Merge branch 'hepj_work' into 'main'

增加conformer代码

See merge request dcutoolkit/deeplearing/dlexamples_new!7

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/fp16/deprecated_fp16_utils.py

+import warnings
+
+from mmcv.runner import (Fp16OptimizerHook, auto_fp16, force_fp32,
+                         wrap_fp16_model)
+
+
+class DeprecatedFp16OptimizerHook(Fp16OptimizerHook):
+    """A wrapper class for the FP16 optimizer hook. This class wraps
+    :class:`Fp16OptimizerHook` in `mmcv.runner` and shows a warning that the
+    :class:`Fp16OptimizerHook` from `mmdet.core` will be deprecated.
+
+    Refer to :class:`Fp16OptimizerHook` in `mmcv.runner` for more details.
+
+    Args:
+        loss_scale (float): Scale factor multiplied with loss.
+    """
+
+    def __init__(*args, **kwargs):
+        super().__init__(*args, **kwargs)
+        warnings.warn(
+            'Importing Fp16OptimizerHook from "mmdet.core" will be '
+            'deprecated in the future. Please import them from "mmcv.runner" '
+            'instead')
+
+
+def deprecated_auto_fp16(*args, **kwargs):
+    warnings.warn(
+        'Importing auto_fp16 from "mmdet.core" will be '
+        'deprecated in the future. Please import them from "mmcv.runner" '
+        'instead')
+    return auto_fp16(*args, **kwargs)
+
+
+def deprecated_force_fp32(*args, **kwargs):
+    warnings.warn(
+        'Importing force_fp32 from "mmdet.core" will be '
+        'deprecated in the future. Please import them from "mmcv.runner" '
+        'instead')
+    return force_fp32(*args, **kwargs)
+
+
+def deprecated_wrap_fp16_model(*args, **kwargs):
+    warnings.warn(
+        'Importing wrap_fp16_model from "mmdet.core" will be '
+        'deprecated in the future. Please import them from "mmcv.runner" '
+        'instead')
+    wrap_fp16_model(*args, **kwargs)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/mask/__init__.py

+from .mask_target import mask_target
+from .structures import BaseInstanceMasks, BitmapMasks, PolygonMasks
+from .utils import encode_mask_results, split_combined_polys
+
+__all__ = [
+    'split_combined_polys', 'mask_target', 'BaseInstanceMasks', 'BitmapMasks',
+    'PolygonMasks', 'encode_mask_results'
+]

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/mask/mask_target.py

+import numpy as np
+import torch
+from torch.nn.modules.utils import _pair
+
+
+def mask_target(pos_proposals_list, pos_assigned_gt_inds_list, gt_masks_list,
+                cfg):
+    """Compute mask target for positive proposals in multiple images.
+
+    Args:
+        pos_proposals_list (list[Tensor]): Positive proposals in multiple
+            images.
+        pos_assigned_gt_inds_list (list[Tensor]): Assigned GT indices for each
+            positive proposals.
+        gt_masks_list (list[:obj:`BaseInstanceMasks`]): Ground truth masks of
+            each image.
+        cfg (dict): Config dict that specifies the mask size.
+
+    Returns:
+        list[Tensor]: Mask target of each image.
+    """
+    cfg_list = [cfg for _ in range(len(pos_proposals_list))]
+    mask_targets = map(mask_target_single, pos_proposals_list,
+                       pos_assigned_gt_inds_list, gt_masks_list, cfg_list)
+    mask_targets = list(mask_targets)
+    if len(mask_targets) > 0:
+        mask_targets = torch.cat(mask_targets)
+    return mask_targets
+
+
+def mask_target_single(pos_proposals, pos_assigned_gt_inds, gt_masks, cfg):
+    """Compute mask target for each positive proposal in the image.
+
+    Args:
+        pos_proposals (Tensor): Positive proposals.
+        pos_assigned_gt_inds (Tensor): Assigned GT inds of positive proposals.
+        gt_masks (:obj:`BaseInstanceMasks`): GT masks in the format of Bitmap
+            or Polygon.
+        cfg (dict): Config dict that indicate the mask size.
+
+    Returns:
+        Tensor: Mask target of each positive proposals in the image.
+    """
+    device = pos_proposals.device
+    mask_size = _pair(cfg.mask_size)
+    num_pos = pos_proposals.size(0)
+    if num_pos > 0:
+        proposals_np = pos_proposals.cpu().numpy()
+        maxh, maxw = gt_masks.height, gt_masks.width
+        proposals_np[:, [0, 2]] = np.clip(proposals_np[:, [0, 2]], 0, maxw)
+        proposals_np[:, [1, 3]] = np.clip(proposals_np[:, [1, 3]], 0, maxh)
+        pos_assigned_gt_inds = pos_assigned_gt_inds.cpu().numpy()
+
+        mask_targets = gt_masks.crop_and_resize(
+            proposals_np, mask_size, device=device,
+            inds=pos_assigned_gt_inds).to_ndarray()
+
+        mask_targets = torch.from_numpy(mask_targets).float().to(device)
+    else:
+        mask_targets = pos_proposals.new_zeros((0, ) + mask_size)
+
+    return mask_targets

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/mask/structures.py

+from abc import ABCMeta, abstractmethod
+
+import cv2
+import mmcv
+import numpy as np
+import pycocotools.mask as maskUtils
+import torch
+from mmcv.ops.roi_align import roi_align
+
+
+class BaseInstanceMasks(metaclass=ABCMeta):
+    """Base class for instance masks."""
+
+    @abstractmethod
+    def rescale(self, scale, interpolation='nearest'):
+        """Rescale masks as large as possible while keeping the aspect ratio.
+        For details can refer to `mmcv.imrescale`.
+
+        Args:
+            scale (tuple[int]): The maximum size (h, w) of rescaled mask.
+            interpolation (str): Same as :func:`mmcv.imrescale`.
+
+        Returns:
+            BaseInstanceMasks: The rescaled masks.
+        """
+        pass
+
+    @abstractmethod
+    def resize(self, out_shape, interpolation='nearest'):
+        """Resize masks to the given out_shape.
+
+        Args:
+            out_shape: Target (h, w) of resized mask.
+            interpolation (str): See :func:`mmcv.imresize`.
+
+        Returns:
+            BaseInstanceMasks: The resized masks.
+        """
+        pass
+
+    @abstractmethod
+    def flip(self, flip_direction='horizontal'):
+        """Flip masks alone the given direction.
+
+        Args:
+            flip_direction (str): Either 'horizontal' or 'vertical'.
+
+        Returns:
+            BaseInstanceMasks: The flipped masks.
+        """
+        pass
+
+    @abstractmethod
+    def pad(self, out_shape, pad_val):
+        """Pad masks to the given size of (h, w).
+
+        Args:
+            out_shape (tuple[int]): Target (h, w) of padded mask.
+            pad_val (int): The padded value.
+
+        Returns:
+            BaseInstanceMasks: The padded masks.
+        """
+        pass
+
+    @abstractmethod
+    def crop(self, bbox):
+        """Crop each mask by the given bbox.
+
+        Args:
+            bbox (ndarray): Bbox in format [x1, y1, x2, y2], shape (4, ).
+
+        Return:
+            BaseInstanceMasks: The cropped masks.
+        """
+        pass
+
+    @abstractmethod
+    def crop_and_resize(self,
+                        bboxes,
+                        out_shape,
+                        inds,
+                        device,
+                        interpolation='bilinear'):
+        """Crop and resize masks by the given bboxes.
+
+        This function is mainly used in mask targets computation.
+        It firstly align mask to bboxes by assigned_inds, then crop mask by the
+        assigned bbox and resize to the size of (mask_h, mask_w)
+
+        Args:
+            bboxes (Tensor): Bboxes in format [x1, y1, x2, y2], shape (N, 4)
+            out_shape (tuple[int]): Target (h, w) of resized mask
+            inds (ndarray): Indexes to assign masks to each bbox
+            device (str): Device of bboxes
+            interpolation (str): See `mmcv.imresize`
+
+        Return:
+            BaseInstanceMasks: the cropped and resized masks.
+        """
+        pass
+
+    @abstractmethod
+    def expand(self, expanded_h, expanded_w, top, left):
+        """see :class:`Expand`."""
+        pass
+
+    @property
+    @abstractmethod
+    def areas(self):
+        """ndarray: areas of each instance."""
+        pass
+
+    @abstractmethod
+    def to_ndarray(self):
+        """Convert masks to the format of ndarray.
+
+        Return:
+            ndarray: Converted masks in the format of ndarray.
+        """
+        pass
+
+    @abstractmethod
+    def to_tensor(self, dtype, device):
+        """Convert masks to the format of Tensor.
+
+        Args:
+            dtype (str): Dtype of converted mask.
+            device (torch.device): Device of converted masks.
+
+        Returns:
+            Tensor: Converted masks in the format of Tensor.
+        """
+        pass
+
+    @abstractmethod
+    def translate(self,
+                  out_shape,
+                  offset,
+                  direction='horizontal',
+                  fill_val=0,
+                  interpolation='bilinear'):
+        """Translate the masks.
+
+        Args:
+            out_shape (tuple[int]): Shape for output mask, format (h, w).
+            offset (int | float): The offset for translate.
+            direction (str): The translate direction, either "horizontal"
+                or "vertical".
+            fill_val (int | float): Border value. Default 0.
+            interpolation (str): Same as :func:`mmcv.imtranslate`.
+
+        Returns:
+            Translated masks.
+        """
+        pass
+
+    def shear(self,
+              out_shape,
+              magnitude,
+              direction='horizontal',
+              border_value=0,
+              interpolation='bilinear'):
+        """Shear the masks.
+
+        Args:
+            out_shape (tuple[int]): Shape for output mask, format (h, w).
+            magnitude (int | float): The magnitude used for shear.
+            direction (str): The shear direction, either "horizontal"
+                or "vertical".
+            border_value (int | tuple[int]): Value used in case of a
+                constant border. Default 0.
+            interpolation (str): Same as in :func:`mmcv.imshear`.
+
+        Returns:
+            ndarray: Sheared masks.
+        """
+        pass
+
+    @abstractmethod
+    def rotate(self, out_shape, angle, center=None, scale=1.0, fill_val=0):
+        """Rotate the masks.
+
+        Args:
+            out_shape (tuple[int]): Shape for output mask, format (h, w).
+            angle (int | float): Rotation angle in degrees. Positive values
+                mean counter-clockwise rotation.
+            center (tuple[float], optional): Center point (w, h) of the
+                rotation in source image. If not specified, the center of
+                the image will be used.
+            scale (int | float): Isotropic scale factor.
+            fill_val (int | float): Border value. Default 0 for masks.
+
+        Returns:
+            Rotated masks.
+        """
+        pass
+
+
+class BitmapMasks(BaseInstanceMasks):
+    """This class represents masks in the form of bitmaps.
+
+    Args:
+        masks (ndarray): ndarray of masks in shape (N, H, W), where N is
+            the number of objects.
+        height (int): height of masks
+        width (int): width of masks
+    """
+
+    def __init__(self, masks, height, width):
+        self.height = height
+        self.width = width
+        if len(masks) == 0:
+            self.masks = np.empty((0, self.height, self.width), dtype=np.uint8)
+        else:
+            assert isinstance(masks, (list, np.ndarray))
+            if isinstance(masks, list):
+                assert isinstance(masks[0], np.ndarray)
+                assert masks[0].ndim == 2  # (H, W)
+            else:
+                assert masks.ndim == 3  # (N, H, W)
+
+            self.masks = np.stack(masks).reshape(-1, height, width)
+            assert self.masks.shape[1] == self.height
+            assert self.masks.shape[2] == self.width
+
+    def __getitem__(self, index):
+        """Index the BitmapMask.
+
+        Args:
+            index (int | ndarray): Indices in the format of integer or ndarray.
+
+        Returns:
+            :obj:`BitmapMasks`: Indexed bitmap masks.
+        """
+        masks = self.masks[index].reshape(-1, self.height, self.width)
+        return BitmapMasks(masks, self.height, self.width)
+
+    def __iter__(self):
+        return iter(self.masks)
+
+    def __repr__(self):
+        s = self.__class__.__name__ + '('
+        s += f'num_masks={len(self.masks)}, '
+        s += f'height={self.height}, '
+        s += f'width={self.width})'
+        return s
+
+    def __len__(self):
+        """Number of masks."""
+        return len(self.masks)
+
+    def rescale(self, scale, interpolation='nearest'):
+        """See :func:`BaseInstanceMasks.rescale`."""
+        if len(self.masks) == 0:
+            new_w, new_h = mmcv.rescale_size((self.width, self.height), scale)
+            rescaled_masks = np.empty((0, new_h, new_w), dtype=np.uint8)
+        else:
+            rescaled_masks = np.stack([
+                mmcv.imrescale(mask, scale, interpolation=interpolation)
+                for mask in self.masks
+            ])
+        height, width = rescaled_masks.shape[1:]
+        return BitmapMasks(rescaled_masks, height, width)
+
+    def resize(self, out_shape, interpolation='nearest'):
+        """See :func:`BaseInstanceMasks.resize`."""
+        if len(self.masks) == 0:
+            resized_masks = np.empty((0, *out_shape), dtype=np.uint8)
+        else:
+            resized_masks = np.stack([
+                mmcv.imresize(
+                    mask, out_shape[::-1], interpolation=interpolation)
+                for mask in self.masks
+            ])
+        return BitmapMasks(resized_masks, *out_shape)
+
+    def flip(self, flip_direction='horizontal'):
+        """See :func:`BaseInstanceMasks.flip`."""
+        assert flip_direction in ('horizontal', 'vertical', 'diagonal')
+
+        if len(self.masks) == 0:
+            flipped_masks = self.masks
+        else:
+            flipped_masks = np.stack([
+                mmcv.imflip(mask, direction=flip_direction)
+                for mask in self.masks
+            ])
+        return BitmapMasks(flipped_masks, self.height, self.width)
+
+    def pad(self, out_shape, pad_val=0):
+        """See :func:`BaseInstanceMasks.pad`."""
+        if len(self.masks) == 0:
+            padded_masks = np.empty((0, *out_shape), dtype=np.uint8)
+        else:
+            padded_masks = np.stack([
+                mmcv.impad(mask, shape=out_shape, pad_val=pad_val)
+                for mask in self.masks
+            ])
+        return BitmapMasks(padded_masks, *out_shape)
+
+    def crop(self, bbox):
+        """See :func:`BaseInstanceMasks.crop`."""
+        assert isinstance(bbox, np.ndarray)
+        assert bbox.ndim == 1
+
+        # clip the boundary
+        bbox = bbox.copy()
+        bbox[0::2] = np.clip(bbox[0::2], 0, self.width)
+        bbox[1::2] = np.clip(bbox[1::2], 0, self.height)
+        x1, y1, x2, y2 = bbox
+        w = np.maximum(x2 - x1, 1)
+        h = np.maximum(y2 - y1, 1)
+
+        if len(self.masks) == 0:
+            cropped_masks = np.empty((0, h, w), dtype=np.uint8)
+        else:
+            cropped_masks = self.masks[:, y1:y1 + h, x1:x1 + w]
+        return BitmapMasks(cropped_masks, h, w)
+
+    def crop_and_resize(self,
+                        bboxes,
+                        out_shape,
+                        inds,
+                        device='cpu',
+                        interpolation='bilinear'):
+        """See :func:`BaseInstanceMasks.crop_and_resize`."""
+        if len(self.masks) == 0:
+            empty_masks = np.empty((0, *out_shape), dtype=np.uint8)
+            return BitmapMasks(empty_masks, *out_shape)
+
+        # convert bboxes to tensor
+        if isinstance(bboxes, np.ndarray):
+            bboxes = torch.from_numpy(bboxes).to(device=device)
+        if isinstance(inds, np.ndarray):
+            inds = torch.from_numpy(inds).to(device=device)
+
+        num_bbox = bboxes.shape[0]
+        fake_inds = torch.arange(
+            num_bbox, device=device).to(dtype=bboxes.dtype)[:, None]
+        rois = torch.cat([fake_inds, bboxes], dim=1)  # Nx5
+        rois = rois.to(device=device)
+        if num_bbox > 0:
+            gt_masks_th = torch.from_numpy(self.masks).to(device).index_select(
+                0, inds).to(dtype=rois.dtype)
+            targets = roi_align(gt_masks_th[:, None, :, :], rois, out_shape,
+                                1.0, 0, 'avg', True).squeeze(1)
+            resized_masks = (targets >= 0.5).cpu().numpy()
+        else:
+            resized_masks = []
+        return BitmapMasks(resized_masks, *out_shape)
+
+    def expand(self, expanded_h, expanded_w, top, left):
+        """See :func:`BaseInstanceMasks.expand`."""
+        if len(self.masks) == 0:
+            expanded_mask = np.empty((0, expanded_h, expanded_w),
+                                     dtype=np.uint8)
+        else:
+            expanded_mask = np.zeros((len(self), expanded_h, expanded_w),
+                                     dtype=np.uint8)
+            expanded_mask[:, top:top + self.height,
+                          left:left + self.width] = self.masks
+        return BitmapMasks(expanded_mask, expanded_h, expanded_w)
+
+    def translate(self,
+                  out_shape,
+                  offset,
+                  direction='horizontal',
+                  fill_val=0,
+                  interpolation='bilinear'):
+        """Translate the BitmapMasks.
+
+        Args:
+            out_shape (tuple[int]): Shape for output mask, format (h, w).
+            offset (int | float): The offset for translate.
+            direction (str): The translate direction, either "horizontal"
+                or "vertical".
+            fill_val (int | float): Border value. Default 0 for masks.
+            interpolation (str): Same as :func:`mmcv.imtranslate`.
+
+        Returns:
+            BitmapMasks: Translated BitmapMasks.
+        """
+        if len(self.masks) == 0:
+            translated_masks = np.empty((0, *out_shape), dtype=np.uint8)
+        else:
+            translated_masks = mmcv.imtranslate(
+                self.masks.transpose((1, 2, 0)),
+                offset,
+                direction,
+                border_value=fill_val,
+                interpolation=interpolation)
+            if translated_masks.ndim == 2:
+                translated_masks = translated_masks[:, :, None]
+            translated_masks = translated_masks.transpose(
+                (2, 0, 1)).astype(self.masks.dtype)
+        return BitmapMasks(translated_masks, *out_shape)
+
+    def shear(self,
+              out_shape,
+              magnitude,
+              direction='horizontal',
+              border_value=0,
+              interpolation='bilinear'):
+        """Shear the BitmapMasks.
+
+        Args:
+            out_shape (tuple[int]): Shape for output mask, format (h, w).
+            magnitude (int | float): The magnitude used for shear.
+            direction (str): The shear direction, either "horizontal"
+                or "vertical".
+            border_value (int | tuple[int]): Value used in case of a
+                constant border.
+            interpolation (str): Same as in :func:`mmcv.imshear`.
+
+        Returns:
+            BitmapMasks: The sheared masks.
+        """
+        if len(self.masks) == 0:
+            sheared_masks = np.empty((0, *out_shape), dtype=np.uint8)
+        else:
+            sheared_masks = mmcv.imshear(
+                self.masks.transpose((1, 2, 0)),
+                magnitude,
+                direction,
+                border_value=border_value,
+                interpolation=interpolation)
+            if sheared_masks.ndim == 2:
+                sheared_masks = sheared_masks[:, :, None]
+            sheared_masks = sheared_masks.transpose(
+                (2, 0, 1)).astype(self.masks.dtype)
+        return BitmapMasks(sheared_masks, *out_shape)
+
+    def rotate(self, out_shape, angle, center=None, scale=1.0, fill_val=0):
+        """Rotate the BitmapMasks.
+
+        Args:
+            out_shape (tuple[int]): Shape for output mask, format (h, w).
+            angle (int | float): Rotation angle in degrees. Positive values
+                mean counter-clockwise rotation.
+            center (tuple[float], optional): Center point (w, h) of the
+                rotation in source image. If not specified, the center of
+                the image will be used.
+            scale (int | float): Isotropic scale factor.
+            fill_val (int | float): Border value. Default 0 for masks.
+
+        Returns:
+            BitmapMasks: Rotated BitmapMasks.
+        """
+        if len(self.masks) == 0:
+            rotated_masks = np.empty((0, *out_shape), dtype=self.masks.dtype)
+        else:
+            rotated_masks = mmcv.imrotate(
+                self.masks.transpose((1, 2, 0)),
+                angle,
+                center=center,
+                scale=scale,
+                border_value=fill_val)
+            if rotated_masks.ndim == 2:
+                # case when only one mask, (h, w)
+                rotated_masks = rotated_masks[:, :, None]  # (h, w, 1)
+            rotated_masks = rotated_masks.transpose(
+                (2, 0, 1)).astype(self.masks.dtype)
+        return BitmapMasks(rotated_masks, *out_shape)
+
+    @property
+    def areas(self):
+        """See :py:attr:`BaseInstanceMasks.areas`."""
+        return self.masks.sum((1, 2))
+
+    def to_ndarray(self):
+        """See :func:`BaseInstanceMasks.to_ndarray`."""
+        return self.masks
+
+    def to_tensor(self, dtype, device):
+        """See :func:`BaseInstanceMasks.to_tensor`."""
+        return torch.tensor(self.masks, dtype=dtype, device=device)
+
+
+class PolygonMasks(BaseInstanceMasks):
+    """This class represents masks in the form of polygons.
+
+    Polygons is a list of three levels. The first level of the list
+    corresponds to objects, the second level to the polys that compose the
+    object, the third level to the poly coordinates
+
+    Args:
+        masks (list[list[ndarray]]): The first level of the list
+            corresponds to objects, the second level to the polys that
+            compose the object, the third level to the poly coordinates
+        height (int): height of masks
+        width (int): width of masks
+    """
+
+    def __init__(self, masks, height, width):
+        assert isinstance(masks, list)
+        if len(masks) > 0:
+            assert isinstance(masks[0], list)
+            assert isinstance(masks[0][0], np.ndarray)
+
+        self.height = height
+        self.width = width
+        self.masks = masks
+
+    def __getitem__(self, index):
+        """Index the polygon masks.
+
+        Args:
+            index (ndarray | List): The indices.
+
+        Returns:
+            :obj:`PolygonMasks`: The indexed polygon masks.
+        """
+        if isinstance(index, np.ndarray):
+            index = index.tolist()
+        if isinstance(index, list):
+            masks = [self.masks[i] for i in index]
+        else:
+            try:
+                masks = self.masks[index]
+            except Exception:
+                raise ValueError(
+                    f'Unsupported input of type {type(index)} for indexing!')
+        if len(masks) and isinstance(masks[0], np.ndarray):
+            masks = [masks]  # ensure a list of three levels
+        return PolygonMasks(masks, self.height, self.width)
+
+    def __iter__(self):
+        return iter(self.masks)
+
+    def __repr__(self):
+        s = self.__class__.__name__ + '('
+        s += f'num_masks={len(self.masks)}, '
+        s += f'height={self.height}, '
+        s += f'width={self.width})'
+        return s
+
+    def __len__(self):
+        """Number of masks."""
+        return len(self.masks)
+
+    def rescale(self, scale, interpolation=None):
+        """see :func:`BaseInstanceMasks.rescale`"""
+        new_w, new_h = mmcv.rescale_size((self.width, self.height), scale)
+        if len(self.masks) == 0:
+            rescaled_masks = PolygonMasks([], new_h, new_w)
+        else:
+            rescaled_masks = self.resize((new_h, new_w))
+        return rescaled_masks
+
+    def resize(self, out_shape, interpolation=None):
+        """see :func:`BaseInstanceMasks.resize`"""
+        if len(self.masks) == 0:
+            resized_masks = PolygonMasks([], *out_shape)
+        else:
+            h_scale = out_shape[0] / self.height
+            w_scale = out_shape[1] / self.width
+            resized_masks = []
+            for poly_per_obj in self.masks:
+                resized_poly = []
+                for p in poly_per_obj:
+                    p = p.copy()
+                    p[0::2] *= w_scale
+                    p[1::2] *= h_scale
+                    resized_poly.append(p)
+                resized_masks.append(resized_poly)
+            resized_masks = PolygonMasks(resized_masks, *out_shape)
+        return resized_masks
+
+    def flip(self, flip_direction='horizontal'):
+        """see :func:`BaseInstanceMasks.flip`"""
+        assert flip_direction in ('horizontal', 'vertical', 'diagonal')
+        if len(self.masks) == 0:
+            flipped_masks = PolygonMasks([], self.height, self.width)
+        else:
+            flipped_masks = []
+            for poly_per_obj in self.masks:
+                flipped_poly_per_obj = []
+                for p in poly_per_obj:
+                    p = p.copy()
+                    if flip_direction == 'horizontal':
+                        p[0::2] = self.width - p[0::2]
+                    elif flip_direction == 'vertical':
+                        p[1::2] = self.height - p[1::2]
+                    else:
+                        p[0::2] = self.width - p[0::2]
+                        p[1::2] = self.height - p[1::2]
+                    flipped_poly_per_obj.append(p)
+                flipped_masks.append(flipped_poly_per_obj)
+            flipped_masks = PolygonMasks(flipped_masks, self.height,
+                                         self.width)
+        return flipped_masks
+
+    def crop(self, bbox):
+        """see :func:`BaseInstanceMasks.crop`"""
+        assert isinstance(bbox, np.ndarray)
+        assert bbox.ndim == 1
+
+        # clip the boundary
+        bbox = bbox.copy()
+        bbox[0::2] = np.clip(bbox[0::2], 0, self.width)
+        bbox[1::2] = np.clip(bbox[1::2], 0, self.height)
+        x1, y1, x2, y2 = bbox
+        w = np.maximum(x2 - x1, 1)
+        h = np.maximum(y2 - y1, 1)
+
+        if len(self.masks) == 0:
+            cropped_masks = PolygonMasks([], h, w)
+        else:
+            cropped_masks = []
+            for poly_per_obj in self.masks:
+                cropped_poly_per_obj = []
+                for p in poly_per_obj:
+                    # pycocotools will clip the boundary
+                    p = p.copy()
+                    p[0::2] -= bbox[0]
+                    p[1::2] -= bbox[1]
+                    cropped_poly_per_obj.append(p)
+                cropped_masks.append(cropped_poly_per_obj)
+            cropped_masks = PolygonMasks(cropped_masks, h, w)
+        return cropped_masks
+
+    def pad(self, out_shape, pad_val=0):
+        """padding has no effect on polygons`"""
+        return PolygonMasks(self.masks, *out_shape)
+
+    def expand(self, *args, **kwargs):
+        """TODO: Add expand for polygon"""
+        raise NotImplementedError
+
+    def crop_and_resize(self,
+                        bboxes,
+                        out_shape,
+                        inds,
+                        device='cpu',
+                        interpolation='bilinear'):
+        """see :func:`BaseInstanceMasks.crop_and_resize`"""
+        out_h, out_w = out_shape
+        if len(self.masks) == 0:
+            return PolygonMasks([], out_h, out_w)
+
+        resized_masks = []
+        for i in range(len(bboxes)):
+            mask = self.masks[inds[i]]
+            bbox = bboxes[i, :]
+            x1, y1, x2, y2 = bbox
+            w = np.maximum(x2 - x1, 1)
+            h = np.maximum(y2 - y1, 1)
+            h_scale = out_h / max(h, 0.1)  # avoid too large scale
+            w_scale = out_w / max(w, 0.1)
+
+            resized_mask = []
+            for p in mask:
+                p = p.copy()
+                # crop
+                # pycocotools will clip the boundary
+                p[0::2] -= bbox[0]
+                p[1::2] -= bbox[1]
+
+                # resize
+                p[0::2] *= w_scale
+                p[1::2] *= h_scale
+                resized_mask.append(p)
+            resized_masks.append(resized_mask)
+        return PolygonMasks(resized_masks, *out_shape)
+
+    def translate(self,
+                  out_shape,
+                  offset,
+                  direction='horizontal',
+                  fill_val=None,
+                  interpolation=None):
+        """Translate the PolygonMasks."""
+        assert fill_val is None or fill_val == 0, 'Here fill_val is not '\
+            f'used, and defaultly should be None or 0. got {fill_val}.'
+        if len(self.masks) == 0:
+            translated_masks = PolygonMasks([], *out_shape)
+        else:
+            translated_masks = []
+            for poly_per_obj in self.masks:
+                translated_poly_per_obj = []
+                for p in poly_per_obj:
+                    p = p.copy()
+                    if direction == 'horizontal':
+                        p[0::2] = np.clip(p[0::2] + offset, 0, out_shape[1])
+                    elif direction == 'vertical':
+                        p[1::2] = np.clip(p[1::2] + offset, 0, out_shape[0])
+                    translated_poly_per_obj.append(p)
+                translated_masks.append(translated_poly_per_obj)
+            translated_masks = PolygonMasks(translated_masks, *out_shape)
+        return translated_masks
+
+    def shear(self,
+              out_shape,
+              magnitude,
+              direction='horizontal',
+              border_value=0,
+              interpolation='bilinear'):
+        """See :func:`BaseInstanceMasks.shear`."""
+        if len(self.masks) == 0:
+            sheared_masks = PolygonMasks([], *out_shape)
+        else:
+            sheared_masks = []
+            if direction == 'horizontal':
+                shear_matrix = np.stack([[1, magnitude],
+                                         [0, 1]]).astype(np.float32)
+            elif direction == 'vertical':
+                shear_matrix = np.stack([[1, 0], [magnitude,
+                                                  1]]).astype(np.float32)
+            for poly_per_obj in self.masks:
+                sheared_poly = []
+                for p in poly_per_obj:
+                    p = np.stack([p[0::2], p[1::2]], axis=0)  # [2, n]
+                    new_coords = np.matmul(shear_matrix, p)  # [2, n]
+                    new_coords[0, :] = np.clip(new_coords[0, :], 0,
+                                               out_shape[1])
+                    new_coords[1, :] = np.clip(new_coords[1, :], 0,
+                                               out_shape[0])
+                    sheared_poly.append(
+                        new_coords.transpose((1, 0)).reshape(-1))
+                sheared_masks.append(sheared_poly)
+            sheared_masks = PolygonMasks(sheared_masks, *out_shape)
+        return sheared_masks
+
+    def rotate(self, out_shape, angle, center=None, scale=1.0, fill_val=0):
+        """See :func:`BaseInstanceMasks.rotate`."""
+        if len(self.masks) == 0:
+            rotated_masks = PolygonMasks([], *out_shape)
+        else:
+            rotated_masks = []
+            rotate_matrix = cv2.getRotationMatrix2D(center, -angle, scale)
+            for poly_per_obj in self.masks:
+                rotated_poly = []
+                for p in poly_per_obj:
+                    p = p.copy()
+                    coords = np.stack([p[0::2], p[1::2]], axis=1)  # [n, 2]
+                    # pad 1 to convert from format [x, y] to homogeneous
+                    # coordinates format [x, y, 1]
+                    coords = np.concatenate(
+                        (coords, np.ones((coords.shape[0], 1), coords.dtype)),
+                        axis=1)  # [n, 3]
+                    rotated_coords = np.matmul(
+                        rotate_matrix[None, :, :],
+                        coords[:, :, None])[..., 0]  # [n, 2, 1] -> [n, 2]
+                    rotated_coords[:, 0] = np.clip(rotated_coords[:, 0], 0,
+                                                   out_shape[1])
+                    rotated_coords[:, 1] = np.clip(rotated_coords[:, 1], 0,
+                                                   out_shape[0])
+                    rotated_poly.append(rotated_coords.reshape(-1))
+                rotated_masks.append(rotated_poly)
+            rotated_masks = PolygonMasks(rotated_masks, *out_shape)
+        return rotated_masks
+
+    def to_bitmap(self):
+        """convert polygon masks to bitmap masks."""
+        bitmap_masks = self.to_ndarray()
+        return BitmapMasks(bitmap_masks, self.height, self.width)
+
+    @property
+    def areas(self):
+        """Compute areas of masks.
+
+        This func is modified from `detectron2
+        <https://github.com/facebookresearch/detectron2/blob/ffff8acc35ea88ad1cb1806ab0f00b4c1c5dbfd9/detectron2/structures/masks.py#L387>`_.
+        The function only works with Polygons using the shoelace formula.
+
+        Return:
+            ndarray: areas of each instance
+        """  # noqa: W501
+        area = []
+        for polygons_per_obj in self.masks:
+            area_per_obj = 0
+            for p in polygons_per_obj:
+                area_per_obj += self._polygon_area(p[0::2], p[1::2])
+            area.append(area_per_obj)
+        return np.asarray(area)
+
+    def _polygon_area(self, x, y):
+        """Compute the area of a component of a polygon.
+
+        Using the shoelace formula:
+        https://stackoverflow.com/questions/24467972/calculate-area-of-polygon-given-x-y-coordinates
+
+        Args:
+            x (ndarray): x coordinates of the component
+            y (ndarray): y coordinates of the component
+
+        Return:
+            float: the are of the component
+        """  # noqa: 501
+        return 0.5 * np.abs(
+            np.dot(x, np.roll(y, 1)) - np.dot(y, np.roll(x, 1)))
+
+    def to_ndarray(self):
+        """Convert masks to the format of ndarray."""
+        if len(self.masks) == 0:
+            return np.empty((0, self.height, self.width), dtype=np.uint8)
+        bitmap_masks = []
+        for poly_per_obj in self.masks:
+            bitmap_masks.append(
+                polygon_to_bitmap(poly_per_obj, self.height, self.width))
+        return np.stack(bitmap_masks)
+
+    def to_tensor(self, dtype, device):
+        """See :func:`BaseInstanceMasks.to_tensor`."""
+        if len(self.masks) == 0:
+            return torch.empty((0, self.height, self.width),
+                               dtype=dtype,
+                               device=device)
+        ndarray_masks = self.to_ndarray()
+        return torch.tensor(ndarray_masks, dtype=dtype, device=device)
+
+
+def polygon_to_bitmap(polygons, height, width):
+    """Convert masks from the form of polygons to bitmaps.
+
+    Args:
+        polygons (list[ndarray]): masks in polygon representation
+        height (int): mask height
+        width (int): mask width
+
+    Return:
+        ndarray: the converted masks in bitmap representation
+    """
+    rles = maskUtils.frPyObjects(polygons, height, width)
+    rle = maskUtils.merge(rles)
+    bitmap_mask = maskUtils.decode(rle).astype(np.bool)
+    return bitmap_mask

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/mask/utils.py

+import mmcv
+import numpy as np
+import pycocotools.mask as mask_util
+
+
+def split_combined_polys(polys, poly_lens, polys_per_mask):
+    """Split the combined 1-D polys into masks.
+
+    A mask is represented as a list of polys, and a poly is represented as
+    a 1-D array. In dataset, all masks are concatenated into a single 1-D
+    tensor. Here we need to split the tensor into original representations.
+
+    Args:
+        polys (list): a list (length = image num) of 1-D tensors
+        poly_lens (list): a list (length = image num) of poly length
+        polys_per_mask (list): a list (length = image num) of poly number
+            of each mask
+
+    Returns:
+        list: a list (length = image num) of list (length = mask num) of \
+            list (length = poly num) of numpy array.
+    """
+    mask_polys_list = []
+    for img_id in range(len(polys)):
+        polys_single = polys[img_id]
+        polys_lens_single = poly_lens[img_id].tolist()
+        polys_per_mask_single = polys_per_mask[img_id].tolist()
+
+        split_polys = mmcv.slice_list(polys_single, polys_lens_single)
+        mask_polys = mmcv.slice_list(split_polys, polys_per_mask_single)
+        mask_polys_list.append(mask_polys)
+    return mask_polys_list
+
+
+# TODO: move this function to more proper place
+def encode_mask_results(mask_results):
+    """Encode bitmap mask to RLE code.
+
+    Args:
+        mask_results (list | tuple[list]): bitmap mask results.
+            In mask scoring rcnn, mask_results is a tuple of (segm_results,
+            segm_cls_score).
+
+    Returns:
+        list | tuple: RLE encoded mask.
+    """
+    if isinstance(mask_results, tuple):  # mask scoring
+        cls_segms, cls_mask_scores = mask_results
+    else:
+        cls_segms = mask_results
+    num_classes = len(cls_segms)
+    encoded_mask_results = [[] for _ in range(num_classes)]
+    for i in range(len(cls_segms)):
+        for cls_segm in cls_segms[i]:
+            encoded_mask_results[i].append(
+                mask_util.encode(
+                    np.array(
+                        cls_segm[:, :, np.newaxis], order='F',
+                        dtype='uint8'))[0])  # encoded with RLE
+    if isinstance(mask_results, tuple):
+        return encoded_mask_results, cls_mask_scores
+    else:
+        return encoded_mask_results

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/post_processing/__init__.py

+from .bbox_nms import fast_nms, multiclass_nms
+from .merge_augs import (merge_aug_bboxes, merge_aug_masks,
+                         merge_aug_proposals, merge_aug_scores)
+
+__all__ = [
+    'multiclass_nms', 'merge_aug_proposals', 'merge_aug_bboxes',
+    'merge_aug_scores', 'merge_aug_masks', 'fast_nms'
+]

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/post_processing/bbox_nms.py

+import torch
+from mmcv.ops.nms import batched_nms
+
+from mmdet.core.bbox.iou_calculators import bbox_overlaps
+
+
+def multiclass_nms(multi_bboxes,
+                   multi_scores,
+                   score_thr,
+                   nms_cfg,
+                   max_num=-1,
+                   score_factors=None,
+                   return_inds=False):
+    """NMS for multi-class bboxes.
+
+    Args:
+        multi_bboxes (Tensor): shape (n, #class*4) or (n, 4)
+        multi_scores (Tensor): shape (n, #class), where the last column
+            contains scores of the background class, but this will be ignored.
+        score_thr (float): bbox threshold, bboxes with scores lower than it
+            will not be considered.
+        nms_thr (float): NMS IoU threshold
+        max_num (int, optional): if there are more than max_num bboxes after
+            NMS, only top max_num will be kept. Default to -1.
+        score_factors (Tensor, optional): The factors multiplied to scores
+            before applying NMS. Default to None.
+        return_inds (bool, optional): Whether return the indices of kept
+            bboxes. Default to False.
+
+    Returns:
+        tuple: (bboxes, labels, indices (optional)), tensors of shape (k, 5),
+            (k), and (k). Labels are 0-based.
+    """
+    num_classes = multi_scores.size(1) - 1
+    # exclude background category
+    if multi_bboxes.shape[1] > 4:
+        bboxes = multi_bboxes.view(multi_scores.size(0), -1, 4)
+    else:
+        bboxes = multi_bboxes[:, None].expand(
+            multi_scores.size(0), num_classes, 4)
+
+    scores = multi_scores[:, :-1]
+
+    labels = torch.arange(num_classes, dtype=torch.long)
+    labels = labels.view(1, -1).expand_as(scores)
+
+    bboxes = bboxes.reshape(-1, 4)
+    scores = scores.reshape(-1)
+    labels = labels.reshape(-1)
+
+    # remove low scoring boxes
+    valid_mask = scores > score_thr
+    # multiply score_factor after threshold to preserve more bboxes, improve
+    # mAP by 1% for YOLOv3
+    if score_factors is not None:
+        # expand the shape to match original shape of score
+        score_factors = score_factors.view(-1, 1).expand(
+            multi_scores.size(0), num_classes)
+        score_factors = score_factors.reshape(-1)
+        scores = scores * score_factors
+    inds = valid_mask.nonzero(as_tuple=False).squeeze(1)
+    bboxes, scores, labels = bboxes[inds], scores[inds], labels[inds]
+    if inds.numel() == 0:
+        if torch.onnx.is_in_onnx_export():
+            raise RuntimeError('[ONNX Error] Can not record NMS '
+                               'as it has not been executed this time')
+        if return_inds:
+            return bboxes, labels, inds
+        else:
+            return bboxes, labels
+
+    # TODO: add size check before feed into batched_nms
+    dets, keep = batched_nms(bboxes, scores, labels, nms_cfg)
+
+    if max_num > 0:
+        dets = dets[:max_num]
+        keep = keep[:max_num]
+
+    if return_inds:
+        return dets, labels[keep], keep
+    else:
+        return dets, labels[keep]
+
+
+def fast_nms(multi_bboxes,
+             multi_scores,
+             multi_coeffs,
+             score_thr,
+             iou_thr,
+             top_k,
+             max_num=-1):
+    """Fast NMS in `YOLACT <https://arxiv.org/abs/1904.02689>`_.
+
+    Fast NMS allows already-removed detections to suppress other detections so
+    that every instance can be decided to be kept or discarded in parallel,
+    which is not possible in traditional NMS. This relaxation allows us to
+    implement Fast NMS entirely in standard GPU-accelerated matrix operations.
+
+    Args:
+        multi_bboxes (Tensor): shape (n, #class*4) or (n, 4)
+        multi_scores (Tensor): shape (n, #class+1), where the last column
+            contains scores of the background class, but this will be ignored.
+        multi_coeffs (Tensor): shape (n, #class*coeffs_dim).
+        score_thr (float): bbox threshold, bboxes with scores lower than it
+            will not be considered.
+        iou_thr (float): IoU threshold to be considered as conflicted.
+        top_k (int): if there are more than top_k bboxes before NMS,
+            only top top_k will be kept.
+        max_num (int): if there are more than max_num bboxes after NMS,
+            only top max_num will be kept. If -1, keep all the bboxes.
+            Default: -1.
+
+    Returns:
+        tuple: (bboxes, labels, coefficients), tensors of shape (k, 5), (k, 1),
+            and (k, coeffs_dim). Labels are 0-based.
+    """
+
+    scores = multi_scores[:, :-1].t()  # [#class, n]
+    scores, idx = scores.sort(1, descending=True)
+
+    idx = idx[:, :top_k].contiguous()
+    scores = scores[:, :top_k]  # [#class, topk]
+    num_classes, num_dets = idx.size()
+    boxes = multi_bboxes[idx.view(-1), :].view(num_classes, num_dets, 4)
+    coeffs = multi_coeffs[idx.view(-1), :].view(num_classes, num_dets, -1)
+
+    iou = bbox_overlaps(boxes, boxes)  # [#class, topk, topk]
+    iou.triu_(diagonal=1)
+    iou_max, _ = iou.max(dim=1)
+
+    # Now just filter out the ones higher than the threshold
+    keep = iou_max <= iou_thr
+
+    # Second thresholding introduces 0.2 mAP gain at negligible time cost
+    keep *= scores > score_thr
+
+    # Assign each kept detection to its corresponding class
+    classes = torch.arange(
+        num_classes, device=boxes.device)[:, None].expand_as(keep)
+    classes = classes[keep]
+
+    boxes = boxes[keep]
+    coeffs = coeffs[keep]
+    scores = scores[keep]
+
+    # Only keep the top max_num highest scores across all classes
+    scores, idx = scores.sort(0, descending=True)
+    if max_num > 0:
+        idx = idx[:max_num]
+        scores = scores[:max_num]
+
+    classes = classes[idx]
+    boxes = boxes[idx]
+    coeffs = coeffs[idx]
+
+    cls_dets = torch.cat([boxes, scores[:, None]], dim=1)
+    return cls_dets, classes, coeffs

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/post_processing/merge_augs.py

+import numpy as np
+import torch
+from mmcv.ops import nms
+
+from ..bbox import bbox_mapping_back
+
+
+def merge_aug_proposals(aug_proposals, img_metas, rpn_test_cfg):
+    """Merge augmented proposals (multiscale, flip, etc.)
+
+    Args:
+        aug_proposals (list[Tensor]): proposals from different testing
+            schemes, shape (n, 5). Note that they are not rescaled to the
+            original image size.
+
+        img_metas (list[dict]): list of image info dict where each dict has:
+            'img_shape', 'scale_factor', 'flip', and may also contain
+            'filename', 'ori_shape', 'pad_shape', and 'img_norm_cfg'.
+            For details on the values of these keys see
+            `mmdet/datasets/pipelines/formatting.py:Collect`.
+
+        rpn_test_cfg (dict): rpn test config.
+
+    Returns:
+        Tensor: shape (n, 4), proposals corresponding to original image scale.
+    """
+    recovered_proposals = []
+    for proposals, img_info in zip(aug_proposals, img_metas):
+        img_shape = img_info['img_shape']
+        scale_factor = img_info['scale_factor']
+        flip = img_info['flip']
+        flip_direction = img_info['flip_direction']
+        _proposals = proposals.clone()
+        _proposals[:, :4] = bbox_mapping_back(_proposals[:, :4], img_shape,
+                                              scale_factor, flip,
+                                              flip_direction)
+        recovered_proposals.append(_proposals)
+    aug_proposals = torch.cat(recovered_proposals, dim=0)
+    merged_proposals, _ = nms(aug_proposals[:, :4].contiguous(),
+                              aug_proposals[:, -1].contiguous(),
+                              rpn_test_cfg.nms_thr)
+    scores = merged_proposals[:, 4]
+    _, order = scores.sort(0, descending=True)
+    num = min(rpn_test_cfg.max_num, merged_proposals.shape[0])
+    order = order[:num]
+    merged_proposals = merged_proposals[order, :]
+    return merged_proposals
+
+
+def merge_aug_bboxes(aug_bboxes, aug_scores, img_metas, rcnn_test_cfg):
+    """Merge augmented detection bboxes and scores.
+
+    Args:
+        aug_bboxes (list[Tensor]): shape (n, 4*#class)
+        aug_scores (list[Tensor] or None): shape (n, #class)
+        img_shapes (list[Tensor]): shape (3, ).
+        rcnn_test_cfg (dict): rcnn test config.
+
+    Returns:
+        tuple: (bboxes, scores)
+    """
+    recovered_bboxes = []
+    for bboxes, img_info in zip(aug_bboxes, img_metas):
+        img_shape = img_info[0]['img_shape']
+        scale_factor = img_info[0]['scale_factor']
+        flip = img_info[0]['flip']
+        flip_direction = img_info[0]['flip_direction']
+        bboxes = bbox_mapping_back(bboxes, img_shape, scale_factor, flip,
+                                   flip_direction)
+        recovered_bboxes.append(bboxes)
+    bboxes = torch.stack(recovered_bboxes).mean(dim=0)
+    if aug_scores is None:
+        return bboxes
+    else:
+        scores = torch.stack(aug_scores).mean(dim=0)
+        return bboxes, scores
+
+
+def merge_aug_scores(aug_scores):
+    """Merge augmented bbox scores."""
+    if isinstance(aug_scores[0], torch.Tensor):
+        return torch.mean(torch.stack(aug_scores), dim=0)
+    else:
+        return np.mean(aug_scores, axis=0)
+
+
+def merge_aug_masks(aug_masks, img_metas, rcnn_test_cfg, weights=None):
+    """Merge augmented mask prediction.
+
+    Args:
+        aug_masks (list[ndarray]): shape (n, #class, h, w)
+        img_shapes (list[ndarray]): shape (3, ).
+        rcnn_test_cfg (dict): rcnn test config.
+
+    Returns:
+        tuple: (bboxes, scores)
+    """
+    recovered_masks = []
+    for mask, img_info in zip(aug_masks, img_metas):
+        flip = img_info[0]['flip']
+        flip_direction = img_info[0]['flip_direction']
+        if flip:
+            if flip_direction == 'horizontal':
+                mask = mask[:, :, :, ::-1]
+            elif flip_direction == 'vertical':
+                mask = mask[:, :, ::-1, :]
+            else:
+                raise ValueError(
+                    f"Invalid flipping direction '{flip_direction}'")
+        recovered_masks.append(mask)
+
+    if weights is None:
+        merged_masks = np.mean(recovered_masks, axis=0)
+    else:
+        merged_masks = np.average(
+            np.array(recovered_masks), axis=0, weights=np.array(weights))
+    return merged_masks

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/utils/__init__.py

+from .dist_utils import DistOptimizerHook, allreduce_grads, reduce_mean
+from .misc import mask2ndarray, multi_apply, unmap
+
+__all__ = [
+    'allreduce_grads', 'DistOptimizerHook', 'reduce_mean', 'multi_apply',
+    'unmap', 'mask2ndarray'
+]

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/utils/dist_utils.py

+import warnings
+from collections import OrderedDict
+
+import torch.distributed as dist
+from mmcv.runner import OptimizerHook
+from torch._utils import (_flatten_dense_tensors, _take_tensors,
+                          _unflatten_dense_tensors)
+
+
+def _allreduce_coalesced(tensors, world_size, bucket_size_mb=-1):
+    if bucket_size_mb > 0:
+        bucket_size_bytes = bucket_size_mb * 1024 * 1024
+        buckets = _take_tensors(tensors, bucket_size_bytes)
+    else:
+        buckets = OrderedDict()
+        for tensor in tensors:
+            tp = tensor.type()
+            if tp not in buckets:
+                buckets[tp] = []
+            buckets[tp].append(tensor)
+        buckets = buckets.values()
+
+    for bucket in buckets:
+        flat_tensors = _flatten_dense_tensors(bucket)
+        dist.all_reduce(flat_tensors)
+        flat_tensors.div_(world_size)
+        for tensor, synced in zip(
+                bucket, _unflatten_dense_tensors(flat_tensors, bucket)):
+            tensor.copy_(synced)
+
+
+def allreduce_grads(params, coalesce=True, bucket_size_mb=-1):
+    """Allreduce gradients.
+
+    Args:
+        params (list[torch.Parameters]): List of parameters of a model
+        coalesce (bool, optional): Whether allreduce parameters as a whole.
+            Defaults to True.
+        bucket_size_mb (int, optional): Size of bucket, the unit is MB.
+            Defaults to -1.
+    """
+    grads = [
+        param.grad.data for param in params
+        if param.requires_grad and param.grad is not None
+    ]
+    world_size = dist.get_world_size()
+    if coalesce:
+        _allreduce_coalesced(grads, world_size, bucket_size_mb)
+    else:
+        for tensor in grads:
+            dist.all_reduce(tensor.div_(world_size))
+
+
+class DistOptimizerHook(OptimizerHook):
+    """Deprecated optimizer hook for distributed training."""
+
+    def __init__(self, *args, **kwargs):
+        warnings.warn('"DistOptimizerHook" is deprecated, please switch to'
+                      '"mmcv.runner.OptimizerHook".')
+        super().__init__(*args, **kwargs)
+
+
+def reduce_mean(tensor):
+    """"Obtain the mean of tensor on different GPUs."""
+    if not (dist.is_available() and dist.is_initialized()):
+        return tensor
+    tensor = tensor.clone()
+    dist.all_reduce(tensor.div_(dist.get_world_size()), op=dist.ReduceOp.SUM)
+    return tensor

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/utils/misc.py

+from functools import partial
+
+import numpy as np
+import torch
+from six.moves import map, zip
+
+from ..mask.structures import BitmapMasks, PolygonMasks
+
+
+def multi_apply(func, *args, **kwargs):
+    """Apply function to a list of arguments.
+
+    Note:
+        This function applies the ``func`` to multiple inputs and
+        map the multiple outputs of the ``func`` into different
+        list. Each list contains the same type of outputs corresponding
+        to different inputs.
+
+    Args:
+        func (Function): A function that will be applied to a list of
+            arguments
+
+    Returns:
+        tuple(list): A tuple containing multiple list, each list contains \
+            a kind of returned results by the function
+    """
+    pfunc = partial(func, **kwargs) if kwargs else func
+    map_results = map(pfunc, *args)
+    return tuple(map(list, zip(*map_results)))
+
+
+def unmap(data, count, inds, fill=0):
+    """Unmap a subset of item (data) back to the original set of items (of size
+    count)"""
+    if data.dim() == 1:
+        ret = data.new_full((count, ), fill)
+        ret[inds.type(torch.bool)] = data
+    else:
+        new_size = (count, ) + data.size()[1:]
+        ret = data.new_full(new_size, fill)
+        ret[inds.type(torch.bool), :] = data
+    return ret
+
+
+def mask2ndarray(mask):
+    """Convert Mask to ndarray..
+
+    Args:
+        mask (:obj:`BitmapMasks` or :obj:`PolygonMasks` or
+        torch.Tensor or np.ndarray): The mask to be converted.
+
+    Returns:
+        np.ndarray: Ndarray mask of shape (n, h, w) that has been converted
+    """
+    if isinstance(mask, (BitmapMasks, PolygonMasks)):
+        mask = mask.to_ndarray()
+    elif isinstance(mask, torch.Tensor):
+        mask = mask.detach().cpu().numpy()
+    elif not isinstance(mask, np.ndarray):
+        raise TypeError(f'Unsupported {type(mask)} data type')
+    return mask

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/visualization/__init__.py

+from .image import (color_val_matplotlib, imshow_det_bboxes,
+                    imshow_gt_det_bboxes)
+
+__all__ = ['imshow_det_bboxes', 'imshow_gt_det_bboxes', 'color_val_matplotlib']

PyTorch/NLP/Conformer-main/mmdetection/mmdet/core/visualization/image.py

+import os.path as osp
+import warnings
+
+import matplotlib.pyplot as plt
+import mmcv
+import numpy as np
+import pycocotools.mask as mask_util
+from matplotlib.collections import PatchCollection
+from matplotlib.patches import Polygon
+
+from ..utils import mask2ndarray
+
+
+def color_val_matplotlib(color):
+    """Convert various input in BGR order to normalized RGB matplotlib color
+    tuples,
+
+    Args:
+        color (:obj:`Color`/str/tuple/int/ndarray): Color inputs
+
+    Returns:
+        tuple[float]: A tuple of 3 normalized floats indicating RGB channels.
+    """
+    color = mmcv.color_val(color)
+    color = [color / 255 for color in color[::-1]]
+    return tuple(color)
+
+
+def imshow_det_bboxes(img,
+                      bboxes,
+                      labels,
+                      segms=None,
+                      class_names=None,
+                      score_thr=0,
+                      bbox_color='green',
+                      text_color='green',
+                      mask_color=None,
+                      thickness=2,
+                      font_scale=0.5,
+                      font_size=13,
+                      win_name='',
+                      fig_size=(15, 10),
+                      show=True,
+                      wait_time=0,
+                      out_file=None):
+    """Draw bboxes and class labels (with scores) on an image.
+
+    Args:
+        img (str or ndarray): The image to be displayed.
+        bboxes (ndarray): Bounding boxes (with scores), shaped (n, 4) or
+            (n, 5).
+        labels (ndarray): Labels of bboxes.
+        segms (ndarray or None): Masks, shaped (n,h,w) or None
+        class_names (list[str]): Names of each classes.
+        score_thr (float): Minimum score of bboxes to be shown.  Default: 0
+        bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
+           The tuple of color should be in BGR order. Default: 'green'
+        text_color (str or tuple(int) or :obj:`Color`):Color of texts.
+           The tuple of color should be in BGR order. Default: 'green'
+        mask_color (str or tuple(int) or :obj:`Color`, optional):
+           Color of masks. The tuple of color should be in BGR order.
+           Default: None
+        thickness (int): Thickness of lines. Default: 2
+        font_scale (float): Font scales of texts. Default: 0.5
+        font_size (int): Font size of texts. Default: 13
+        show (bool): Whether to show the image. Default: True
+        win_name (str): The window name. Default: ''
+        fig_size (tuple): Figure size of the pyplot figure. Default: (15, 10)
+        wait_time (float): Value of waitKey param. Default: 0.
+        out_file (str, optional): The filename to write the image.
+            Default: None
+
+    Returns:
+        ndarray: The image with bboxes drawn on it.
+    """
+    warnings.warn('"font_scale" will be deprecated in v2.9.0,'
+                  'Please use "font_size"')
+    assert bboxes.ndim == 2, \
+        f' bboxes ndim should be 2, but its ndim is {bboxes.ndim}.'
+    assert labels.ndim == 1, \
+        f' labels ndim should be 1, but its ndim is {labels.ndim}.'
+    assert bboxes.shape[0] == labels.shape[0], \
+        'bboxes.shape[0] and labels.shape[0] should have the same length.'
+    assert bboxes.shape[1] == 4 or bboxes.shape[1] == 5, \
+        f' bboxes.shape[1] should be 4 or 5, but its {bboxes.shape[1]}.'
+    img = mmcv.imread(img).copy()
+
+    if score_thr > 0:
+        assert bboxes.shape[1] == 5
+        scores = bboxes[:, -1]
+        inds = scores > score_thr
+        bboxes = bboxes[inds, :]
+        labels = labels[inds]
+        if segms is not None:
+            segms = segms[inds, ...]
+
+    mask_colors = []
+    if labels.shape[0] > 0:
+        if mask_color is None:
+            # random color
+            np.random.seed(42)
+            mask_colors = [
+                np.random.randint(0, 256, (1, 3), dtype=np.uint8)
+                for _ in range(max(labels) + 1)
+            ]
+        else:
+            # specify  color
+            mask_colors = [
+                np.array(mmcv.color_val(mask_color)[::-1], dtype=np.uint8)
+            ] * (
+                max(labels) + 1)
+
+    bbox_color = color_val_matplotlib(bbox_color)
+    text_color = color_val_matplotlib(text_color)
+
+    img = mmcv.bgr2rgb(img)
+    img = np.ascontiguousarray(img)
+
+    plt.figure(win_name, figsize=fig_size)
+    plt.title(win_name)
+    plt.axis('off')
+    ax = plt.gca()
+
+    polygons = []
+    color = []
+    for i, (bbox, label) in enumerate(zip(bboxes, labels)):
+        bbox_int = bbox.astype(np.int32)
+        poly = [[bbox_int[0], bbox_int[1]], [bbox_int[0], bbox_int[3]],
+                [bbox_int[2], bbox_int[3]], [bbox_int[2], bbox_int[1]]]
+        np_poly = np.array(poly).reshape((4, 2))
+        polygons.append(Polygon(np_poly))
+        color.append(bbox_color)
+        label_text = class_names[
+            label] if class_names is not None else f'class {label}'
+        if len(bbox) > 4:
+            label_text += f'|{bbox[-1]:.02f}'
+        ax.text(
+            bbox_int[0],
+            bbox_int[1],
+            f'{label_text}',
+            bbox={
+                'facecolor': 'black',
+                'alpha': 0.8,
+                'pad': 0.7,
+                'edgecolor': 'none'
+            },
+            color=text_color,
+            fontsize=font_size,
+            verticalalignment='top',
+            horizontalalignment='left')
+        if segms is not None:
+            color_mask = mask_colors[labels[i]]
+            mask = segms[i].astype(bool)
+            img[mask] = img[mask] * 0.5 + color_mask * 0.5
+
+    plt.imshow(img)
+
+    p = PatchCollection(
+        polygons, facecolor='none', edgecolors=color, linewidths=thickness)
+    ax.add_collection(p)
+
+    if out_file is not None:
+        dir_name = osp.abspath(osp.dirname(out_file))
+        mmcv.mkdir_or_exist(dir_name)
+        plt.savefig(out_file)
+        if not show:
+            plt.close()
+    if show:
+        if wait_time == 0:
+            plt.show()
+        else:
+            plt.show(block=False)
+            plt.pause(wait_time)
+            plt.close()
+    return mmcv.rgb2bgr(img)
+
+
+def imshow_gt_det_bboxes(img,
+                         annotation,
+                         result,
+                         class_names=None,
+                         score_thr=0,
+                         gt_bbox_color=(255, 102, 61),
+                         gt_text_color=(255, 102, 61),
+                         gt_mask_color=(255, 102, 61),
+                         det_bbox_color=(72, 101, 241),
+                         det_text_color=(72, 101, 241),
+                         det_mask_color=(72, 101, 241),
+                         thickness=2,
+                         font_size=13,
+                         win_name='',
+                         fig_size=(15, 10),
+                         show=True,
+                         wait_time=0,
+                         out_file=None):
+    """General visualization GT and result function.
+
+    Args:
+      img (str or ndarray): The image to be displayed.)
+      annotation (dict): Ground truth annotations where contain keys of
+          'gt_bboxes' and 'gt_labels' or 'gt_masks'
+      result (tuple[list] or list): The detection result, can be either
+          (bbox, segm) or just bbox.
+      class_names (list[str]): Names of each classes.
+      score_thr (float): Minimum score of bboxes to be shown.  Default: 0
+      gt_bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
+           The tuple of color should be in BGR order. Default: (255, 102, 61)
+      gt_text_color (str or tuple(int) or :obj:`Color`):Color of texts.
+           The tuple of color should be in BGR order. Default: (255, 102, 61)
+      gt_mask_color (str or tuple(int) or :obj:`Color`, optional):
+           Color of masks. The tuple of color should be in BGR order.
+           Default: (255, 102, 61)
+      det_bbox_color (str or tuple(int) or :obj:`Color`):Color of bbox lines.
+           The tuple of color should be in BGR order. Default: (72, 101, 241)
+      det_text_color (str or tuple(int) or :obj:`Color`):Color of texts.
+           The tuple of color should be in BGR order. Default: (72, 101, 241)
+      det_mask_color (str or tuple(int) or :obj:`Color`, optional):
+           Color of masks. The tuple of color should be in BGR order.
+           Default: (72, 101, 241)
+      thickness (int): Thickness of lines. Default: 2
+      font_size (int): Font size of texts. Default: 13
+      win_name (str): The window name. Default: ''
+      fig_size (tuple): Figure size of the pyplot figure. Default: (15, 10)
+      show (bool): Whether to show the image. Default: True
+      wait_time (float): Value of waitKey param. Default: 0.
+      out_file (str, optional): The filename to write the image.
+         Default: None
+
+    Returns:
+        ndarray: The image with bboxes or masks drawn on it.
+    """
+    assert 'gt_bboxes' in annotation
+    assert 'gt_labels' in annotation
+    assert isinstance(
+        result,
+        (tuple, list)), f'Expected tuple or list, but get {type(result)}'
+
+    gt_masks = annotation.get('gt_masks', None)
+    if gt_masks is not None:
+        gt_masks = mask2ndarray(gt_masks)
+
+    img = mmcv.imread(img)
+
+    img = imshow_det_bboxes(
+        img,
+        annotation['gt_bboxes'],
+        annotation['gt_labels'],
+        gt_masks,
+        class_names=class_names,
+        bbox_color=gt_bbox_color,
+        text_color=gt_text_color,
+        mask_color=gt_mask_color,
+        thickness=thickness,
+        font_size=font_size,
+        win_name=win_name,
+        fig_size=fig_size,
+        show=False)
+
+    if isinstance(result, tuple):
+        bbox_result, segm_result = result
+        if isinstance(segm_result, tuple):
+            segm_result = segm_result[0]  # ms rcnn
+    else:
+        bbox_result, segm_result = result, None
+
+    bboxes = np.vstack(bbox_result)
+    labels = [
+        np.full(bbox.shape[0], i, dtype=np.int32)
+        for i, bbox in enumerate(bbox_result)
+    ]
+    labels = np.concatenate(labels)
+
+    segms = None
+    if segm_result is not None and len(labels) > 0:  # non empty
+        segms = mmcv.concat_list(segm_result)
+        segms = mask_util.decode(segms)
+        segms = segms.transpose(2, 0, 1)
+
+    img = imshow_det_bboxes(
+        img,
+        bboxes,
+        labels,
+        segms=segms,
+        class_names=class_names,
+        score_thr=score_thr,
+        bbox_color=det_bbox_color,
+        text_color=det_text_color,
+        mask_color=det_mask_color,
+        thickness=thickness,
+        font_size=font_size,
+        win_name=win_name,
+        fig_size=fig_size,
+        show=show,
+        wait_time=wait_time,
+        out_file=out_file)
+    return img

PyTorch/NLP/Conformer-main/mmdetection/mmdet/datasets/__init__.py

+from .builder import DATASETS, PIPELINES, build_dataloader, build_dataset
+from .cityscapes import CityscapesDataset
+from .coco import CocoDataset
+from .custom import CustomDataset
+from .dataset_wrappers import (ClassBalancedDataset, ConcatDataset,
+                               RepeatDataset)
+from .deepfashion import DeepFashionDataset
+from .lvis import LVISDataset, LVISV1Dataset, LVISV05Dataset
+from .samplers import DistributedGroupSampler, DistributedSampler, GroupSampler
+from .utils import get_loading_pipeline, replace_ImageToTensor
+from .voc import VOCDataset
+from .wider_face import WIDERFaceDataset
+from .xml_style import XMLDataset
+
+__all__ = [
+    'CustomDataset', 'XMLDataset', 'CocoDataset', 'DeepFashionDataset',
+    'VOCDataset', 'CityscapesDataset', 'LVISDataset', 'LVISV05Dataset',
+    'LVISV1Dataset', 'GroupSampler', 'DistributedGroupSampler',
+    'DistributedSampler', 'build_dataloader', 'ConcatDataset', 'RepeatDataset',
+    'ClassBalancedDataset', 'WIDERFaceDataset', 'DATASETS', 'PIPELINES',
+    'build_dataset', 'replace_ImageToTensor', 'get_loading_pipeline'
+]

PyTorch/NLP/Conformer-main/mmdetection/mmdet/datasets/builder.py

+import copy
+import platform
+import random
+from functools import partial
+
+import numpy as np
+from mmcv.parallel import collate
+from mmcv.runner import get_dist_info
+from mmcv.utils import Registry, build_from_cfg
+from torch.utils.data import DataLoader
+
+from .samplers import DistributedGroupSampler, DistributedSampler, GroupSampler
+
+if platform.system() != 'Windows':
+    # https://github.com/pytorch/pytorch/issues/973
+    import resource
+    rlimit = resource.getrlimit(resource.RLIMIT_NOFILE)
+    hard_limit = rlimit[1]
+    soft_limit = min(4096, hard_limit)
+    resource.setrlimit(resource.RLIMIT_NOFILE, (soft_limit, hard_limit))
+
+DATASETS = Registry('dataset')
+PIPELINES = Registry('pipeline')
+
+
+def _concat_dataset(cfg, default_args=None):
+    from .dataset_wrappers import ConcatDataset
+    ann_files = cfg['ann_file']
+    img_prefixes = cfg.get('img_prefix', None)
+    seg_prefixes = cfg.get('seg_prefix', None)
+    proposal_files = cfg.get('proposal_file', None)
+    separate_eval = cfg.get('separate_eval', True)
+
+    datasets = []
+    num_dset = len(ann_files)
+    for i in range(num_dset):
+        data_cfg = copy.deepcopy(cfg)
+        # pop 'separate_eval' since it is not a valid key for common datasets.
+        if 'separate_eval' in data_cfg:
+            data_cfg.pop('separate_eval')
+        data_cfg['ann_file'] = ann_files[i]
+        if isinstance(img_prefixes, (list, tuple)):
+            data_cfg['img_prefix'] = img_prefixes[i]
+        if isinstance(seg_prefixes, (list, tuple)):
+            data_cfg['seg_prefix'] = seg_prefixes[i]
+        if isinstance(proposal_files, (list, tuple)):
+            data_cfg['proposal_file'] = proposal_files[i]
+        datasets.append(build_dataset(data_cfg, default_args))
+
+    return ConcatDataset(datasets, separate_eval)
+
+
+def build_dataset(cfg, default_args=None):
+    from .dataset_wrappers import (ConcatDataset, RepeatDataset,
+                                   ClassBalancedDataset)
+    if isinstance(cfg, (list, tuple)):
+        dataset = ConcatDataset([build_dataset(c, default_args) for c in cfg])
+    elif cfg['type'] == 'ConcatDataset':
+        dataset = ConcatDataset(
+            [build_dataset(c, default_args) for c in cfg['datasets']],
+            cfg.get('separate_eval', True))
+    elif cfg['type'] == 'RepeatDataset':
+        dataset = RepeatDataset(
+            build_dataset(cfg['dataset'], default_args), cfg['times'])
+    elif cfg['type'] == 'ClassBalancedDataset':
+        dataset = ClassBalancedDataset(
+            build_dataset(cfg['dataset'], default_args), cfg['oversample_thr'])
+    elif isinstance(cfg.get('ann_file'), (list, tuple)):
+        dataset = _concat_dataset(cfg, default_args)
+    else:
+        dataset = build_from_cfg(cfg, DATASETS, default_args)
+
+    return dataset
+
+
+def build_dataloader(dataset,
+                     samples_per_gpu,
+                     workers_per_gpu,
+                     num_gpus=1,
+                     dist=True,
+                     shuffle=True,
+                     seed=None,
+                     **kwargs):
+    """Build PyTorch DataLoader.
+
+    In distributed training, each GPU/process has a dataloader.
+    In non-distributed training, there is only one dataloader for all GPUs.
+
+    Args:
+        dataset (Dataset): A PyTorch dataset.
+        samples_per_gpu (int): Number of training samples on each GPU, i.e.,
+            batch size of each GPU.
+        workers_per_gpu (int): How many subprocesses to use for data loading
+            for each GPU.
+        num_gpus (int): Number of GPUs. Only used in non-distributed training.
+        dist (bool): Distributed training/test or not. Default: True.
+        shuffle (bool): Whether to shuffle the data at every epoch.
+            Default: True.
+        kwargs: any keyword argument to be used to initialize DataLoader
+
+    Returns:
+        DataLoader: A PyTorch dataloader.
+    """
+    rank, world_size = get_dist_info()
+    if dist:
+        # DistributedGroupSampler will definitely shuffle the data to satisfy
+        # that images on each GPU are in the same group
+        if shuffle:
+            sampler = DistributedGroupSampler(dataset, samples_per_gpu,
+                                              world_size, rank)
+        else:
+            sampler = DistributedSampler(
+                dataset, world_size, rank, shuffle=False)
+        batch_size = samples_per_gpu
+        num_workers = workers_per_gpu
+    else:
+        sampler = GroupSampler(dataset, samples_per_gpu) if shuffle else None
+        batch_size = num_gpus * samples_per_gpu
+        num_workers = num_gpus * workers_per_gpu
+
+    init_fn = partial(
+        worker_init_fn, num_workers=num_workers, rank=rank,
+        seed=seed) if seed is not None else None
+
+    data_loader = DataLoader(
+        dataset,
+        batch_size=batch_size,
+        sampler=sampler,
+        num_workers=num_workers,
+        collate_fn=partial(collate, samples_per_gpu=samples_per_gpu),
+        pin_memory=False,
+        worker_init_fn=init_fn,
+        **kwargs)
+
+    return data_loader
+
+
+def worker_init_fn(worker_id, num_workers, rank, seed):
+    # The seed of each worker equals to
+    # num_worker * rank + worker_id + user_seed
+    worker_seed = num_workers * rank + worker_id + seed
+    np.random.seed(worker_seed)
+    random.seed(worker_seed)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/datasets/cityscapes.py

+# Modified from https://github.com/facebookresearch/detectron2/blob/master/detectron2/data/datasets/cityscapes.py # noqa
+# and https://github.com/mcordts/cityscapesScripts/blob/master/cityscapesscripts/evaluation/evalInstanceLevelSemanticLabeling.py # noqa
+
+import glob
+import os
+import os.path as osp
+import tempfile
+from collections import OrderedDict
+
+import mmcv
+import numpy as np
+import pycocotools.mask as maskUtils
+from mmcv.utils import print_log
+
+from .builder import DATASETS
+from .coco import CocoDataset
+
+
+@DATASETS.register_module()
+class CityscapesDataset(CocoDataset):
+
+    CLASSES = ('person', 'rider', 'car', 'truck', 'bus', 'train', 'motorcycle',
+               'bicycle')
+
+    def _filter_imgs(self, min_size=32):
+        """Filter images too small or without ground truths."""
+        valid_inds = []
+        # obtain images that contain annotation
+        ids_with_ann = set(_['image_id'] for _ in self.coco.anns.values())
+        # obtain images that contain annotations of the required categories
+        ids_in_cat = set()
+        for i, class_id in enumerate(self.cat_ids):
+            ids_in_cat |= set(self.coco.cat_img_map[class_id])
+        # merge the image id sets of the two conditions and use the merged set
+        # to filter out images if self.filter_empty_gt=True
+        ids_in_cat &= ids_with_ann
+
+        valid_img_ids = []
+        for i, img_info in enumerate(self.data_infos):
+            img_id = img_info['id']
+            ann_ids = self.coco.getAnnIds(imgIds=[img_id])
+            ann_info = self.coco.loadAnns(ann_ids)
+            all_iscrowd = all([_['iscrowd'] for _ in ann_info])
+            if self.filter_empty_gt and (self.img_ids[i] not in ids_in_cat
+                                         or all_iscrowd):
+                continue
+            if min(img_info['width'], img_info['height']) >= min_size:
+                valid_inds.append(i)
+                valid_img_ids.append(img_id)
+        self.img_ids = valid_img_ids
+        return valid_inds
+
+    def _parse_ann_info(self, img_info, ann_info):
+        """Parse bbox and mask annotation.
+
+        Args:
+            img_info (dict): Image info of an image.
+            ann_info (list[dict]): Annotation info of an image.
+
+        Returns:
+            dict: A dict containing the following keys: bboxes, \
+                bboxes_ignore, labels, masks, seg_map. \
+                "masks" are already decoded into binary masks.
+        """
+        gt_bboxes = []
+        gt_labels = []
+        gt_bboxes_ignore = []
+        gt_masks_ann = []
+
+        for i, ann in enumerate(ann_info):
+            if ann.get('ignore', False):
+                continue
+            x1, y1, w, h = ann['bbox']
+            if ann['area'] <= 0 or w < 1 or h < 1:
+                continue
+            if ann['category_id'] not in self.cat_ids:
+                continue
+            bbox = [x1, y1, x1 + w, y1 + h]
+            if ann.get('iscrowd', False):
+                gt_bboxes_ignore.append(bbox)
+            else:
+                gt_bboxes.append(bbox)
+                gt_labels.append(self.cat2label[ann['category_id']])
+                gt_masks_ann.append(ann['segmentation'])
+
+        if gt_bboxes:
+            gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
+            gt_labels = np.array(gt_labels, dtype=np.int64)
+        else:
+            gt_bboxes = np.zeros((0, 4), dtype=np.float32)
+            gt_labels = np.array([], dtype=np.int64)
+
+        if gt_bboxes_ignore:
+            gt_bboxes_ignore = np.array(gt_bboxes_ignore, dtype=np.float32)
+        else:
+            gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)
+
+        ann = dict(
+            bboxes=gt_bboxes,
+            labels=gt_labels,
+            bboxes_ignore=gt_bboxes_ignore,
+            masks=gt_masks_ann,
+            seg_map=img_info['segm_file'])
+
+        return ann
+
+    def results2txt(self, results, outfile_prefix):
+        """Dump the detection results to a txt file.
+
+        Args:
+            results (list[list | tuple]): Testing results of the
+                dataset.
+            outfile_prefix (str): The filename prefix of the json files.
+                If the prefix is "somepath/xxx",
+                the txt files will be named "somepath/xxx.txt".
+
+        Returns:
+            list[str]: Result txt files which contains corresponding \
+                instance segmentation images.
+        """
+        try:
+            import cityscapesscripts.helpers.labels as CSLabels
+        except ImportError:
+            raise ImportError('Please run "pip install citscapesscripts" to '
+                              'install cityscapesscripts first.')
+        result_files = []
+        os.makedirs(outfile_prefix, exist_ok=True)
+        prog_bar = mmcv.ProgressBar(len(self))
+        for idx in range(len(self)):
+            result = results[idx]
+            filename = self.data_infos[idx]['filename']
+            basename = osp.splitext(osp.basename(filename))[0]
+            pred_txt = osp.join(outfile_prefix, basename + '_pred.txt')
+
+            bbox_result, segm_result = result
+            bboxes = np.vstack(bbox_result)
+            # segm results
+            if isinstance(segm_result, tuple):
+                # Some detectors use different scores for bbox and mask,
+                # like Mask Scoring R-CNN. Score of segm will be used instead
+                # of bbox score.
+                segms = mmcv.concat_list(segm_result[0])
+                mask_score = segm_result[1]
+            else:
+                # use bbox score for mask score
+                segms = mmcv.concat_list(segm_result)
+                mask_score = [bbox[-1] for bbox in bboxes]
+            labels = [
+                np.full(bbox.shape[0], i, dtype=np.int32)
+                for i, bbox in enumerate(bbox_result)
+            ]
+            labels = np.concatenate(labels)
+
+            assert len(bboxes) == len(segms) == len(labels)
+            num_instances = len(bboxes)
+            prog_bar.update()
+            with open(pred_txt, 'w') as fout:
+                for i in range(num_instances):
+                    pred_class = labels[i]
+                    classes = self.CLASSES[pred_class]
+                    class_id = CSLabels.name2label[classes].id
+                    score = mask_score[i]
+                    mask = maskUtils.decode(segms[i]).astype(np.uint8)
+                    png_filename = osp.join(outfile_prefix,
+                                            basename + f'_{i}_{classes}.png')
+                    mmcv.imwrite(mask, png_filename)
+                    fout.write(f'{osp.basename(png_filename)} {class_id} '
+                               f'{score}\n')
+            result_files.append(pred_txt)
+
+        return result_files
+
+    def format_results(self, results, txtfile_prefix=None):
+        """Format the results to txt (standard format for Cityscapes
+        evaluation).
+
+        Args:
+            results (list): Testing results of the dataset.
+            txtfile_prefix (str | None): The prefix of txt files. It includes
+                the file path and the prefix of filename, e.g., "a/b/prefix".
+                If not specified, a temp file will be created. Default: None.
+
+        Returns:
+            tuple: (result_files, tmp_dir), result_files is a dict containing \
+                the json filepaths, tmp_dir is the temporal directory created \
+                for saving txt/png files when txtfile_prefix is not specified.
+        """
+        assert isinstance(results, list), 'results must be a list'
+        assert len(results) == len(self), (
+            'The length of results is not equal to the dataset len: {} != {}'.
+            format(len(results), len(self)))
+
+        assert isinstance(results, list), 'results must be a list'
+        assert len(results) == len(self), (
+            'The length of results is not equal to the dataset len: {} != {}'.
+            format(len(results), len(self)))
+
+        if txtfile_prefix is None:
+            tmp_dir = tempfile.TemporaryDirectory()
+            txtfile_prefix = osp.join(tmp_dir.name, 'results')
+        else:
+            tmp_dir = None
+        result_files = self.results2txt(results, txtfile_prefix)
+
+        return result_files, tmp_dir
+
+    def evaluate(self,
+                 results,
+                 metric='bbox',
+                 logger=None,
+                 outfile_prefix=None,
+                 classwise=False,
+                 proposal_nums=(100, 300, 1000),
+                 iou_thrs=np.arange(0.5, 0.96, 0.05)):
+        """Evaluation in Cityscapes/COCO protocol.
+
+        Args:
+            results (list[list | tuple]): Testing results of the dataset.
+            metric (str | list[str]): Metrics to be evaluated. Options are
+                'bbox', 'segm', 'proposal', 'proposal_fast'.
+            logger (logging.Logger | str | None): Logger used for printing
+                related information during evaluation. Default: None.
+            outfile_prefix (str | None): The prefix of output file. It includes
+                the file path and the prefix of filename, e.g., "a/b/prefix".
+                If results are evaluated with COCO protocol, it would be the
+                prefix of output json file. For example, the metric is 'bbox'
+                and 'segm', then json files would be "a/b/prefix.bbox.json" and
+                "a/b/prefix.segm.json".
+                If results are evaluated with cityscapes protocol, it would be
+                the prefix of output txt/png files. The output files would be
+                png images under folder "a/b/prefix/xxx/" and the file name of
+                images would be written into a txt file
+                "a/b/prefix/xxx_pred.txt", where "xxx" is the video name of
+                cityscapes. If not specified, a temp file will be created.
+                Default: None.
+            classwise (bool): Whether to evaluating the AP for each class.
+            proposal_nums (Sequence[int]): Proposal number used for evaluating
+                recalls, such as recall@100, recall@1000.
+                Default: (100, 300, 1000).
+            iou_thrs (Sequence[float]): IoU threshold used for evaluating
+                recalls. If set to a list, the average recall of all IoUs will
+                also be computed. Default: 0.5.
+
+        Returns:
+            dict[str, float]: COCO style evaluation metric or cityscapes mAP \
+                and AP@50.
+        """
+        eval_results = dict()
+
+        metrics = metric.copy() if isinstance(metric, list) else [metric]
+
+        if 'cityscapes' in metrics:
+            eval_results.update(
+                self._evaluate_cityscapes(results, outfile_prefix, logger))
+            metrics.remove('cityscapes')
+
+        # left metrics are all coco metric
+        if len(metrics) > 0:
+            # create CocoDataset with CityscapesDataset annotation
+            self_coco = CocoDataset(self.ann_file, self.pipeline.transforms,
+                                    None, self.data_root, self.img_prefix,
+                                    self.seg_prefix, self.proposal_file,
+                                    self.test_mode, self.filter_empty_gt)
+            # TODO: remove this in the future
+            # reload annotations of correct class
+            self_coco.CLASSES = self.CLASSES
+            self_coco.data_infos = self_coco.load_annotations(self.ann_file)
+            eval_results.update(
+                self_coco.evaluate(results, metrics, logger, outfile_prefix,
+                                   classwise, proposal_nums, iou_thrs))
+
+        return eval_results
+
+    def _evaluate_cityscapes(self, results, txtfile_prefix, logger):
+        """Evaluation in Cityscapes protocol.
+
+        Args:
+            results (list): Testing results of the dataset.
+            txtfile_prefix (str | None): The prefix of output txt file
+            logger (logging.Logger | str | None): Logger used for printing
+                related information during evaluation. Default: None.
+
+        Returns:
+            dict[str: float]: Cityscapes evaluation results, contains 'mAP' \
+                and 'AP@50'.
+        """
+
+        try:
+            import cityscapesscripts.evaluation.evalInstanceLevelSemanticLabeling as CSEval  # noqa
+        except ImportError:
+            raise ImportError('Please run "pip install citscapesscripts" to '
+                              'install cityscapesscripts first.')
+        msg = 'Evaluating in Cityscapes style'
+        if logger is None:
+            msg = '\n' + msg
+        print_log(msg, logger=logger)
+
+        result_files, tmp_dir = self.format_results(results, txtfile_prefix)
+
+        if tmp_dir is None:
+            result_dir = osp.join(txtfile_prefix, 'results')
+        else:
+            result_dir = osp.join(tmp_dir.name, 'results')
+
+        eval_results = OrderedDict()
+        print_log(f'Evaluating results under {result_dir} ...', logger=logger)
+
+        # set global states in cityscapes evaluation API
+        CSEval.args.cityscapesPath = os.path.join(self.img_prefix, '../..')
+        CSEval.args.predictionPath = os.path.abspath(result_dir)
+        CSEval.args.predictionWalk = None
+        CSEval.args.JSONOutput = False
+        CSEval.args.colorized = False
+        CSEval.args.gtInstancesFile = os.path.join(result_dir,
+                                                   'gtInstances.json')
+        CSEval.args.groundTruthSearch = os.path.join(
+            self.img_prefix.replace('leftImg8bit', 'gtFine'),
+            '*/*_gtFine_instanceIds.png')
+
+        groundTruthImgList = glob.glob(CSEval.args.groundTruthSearch)
+        assert len(groundTruthImgList), 'Cannot find ground truth images' \
+            f' in {CSEval.args.groundTruthSearch}.'
+        predictionImgList = []
+        for gt in groundTruthImgList:
+            predictionImgList.append(CSEval.getPrediction(gt, CSEval.args))
+        CSEval_results = CSEval.evaluateImgLists(predictionImgList,
+                                                 groundTruthImgList,
+                                                 CSEval.args)['averages']
+
+        eval_results['mAP'] = CSEval_results['allAp']
+        eval_results['AP@50'] = CSEval_results['allAp50%']
+        if tmp_dir is not None:
+            tmp_dir.cleanup()
+        return eval_results

