src/pixparse/task/task_cruller_eval_cord.py [181:228]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        self.vocab_size = len(self.tokenizer.trunk)

        # We resize token embeddings after initializing
        if newly_added_num > 0:
            self.model.text_decoder.trunk.resize_token_embeddings(
                len(self.tokenizer.trunk)
            )

# ------ 
        self.loss = nn.CrossEntropyLoss(ignore_index=-100)
        self.has_no_sync = False
        self.num_image_chs = 1 if cfg.model.image_encoder.image_fmt == "L" else 3

        # TODO refactor, used in many tasks

        img_mean = self.model.image_encoder.trunk.pretrained_cfg["mean"]
        img_std = self.model.image_encoder.trunk.pretrained_cfg["std"]

        self.img_mean = (
            sum(img_mean) / len(img_mean)
            if cfg.model.image_encoder.image_fmt == "L"
            else img_mean
        )
        self.img_std = (
            sum(img_std) / len(img_std)
            if cfg.model.image_encoder.image_fmt == "L"
            else img_std
        )

        # preprocessors cross both the task/model & dataset domain,
        # created within task here and passed to data loaders
        self.image_preprocess_eval = transforms.Compose(
            [
                transforms.ToTensor(),
                transforms.Grayscale(),
                transforms.Resize(
                    cfg.model.image_encoder.image_size,
                    interpolation=transforms.InterpolationMode.BICUBIC,
                    antialias=True,
                ),
                # transforms.CenterCrop(448),  # FIXME need better aspect preserving resize & pad
                transforms.Normalize(
                    mean=self.img_mean,
                    std=self.img_std,
                ),
            ]
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/pixparse/task/task_cruller_eval_docvqa.py [127:174]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        )
        self.vocab_size = len(self.tokenizer.trunk)

        # We resize token embeddings after initializing
        if newly_added_num > 0:
            self.model.text_decoder.trunk.resize_token_embeddings(
                len(self.tokenizer.trunk)
            )

# ------ 
        self.loss = nn.CrossEntropyLoss(ignore_index=-100)
        self.has_no_sync = False
        self.num_image_chs = 1 if cfg.model.image_encoder.image_fmt == "L" else 3

        # TODO refactor, used in many tasks

        img_mean = self.model.image_encoder.trunk.pretrained_cfg["mean"]
        img_std = self.model.image_encoder.trunk.pretrained_cfg["std"]

        self.img_mean = (
            sum(img_mean) / len(img_mean)
            if cfg.model.image_encoder.image_fmt == "L"
            else img_mean
        )
        self.img_std = (
            sum(img_std) / len(img_std)
            if cfg.model.image_encoder.image_fmt == "L"
            else img_std
        )

        # preprocessors cross both the task/model & dataset domain,
        # created within task here and passed to data loaders
        self.image_preprocess_eval = transforms.Compose(
            [
                transforms.ToTensor(),
                transforms.Grayscale(),
                transforms.Resize(
                    cfg.model.image_encoder.image_size,
                    interpolation=transforms.InterpolationMode.BICUBIC,
                    antialias=True,
                ),
                # transforms.CenterCrop(448),  # FIXME need better aspect preserving resize & pad
                transforms.Normalize(
                    mean=self.img_mean,
                    std=self.img_std,
                ),
            ]
        )
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -