current_sample.update(processed_text)
current_sample.id = torch.tensor(int(sample_info["id"]),
dtype=torch.int)
# Instead of using idx directly here, use sample_info to fetch
# the features as feature_path has been dynamically added
features = self.features_db.get(sample_info)
if hasattr(self, "transformer_bbox_processor"):
features["image_info_0"] = self.transformer_bbox_processor(
features["image_info_0"])
current_sample.update(features)
if "label" in sample_info:
current_sample.targets = torch.tensor(sample_info["label"],
dtype=torch.long)
return current_sample
def __getitem__(self, idx: int) -> Type[Sample]:
sample_info = self.annotation_db[idx]
current_sample = Sample()
processed_question = self.text_processor(
{"text": sample_info["question"]})
current_sample.update(processed_question)
current_sample.id = torch.tensor(int(sample_info["question_id"]),
dtype=torch.int)
image_path = self.get_image_path(sample_info["image_id"],
sample_info["coco_split"])
current_sample.image = self.image_db.from_path(image_path)["images"][0]
if "answers" in sample_info:
answers = self.answer_processor(
{"answers": sample_info["answers"]})
current_sample.targets = answers["answers_scores"]
return current_sample
def __getitem__(self, idx):
sample_info = self.annotation_db[idx]
current_sample = Sample()
processed_text = self.text_processor({"text": sample_info["text"]})
current_sample.text = processed_text["text"]
if "input_ids" in processed_text:
current_sample.update(processed_text)
current_sample.id = torch.tensor(int(sample_info["id"]),
dtype=torch.int)
# Get the first image from the set of images returned from the image_db
current_sample.image = self.image_db[idx]["images"][0]
if "label" in sample_info:
current_sample.targets = torch.tensor(sample_info["label"],
dtype=torch.long)
return current_sample