src/pixparse/task/task_cruller_eval_cord.py [229:295]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def setup(self):
        device = self.device_env.device
        self.model.load_state_dict(self.resume_state_dict)
        self.model.eval()
        self.model.to(device)
        self.all_ground_truths = []
        self.all_predictions = []
        self.acc_list = []

        self.evaluator = JSONParseEvaluator()


    def prepare_inputs_for_inference(
        self,
        input_ids: torch.Tensor,
        encoder_outputs: torch.Tensor,
        past_key_values=None,
        past=None,
        use_cache: bool = None,
        attention_mask: torch.Tensor = None,
    ):
        if past is not None:
            past_key_values = past
        attention_mask = input_ids.ne(self.tokenizer.trunk.pad_token_id).long()
        if past_key_values is not None:
            input_ids = input_ids[:, -1:]
        output = {
            "input_ids": input_ids,
            "attention_mask": attention_mask,
            "past_key_values": past_key_values,
            "use_cache": use_cache,
            "encoder_hidden_states": encoder_outputs,  # .last_hidden_state,
        }
        return output

    def prepare_for_evaluation(self, loaders):
        loaders = {
            loader_key: loader
            for loader_key, loader in loaders.items()
            if loader_key in ["eval", "eval_FUNSD"]
        }

        return loaders
        # return loaders_and_tasks


    def safe_image_transform(self, img):
        try:
            transformed_img = self.image_preprocess_eval(img)
        except PIL.UnidentifiedImageError as e:
            print(f'Encountered PIL issue {e}. Filtering...')
            transformed_img = None
        return transformed_img

    def text_input_to_target(self, text_input, ignore_id=-100):
        target = text_input.clone()
        # model doesn't need to predict pad token
        target[target == self.tokenizer.trunk.pad_token_id] = ignore_id
        # model doesn't need to predict prompt (for VQA)
        prompt_end_token_id = self.tokenizer.trunk.convert_tokens_to_ids(
            self.prompt_end_token
        )
        slice_id = torch.nonzero(target == prompt_end_token_id).sum() + 1
        target[:slice_id] = ignore_id
        return target

    def collate_fn(self, batch):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/pixparse/task/task_cruller_eval_docvqa.py [178:244]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
    def setup(self):
        device = self.device_env.device
        self.model.load_state_dict(self.resume_state_dict)
        self.model.eval()
        self.model.to(device)
        self.all_ground_truths = []
        self.all_predictions = []
        self.acc_list = []

        self.evaluator = JSONParseEvaluator()


    def prepare_inputs_for_inference(
        self,
        input_ids: torch.Tensor,
        encoder_outputs: torch.Tensor,
        past_key_values=None,
        past=None,
        use_cache: bool = None,
        attention_mask: torch.Tensor = None,
    ):
        if past is not None:
            past_key_values = past
        attention_mask = input_ids.ne(self.tokenizer.trunk.pad_token_id).long()
        if past_key_values is not None:
            input_ids = input_ids[:, -1:]
        output = {
            "input_ids": input_ids,
            "attention_mask": attention_mask,
            "past_key_values": past_key_values,
            "use_cache": use_cache,
            "encoder_hidden_states": encoder_outputs,  # .last_hidden_state,
        }
        return output

    def prepare_for_evaluation(self, loaders):
        loaders = {
            loader_key: loader
            for loader_key, loader in loaders.items()
            if loader_key in ["eval", "eval_FUNSD"]
        }

        return loaders
        # return loaders_and_tasks


    def safe_image_transform(self, img):
        try:
            transformed_img = self.image_preprocess_eval(img)
        except PIL.UnidentifiedImageError as e:
            print(f'Encountered PIL issue {e}. Filtering...')
            transformed_img = None
        return transformed_img

    def text_input_to_target(self, text_input, ignore_id=-100):
        target = text_input.clone()
        # model doesn't need to predict pad token
        target[target == self.tokenizer.trunk.pad_token_id] = ignore_id
        # model doesn't need to predict prompt (for VQA)
        prompt_end_token_id = self.tokenizer.trunk.convert_tokens_to_ids(
            self.prompt_end_token
        )
        slice_id = torch.nonzero(target == prompt_end_token_id).sum() + 1
        target[:slice_id] = ignore_id
        return target

    def collate_fn(self, batch):
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -