def prepare_images()

in lerobot/common/policies/smolvla/modeling_smolvla.py [0:0]

• 30 lines of code
• 12 McCabe index (conditional complexity)

    def prepare_images(self, batch):
        """Apply SmolVLA preprocessing to the images, like resizing to 224x224 and padding to keep aspect ratio, and
        convert pixel range from [0.0, 1.0] to [-1.0, 1.0] as requested by SigLIP.
        """
        images = []
        img_masks = []
        present_img_keys = [key for key in self.config.image_features if key in batch]
        missing_img_keys = [key for key in self.config.image_features if key not in batch]

        if len(present_img_keys) == 0:
            raise ValueError(
                f"All image features are missing from the batch. At least one expected. (batch: {batch.keys()}) (image_features:{self.config.image_features})"
            )
        # Preprocess image features present in the batch
        for key in present_img_keys:
            img = batch[key][:, -1, :, :, :] if batch[key].ndim == 5 else batch[key]
            if self.config.resize_imgs_with_padding is not None:
                img = resize_with_pad(img, *self.config.resize_imgs_with_padding, pad_value=0)

            # Normalize from range [0,1] to [-1,1] as expacted by siglip
            img = img * 2.0 - 1.0

            bsize = img.shape[0]
            device = img.device
            if f"{key}_padding_mask" in batch:
                mask = batch[f"{key}_padding_mask"].bool()
            else:
                mask = torch.ones(bsize, dtype=torch.bool, device=device)
            images.append(img)
            img_masks.append(mask)

        # Create image features not present in the batch
        # as fully 0 padded images.
        for num_empty_cameras in range(len(missing_img_keys)):
            if num_empty_cameras >= self.config.empty_cameras:
                break
            img = torch.ones_like(img) * -1
            mask = torch.zeros_like(mask)
            images.append(img)
            img_masks.append(mask)
        return images, img_masks