mmdet/datasets/transforms/hsi/hsi_load.py

from mmcv.transforms import to_tensor
from mmengine.structures import InstanceData, PixelData
from mmdet.structures import DetDataSample
from mmdet.structures.bbox import BaseBoxes
import mmengine.fileio as fileio
from typing import Optional, Tuple, Union
import mmcv
import numpy as np
import pycocotools.mask as maskUtils
import torch
from mmcv.transforms import BaseTransform
from mmcv.transforms import LoadAnnotations as MMCV_LoadAnnotations
from mmdet.registry import TRANSFORMS
from mmdet.structures.bbox import get_box_type
from mmdet.structures.mask import BitmapMasks, PolygonMasks
import scipy.io as sio

def hsifromfile(img_path, backend='npy' ) -> np.ndarray:
    """Read an image from bytes.

    Args:
        backend (str | None): The image decoding backend type.
    Returns:
        ndarray: Loaded image array.

    Examples:
    """
    if backend =='npy':
        img = np.load(img_path)
        return img

@TRANSFORMS.register_module()
class LoadHyperspectralImageFromFiles(BaseTransform):
    """Load multi-channel images from a list of separate channel files.

    Required Keys:

    - img_path

    Modified Keys:

    - img
    - img_shape
    - ori_shape

    Args:
        to_float32 (bool): Whether to convert the loaded image to a float32
            numpy array. If set to False, the loaded image is an uint8 array.
            Defaults to False.
    """

    def __init__(
        self,
        to_float32: bool = False,
        normalized_basis = None,
    ) -> None:
        self.to_float32 = to_float32
        self.normalized_basis = normalized_basis

    def transform(self, results: dict) -> dict:
        """Transform functions to load multiple images and get images meta
        information.

        Args:
            results (dict): Result dict from :obj:`mmdet.CustomDataset`.

        Returns:
            dict: The dict contains loaded images and meta information.
        """

        img = hsifromfile(results['img_path'])
        # up_limit = 3500
        # low_limit = 600
        # new_img = (img - low_limit) / up_limit
        # new_img[new_img > 1] = 1
        # new_img[new_img < 0] = 0
        # img = new_img * 255
        if self.normalized_basis == None:
            img = img/500
        else:
            img = img/np.array(self.normalized_basis)
        if self.to_float32:
            img = img.astype(np.float32)

        results['img'] = img
        results['img_shape'] = img.shape[:2]
        results['ori_shape'] = img.shape[:2]
        return results

    def __repr__(self):
        repr_str = (f'{self.__class__.__name__}('
                    f'to_float32={self.to_float32}, ')
        return repr_str


@TRANSFORMS.register_module()
class LoadAnnotationsPiexlTarget(MMCV_LoadAnnotations):
    """Load and process the ``instances`` and ``seg_map`` annotation provided
    by dataset.

    The annotation format is as the following:

    .. code-block:: python

        {
            'instances':
            [
                {
                # List of 4 numbers representing the bounding box of the
                # instance, in (x1, y1, x2, y2) order.
                'bbox': [x1, y1, x2, y2],

                # Label of image classification.
                'bbox_label': 1,

                # Used in instance/panoptic segmentation. The segmentation mask
                # of the instance or the information of segments.
                # 1. If list[list[float]], it represents a list of polygons,
                # one for each connected component of the object. Each
                # list[float] is one simple polygon in the format of
                # [x1, y1, ..., xn, yn] (n≥3). The Xs and Ys are absolute
                # coordinates in unit of pixels.
                # 2. If dict, it represents the per-pixel segmentation mask in
                # COCO’s compressed RLE format. The dict should have keys
                # “size” and “counts”.  Can be loaded by pycocotools
                'mask': list[list[float]] or dict,

                }
            ]
            # Filename of semantic or panoptic segmentation ground truth file.
            'seg_map_path': 'a/b/c'
        }

    After this module, the annotation has been changed to the format below:

    .. code-block:: python

        {
            # In (x1, y1, x2, y2) order, float type. N is the number of bboxes
            # in an image
            'gt_bboxes': BaseBoxes(N, 4)
             # In int type.
            'gt_bboxes_labels': np.ndarray(N, )
             # In built-in class
            'gt_masks': PolygonMasks (H, W) or BitmapMasks (H, W)
             # In uint8 type.
            'gt_seg_map': np.ndarray (H, W)
             # in (x, y, v) order, float type.
        }

    Required Keys:

    - height
    - width
    - instances

      - bbox (optional)
      - bbox_label
      - mask (optional)
      - ignore_flag

    - seg_map_path (optional)

    Added Keys:

    - gt_bboxes (BaseBoxes[torch.float32])
    - gt_bboxes_labels (np.int64)
    - gt_masks (BitmapMasks | PolygonMasks)
    - gt_seg_map (np.uint8)
    - gt_ignore_flags (bool)

    Args:
        with_bbox (bool): Whether to parse and load the bbox annotation.
            Defaults to True.
        with_label (bool): Whether to parse and load the label annotation.
            Defaults to True.
        with_mask (bool): Whether to parse and load the mask annotation.
             Default: False.
        with_seg (bool): Whether to parse and load the semantic segmentation
            annotation. Defaults to False.
        poly2mask (bool): Whether to convert mask to bitmap. Default: True.
        box_type (str): The box type used to wrap the bboxes. If ``box_type``
            is None, gt_bboxes will keep being np.ndarray. Defaults to 'hbox'.
        imdecode_backend (str): The image decoding backend type. The backend
            argument for :func:``mmcv.imfrombytes``.
            See :fun:``mmcv.imfrombytes`` for details.
            Defaults to 'cv2'.
        backend_args (dict, optional): Arguments to instantiate the
            corresponding backend. Defaults to None.
    """

    def __init__(self,
                 with_mask: bool = False,
                 with_seg: bool = False,
                 with_abu: bool = False,
                 poly2mask: bool = True,
                 box_type: str = 'hbox',
                 **kwargs) -> None:
        super(LoadAnnotationsPiexlTarget, self).__init__(**kwargs)
        self.with_mask = with_mask
        self.poly2mask = poly2mask
        self.box_type = box_type
        self.with_seg = with_seg
        self.with_abu = with_abu

    def _load_bboxes(self, results: dict) -> None:
        """Private function to load bounding box annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.
        Returns:
            dict: The dict contains loaded bounding box annotations.
        """
        gt_bboxes = []
        gt_ignore_flags = []
        for instance in results.get('instances', []):
            gt_bboxes.append(instance['bbox'])
            gt_ignore_flags.append(instance['ignore_flag'])
        if self.box_type is None:
            results['gt_bboxes'] = np.array(
                gt_bboxes, dtype=np.float32).reshape((-1, 4))
        else:
            _, box_type_cls = get_box_type(self.box_type)
            results['gt_bboxes'] = box_type_cls(gt_bboxes, dtype=torch.float32)
        results['gt_ignore_flags'] = np.array(gt_ignore_flags, dtype=bool)

    def _load_labels(self, results: dict) -> None:
        """Private function to load label annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.

        Returns:
            dict: The dict contains loaded label annotations.
        """
        gt_bboxes_labels = []
        for instance in results.get('instances', []):
            gt_bboxes_labels.append(instance['bbox_label'])
        # TODO: Inconsistent with mmcv, consider how to deal with it later.
        results['gt_bboxes_labels'] = np.array(
            gt_bboxes_labels, dtype=np.int64)

    def _poly2mask(self, mask_ann: Union[list, dict], img_h: int,
                   img_w: int) -> np.ndarray:
        """Private function to convert masks represented with polygon to
        bitmaps.

        Args:
            mask_ann (list | dict): Polygon mask annotation input.
            img_h (int): The height of output mask.
            img_w (int): The width of output mask.

        Returns:
            np.ndarray: The decode bitmap mask of shape (img_h, img_w).
        """

        if isinstance(mask_ann, list):
            # polygon -- a single object might consist of multiple parts
            # we merge all parts into one mask rle code
            rles = maskUtils.frPyObjects(mask_ann, img_h, img_w)
            rle = maskUtils.merge(rles)
        elif isinstance(mask_ann['counts'], list):
            # uncompressed RLE
            rle = maskUtils.frPyObjects(mask_ann, img_h, img_w)
        else:
            # rle
            rle = mask_ann
        mask = maskUtils.decode(rle)
        return mask

    def _process_masks(self, results: dict) -> list:
        """Process gt_masks and filter invalid polygons.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.

        Returns:
            list: Processed gt_masks.
        """
        gt_masks = []
        gt_ignore_flags = []
        for instance in results.get('instances', []):
            gt_mask = instance['mask']
            # If the annotation of segmentation mask is invalid,
            # ignore the whole instance.
            if isinstance(gt_mask, list):
                gt_mask = [
                    np.array(polygon) for polygon in gt_mask
                    if len(polygon) % 2 == 0 and len(polygon) >= 6
                ]
                if len(gt_mask) == 0:
                    # ignore this instance and set gt_mask to a fake mask
                    instance['ignore_flag'] = 1
                    gt_mask = [np.zeros(6)]
            elif not self.poly2mask:
                # `PolygonMasks` requires a ploygon of format List[np.array],
                # other formats are invalid.
                instance['ignore_flag'] = 1
                gt_mask = [np.zeros(6)]
            elif isinstance(gt_mask, dict) and \
                    not (gt_mask.get('counts') is not None and
                         gt_mask.get('size') is not None and
                         isinstance(gt_mask['counts'], (list, str))):
                # if gt_mask is a dict, it should include `counts` and `size`,
                # so that `BitmapMasks` can uncompressed RLE
                instance['ignore_flag'] = 1
                gt_mask = [np.zeros(6)]
            gt_masks.append(gt_mask)
            # re-process gt_ignore_flags
            gt_ignore_flags.append(instance['ignore_flag'])
        results['gt_ignore_flags'] = np.array(gt_ignore_flags, dtype=bool)
        return gt_masks

    def _load_masks(self, results: dict) -> None:
        """Private function to load mask annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.
        """
        h, w = results['ori_shape']
        gt_masks = self._process_masks(results)
        if self.poly2mask:
            gt_masks = BitmapMasks(
                [self._poly2mask(mask, h, w) for mask in gt_masks], h, w)
        else:
            # fake polygon masks will be ignored in `PackDetInputs`
            gt_masks = PolygonMasks([mask for mask in gt_masks], h, w)
        results['gt_masks'] = gt_masks

    def _load_seg_map(self, results: dict) -> None:
        """Private function to load semantic segmentation annotations.

        Args:
            results (dict): Result dict from
                :class:`mmengine.dataset.BaseDataset`.

        Returns:
            dict: The dict contains loaded semantic segmentation annotations.
        """
        assert results['seg_path'] is not None
        img_bytes = fileio.get(results['seg_path'])
        img = mmcv.imfrombytes(
            img_bytes, flag='grayscale', backend='pillow')
        results['gt_seg'] = img.astype('float32')

    def _load_abu_map(self, results: dict) -> None:
        """Private function to load semantic segmentation annotations.

        Args:
            results (dict): Result dict from
                :class:`mmengine.dataset.BaseDataset`.

        Returns:
            dict: The dict contains loaded semantic segmentation annotations.
        """
        assert results['abu_path'] is not None
        img = sio.loadmat(results['abu_path'])['data']
        results['gt_abu'] = img.astype('float32')
        # img_bytes = fileio.get(results['seg_path'])
        # img = mmcv.imfrombytes(
        #     img_bytes, flag='grayscale', backend='pillow')
        # results['gt_seg'] = img



    def transform(self, results: dict) -> dict:
        """Function to load multiple types annotations.

        Args:
            results (dict): Result dict from :obj:``mmengine.BaseDataset``.

