def __getitem__()

in florence2-VQA/src_train/train_mlflow.py [0:0]

• 8 lines of code
• 2 McCabe index (conditional complexity)

    def __getitem__(self, idx):
        example = self.data[idx]
        question = "<DocVQA>" + example['question']
        first_answer = example['answers'][0]
        image = example['image']
        if image.mode != "RGB":
            image = image.convert("RGB")
        return question, first_answer, image