        Returns:
            dict: The dict contains loaded bounding box, label and
            semantic segmentation.
        """

        if self.with_bbox:
            self._load_bboxes(results)
        if self.with_label:
            self._load_labels(results)
        if self.with_mask:
            self._load_masks(results)
        if self.with_seg:
            self._load_seg_map(results)
        if self.with_abu:
            self._load_abu_map(results)

        return results

    def __repr__(self) -> str:
        repr_str = self.__class__.__name__
        repr_str += f'(with_bbox={self.with_bbox}, '
        repr_str += f'with_label={self.with_label}, '
        repr_str += f'with_mask={self.with_mask}, '
        repr_str += f'with_seg={self.with_seg}, '
        repr_str += f'with_abu={self.with_abu}, '
        repr_str += f'poly2mask={self.poly2mask}, '
        repr_str += f"imdecode_backend='{self.imdecode_backend}', "
        repr_str += f'backend_args={self.backend_args})'
        return repr_str





@TRANSFORMS.register_module()
class LoadHyperspectralMaskImageFromFiles(BaseTransform):
    """Load multi-channel images from a list of separate channel files.

    Required Keys:

    - img_path

    Modified Keys:

    - img
    - img_shape
    - ori_shape

    Args:
        to_float32 (bool): Whether to convert the loaded image to a float32
            numpy array. If set to False, the loaded image is an uint8 array.
            Defaults to False.
    """

    def __init__(
        self,
        to_float32: bool = False,
        normalized_basis = None,
        color_type: str = 'color',
        imdecode_backend: str = 'cv2',
        backend_args: Optional[dict] = None
    ) -> None:
        self.to_float32 = to_float32
        self.normalized_basis = normalized_basis
        self.color_type = color_type
        self.imdecode_backend = imdecode_backend
        self.backend_args: Optional[dict] = None
        if backend_args is not None:
            self.backend_args = backend_args.copy()

    def transform(self, results: dict) -> dict:
        """Transform functions to load multiple images and get images meta
        information.

        Args:
            results (dict): Result dict from :obj:`mmdet.CustomDataset`.

        Returns:
            dict: The dict contains loaded images and meta information.
        """

        img = hsifromfile(results['img_path']+'_rd.npy')
        # up_limit = 3500
        # low_limit = 600
        # new_img = (img - low_limit) / up_limit
        # new_img[new_img > 1] = 1
        # new_img[new_img < 0] = 0
        # img = new_img * 255
        if self.normalized_basis == None:
            img = img/1000
        else:
            img = img/np.array(self.normalized_basis)
        if self.to_float32:
            img = img.astype(np.float32)

        maskname = results['mask_path']+'_mask.png'
        mask_bytes = fileio.get(
            maskname, backend_args=self.backend_args)
        mask = mmcv.imfrombytes(
            mask_bytes, flag=self.color_type, backend=self.imdecode_backend)
        if self.to_float32:
            mask = mask.astype(np.float32)

        mask[mask == 255] = 1
        mask = np.repeat(mask, 17, axis = 2)
        img = img * mask

        results['img'] = img
        results['img_shape'] = img.shape[:2]
        results['ori_shape'] = img.shape[:2]
        return results

    def __repr__(self):
        repr_str = (f'{self.__class__.__name__}('
                    f'to_float32={self.to_float32}, ')
        return repr_str


def to_tensor_HSI(
    data: Union[torch.Tensor, np.ndarray]) -> torch.Tensor:
    """Convert objects of various python types to :obj:`torch.Tensor`.

    Supported types are: :class:`numpy.ndarray`, :class:`torch.Tensor`,
    :class:`Sequence`, :class:`int` and :class:`float`.

    Args:
        data (torch.Tensor | numpy.ndarray | Sequence | int | float): Data to
            be converted.

    Returns:
        torch.Tensor: the converted data.
    """

    if isinstance(data, torch.Tensor):
        return data
    elif isinstance(data, np.ndarray):
        # rw by lzx
        if data.dtype == '>i2':
            return torch.from_numpy(data.astype(np.float32))
        else:
            return torch.from_numpy(data)
    else:
        raise TypeError(f'type {type(data)} cannot be converted to tensor.')

@TRANSFORMS.register_module()
class PackDetInputs_HSI(BaseTransform):
    """Pack the inputs data for the detection / semantic segmentation /
    panoptic segmentation.

    The ``img_meta`` item is always populated.  The contents of the
    ``img_meta`` dictionary depends on ``meta_keys``. By default this includes:

        - ``img_id``: id of the image

        - ``img_path``: path to the image file

        - ``ori_shape``: original shape of the image as a tuple (h, w)

        - ``img_shape``: shape of the image input to the network as a tuple \
            (h, w).  Note that images may be zero padded on the \
            bottom/right if the batch tensor is larger than this shape.

        - ``scale_factor``: a float indicating the preprocessing scale

        - ``flip``: a boolean indicating if image flip transform was used

        - ``flip_direction``: the flipping direction

    Args:
        meta_keys (Sequence[str], optional): Meta keys to be converted to
            ``mmcv.DataContainer`` and collected in ``data[img_metas]``.
            Default: ``('img_id', 'img_path', 'ori_shape', 'img_shape',
            'scale_factor', 'flip', 'flip_direction')``
    """
    mapping_table = {
        'gt_bboxes': 'bboxes',
        'gt_bboxes_labels': 'labels',
        'gt_masks': 'masks'
    }

    def __init__(self,
                 meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
                            'scale_factor', 'flip', 'flip_direction')):
        self.meta_keys = meta_keys

    def transform(self, results: dict) -> dict:
        """Method to pack the input data.

        Args:
            results (dict): Result dict from the data pipeline.

        Returns:
            dict:

            - 'inputs' (obj:`torch.Tensor`): The forward data of models.
            - 'data_sample' (obj:`DetDataSample`): The annotation info of the
                sample.
        """
        packed_results = dict()
        if 'img' in results:
            img = results['img']
            if len(img.shape) < 3:
                img = np.expand_dims(img, -1)
            # To improve the computational speed by by 3-5 times, apply:
            # If image is not contiguous, use
            # `numpy.transpose()` followed by `numpy.ascontiguousarray()`
            # If image is already contiguous, use
            # `torch.permute()` followed by `torch.contiguous()`
            # Refer to https://github.com/open-mmlab/mmdetection/pull/9533
            # for more details
            if not img.flags.c_contiguous:
                img = np.ascontiguousarray(img.transpose(2, 0, 1))
                img = to_tensor(img)
            else:
                img = to_tensor(img).permute(2, 0, 1).contiguous()

            packed_results['inputs'] = img

        if 'gt_ignore_flags' in results:
            valid_idx = np.where(results['gt_ignore_flags'] == 0)[0]
            ignore_idx = np.where(results['gt_ignore_flags'] == 1)[0]

        data_sample = DetDataSample()
        instance_data = InstanceData()
        ignore_instance_data = InstanceData()

        for key in self.mapping_table.keys():
            if key not in results:
                continue
            if key == 'gt_masks' or isinstance(results[key], BaseBoxes):
                if 'gt_ignore_flags' in results:
                    instance_data[
                        self.mapping_table[key]] = results[key][valid_idx]
                    ignore_instance_data[
                        self.mapping_table[key]] = results[key][ignore_idx]
                else:
                    instance_data[self.mapping_table[key]] = results[key]
            else:
                if 'gt_ignore_flags' in results:
                    instance_data[self.mapping_table[key]] = to_tensor(
                        results[key][valid_idx])
                    ignore_instance_data[self.mapping_table[key]] = to_tensor(
                        results[key][ignore_idx])
                else:
                    instance_data[self.mapping_table[key]] = to_tensor(
                        results[key])
        data_sample.gt_instances = instance_data
        data_sample.ignored_instances = ignore_instance_data

        if 'proposals' in results:
            proposals = InstanceData(
                bboxes=to_tensor(results['proposals']),
                scores=to_tensor(results['proposals_scores']))
            data_sample.proposals = proposals

        if 'gt_seg_map' in results:
            gt_sem_seg_data = dict(
                sem_seg=to_tensor(results['gt_seg_map'][None, ...].copy()))
            data_sample.gt_sem_seg = PixelData(**gt_sem_seg_data)

        img_meta = {}
        for key in self.meta_keys:
            assert key in results, f'`{key}` is not found in `results`, ' \
                f'the valid keys are {list(results)}.'
            img_meta[key] = results[key]

        data_sample.set_metainfo(img_meta)
        packed_results['data_samples'] = data_sample

        return packed_results

    def __repr__(self) -> str:
        repr_str = self.__class__.__name__
        repr_str += f'(meta_keys={self.meta_keys})'
        return repr_str