PyTorch/NLP/Conformer-main/mmdetection/mmdet/datasets/coco.py

+import itertools
+import logging
+import os.path as osp
+import tempfile
+from collections import OrderedDict
+
+import mmcv
+import numpy as np
+from mmcv.utils import print_log
+from pycocotools.coco import COCO
+from pycocotools.cocoeval import COCOeval
+from terminaltables import AsciiTable
+
+from mmdet.core import eval_recalls
+from .builder import DATASETS
+from .custom import CustomDataset
+
+try:
+    import pycocotools
+    if not hasattr(pycocotools, '__sphinx_mock__'):  # for doc generation
+        assert pycocotools.__version__ >= '12.0.2'
+except AssertionError:
+    raise AssertionError('Incompatible version of pycocotools is installed. '
+                         'Run pip uninstall pycocotools first. Then run pip '
+                         'install mmpycocotools to install open-mmlab forked '
+                         'pycocotools.')
+
+
+@DATASETS.register_module()
+class CocoDataset(CustomDataset):
+
+    CLASSES = ('person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus',
+               'train', 'truck', 'boat', 'traffic light', 'fire hydrant',
+               'stop sign', 'parking meter', 'bench', 'bird', 'cat', 'dog',
+               'horse', 'sheep', 'cow', 'elephant', 'bear', 'zebra', 'giraffe',
+               'backpack', 'umbrella', 'handbag', 'tie', 'suitcase', 'frisbee',
+               'skis', 'snowboard', 'sports ball', 'kite', 'baseball bat',
+               'baseball glove', 'skateboard', 'surfboard', 'tennis racket',
+               'bottle', 'wine glass', 'cup', 'fork', 'knife', 'spoon', 'bowl',
+               'banana', 'apple', 'sandwich', 'orange', 'broccoli', 'carrot',
+               'hot dog', 'pizza', 'donut', 'cake', 'chair', 'couch',
+               'potted plant', 'bed', 'dining table', 'toilet', 'tv', 'laptop',
+               'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
+               'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock',
+               'vase', 'scissors', 'teddy bear', 'hair drier', 'toothbrush')
+
+    def load_annotations(self, ann_file):
+        """Load annotation from COCO style annotation file.
+
+        Args:
+            ann_file (str): Path of annotation file.
+
+        Returns:
+            list[dict]: Annotation info from COCO api.
+        """
+
+        self.coco = COCO(ann_file)
+        self.cat_ids = self.coco.get_cat_ids(cat_names=self.CLASSES)
+        self.cat2label = {cat_id: i for i, cat_id in enumerate(self.cat_ids)}
+        self.img_ids = self.coco.get_img_ids()
+        data_infos = []
+        for i in self.img_ids:
+            info = self.coco.load_imgs([i])[0]
+            info['filename'] = info['file_name']
+            data_infos.append(info)
+        return data_infos
+
+    def get_ann_info(self, idx):
+        """Get COCO annotation by index.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Annotation info of specified index.
+        """
+
+        img_id = self.data_infos[idx]['id']
+        ann_ids = self.coco.get_ann_ids(img_ids=[img_id])
+        ann_info = self.coco.load_anns(ann_ids)
+        return self._parse_ann_info(self.data_infos[idx], ann_info)
+
+    def get_cat_ids(self, idx):
+        """Get COCO category ids by index.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            list[int]: All categories in the image of specified index.
+        """
+
+        img_id = self.data_infos[idx]['id']
+        ann_ids = self.coco.get_ann_ids(img_ids=[img_id])
+        ann_info = self.coco.load_anns(ann_ids)
+        return [ann['category_id'] for ann in ann_info]
+
+    def _filter_imgs(self, min_size=32):
+        """Filter images too small or without ground truths."""
+        valid_inds = []
+        # obtain images that contain annotation
+        ids_with_ann = set(_['image_id'] for _ in self.coco.anns.values())
+        # obtain images that contain annotations of the required categories
+        ids_in_cat = set()
+        for i, class_id in enumerate(self.cat_ids):
+            ids_in_cat |= set(self.coco.cat_img_map[class_id])
+        # merge the image id sets of the two conditions and use the merged set
+        # to filter out images if self.filter_empty_gt=True
+        ids_in_cat &= ids_with_ann
+
+        valid_img_ids = []
+        for i, img_info in enumerate(self.data_infos):
+            img_id = self.img_ids[i]
+            if self.filter_empty_gt and img_id not in ids_in_cat:
+                continue
+            if min(img_info['width'], img_info['height']) >= min_size:
+                valid_inds.append(i)
+                valid_img_ids.append(img_id)
+        self.img_ids = valid_img_ids
+        return valid_inds
+
+    def _parse_ann_info(self, img_info, ann_info):
+        """Parse bbox and mask annotation.
+
+        Args:
+            ann_info (list[dict]): Annotation info of an image.
+            with_mask (bool): Whether to parse mask annotations.
+
+        Returns:
+            dict: A dict containing the following keys: bboxes, bboxes_ignore,\
+                labels, masks, seg_map. "masks" are raw annotations and not \
+                decoded into binary masks.
+        """
+        gt_bboxes = []
+        gt_labels = []
+        gt_bboxes_ignore = []
+        gt_masks_ann = []
+        for i, ann in enumerate(ann_info):
+            if ann.get('ignore', False):
+                continue
+            x1, y1, w, h = ann['bbox']
+            inter_w = max(0, min(x1 + w, img_info['width']) - max(x1, 0))
+            inter_h = max(0, min(y1 + h, img_info['height']) - max(y1, 0))
+            if inter_w * inter_h == 0:
+                continue
+            if ann['area'] <= 0 or w < 1 or h < 1:
+                continue
+            if ann['category_id'] not in self.cat_ids:
+                continue
+            bbox = [x1, y1, x1 + w, y1 + h]
+            if ann.get('iscrowd', False):
+                gt_bboxes_ignore.append(bbox)
+            else:
+                gt_bboxes.append(bbox)
+                gt_labels.append(self.cat2label[ann['category_id']])
+                gt_masks_ann.append(ann.get('segmentation', None))
+
+        if gt_bboxes:
+            gt_bboxes = np.array(gt_bboxes, dtype=np.float32)
+            gt_labels = np.array(gt_labels, dtype=np.int64)
+        else:
+            gt_bboxes = np.zeros((0, 4), dtype=np.float32)
+            gt_labels = np.array([], dtype=np.int64)
+
+        if gt_bboxes_ignore:
+            gt_bboxes_ignore = np.array(gt_bboxes_ignore, dtype=np.float32)
+        else:
+            gt_bboxes_ignore = np.zeros((0, 4), dtype=np.float32)
+
+        seg_map = img_info['filename'].replace('jpg', 'png')
+
+        ann = dict(
+            bboxes=gt_bboxes,
+            labels=gt_labels,
+            bboxes_ignore=gt_bboxes_ignore,
+            masks=gt_masks_ann,
+            seg_map=seg_map)
+
+        return ann
+
+    def xyxy2xywh(self, bbox):
+        """Convert ``xyxy`` style bounding boxes to ``xywh`` style for COCO
+        evaluation.
+
+        Args:
+            bbox (numpy.ndarray): The bounding boxes, shape (4, ), in
+                ``xyxy`` order.
+
+        Returns:
+            list[float]: The converted bounding boxes, in ``xywh`` order.
+        """
+
+        _bbox = bbox.tolist()
+        return [
+            _bbox[0],
+            _bbox[1],
+            _bbox[2] - _bbox[0],
+            _bbox[3] - _bbox[1],
+        ]
+
+    def _proposal2json(self, results):
+        """Convert proposal results to COCO json style."""
+        json_results = []
+        for idx in range(len(self)):
+            img_id = self.img_ids[idx]
+            bboxes = results[idx]
+            for i in range(bboxes.shape[0]):
+                data = dict()
+                data['image_id'] = img_id
+                data['bbox'] = self.xyxy2xywh(bboxes[i])
+                data['score'] = float(bboxes[i][4])
+                data['category_id'] = 1
+                json_results.append(data)
+        return json_results
+
+    def _det2json(self, results):
+        """Convert detection results to COCO json style."""
+        json_results = []
+        for idx in range(len(self)):
+            img_id = self.img_ids[idx]
+            result = results[idx]
+            for label in range(len(result)):
+                bboxes = result[label]
+                for i in range(bboxes.shape[0]):
+                    data = dict()
+                    data['image_id'] = img_id
+                    data['bbox'] = self.xyxy2xywh(bboxes[i])
+                    data['score'] = float(bboxes[i][4])
+                    data['category_id'] = self.cat_ids[label]
+                    json_results.append(data)
+        return json_results
+
+    def _segm2json(self, results):
+        """Convert instance segmentation results to COCO json style."""
+        bbox_json_results = []
+        segm_json_results = []
+        for idx in range(len(self)):
+            img_id = self.img_ids[idx]
+            det, seg = results[idx]
+            for label in range(len(det)):
+                # bbox results
+                bboxes = det[label]
+                for i in range(bboxes.shape[0]):
+                    data = dict()
+                    data['image_id'] = img_id
+                    data['bbox'] = self.xyxy2xywh(bboxes[i])
+                    data['score'] = float(bboxes[i][4])
+                    data['category_id'] = self.cat_ids[label]
+                    bbox_json_results.append(data)
+
+                # segm results
+                # some detectors use different scores for bbox and mask
+                if isinstance(seg, tuple):
+                    segms = seg[0][label]
+                    mask_score = seg[1][label]
+                else:
+                    segms = seg[label]
+                    mask_score = [bbox[4] for bbox in bboxes]
+                for i in range(bboxes.shape[0]):
+                    data = dict()
+                    data['image_id'] = img_id
+                    data['bbox'] = self.xyxy2xywh(bboxes[i])
+                    data['score'] = float(mask_score[i])
+                    data['category_id'] = self.cat_ids[label]
+                    if isinstance(segms[i]['counts'], bytes):
+                        segms[i]['counts'] = segms[i]['counts'].decode()
+                    data['segmentation'] = segms[i]
+                    segm_json_results.append(data)
+        return bbox_json_results, segm_json_results
+
+    def results2json(self, results, outfile_prefix):
+        """Dump the detection results to a COCO style json file.
+
+        There are 3 types of results: proposals, bbox predictions, mask
+        predictions, and they have different data types. This method will
+        automatically recognize the type, and dump them to json files.
+
+        Args:
+            results (list[list | tuple | ndarray]): Testing results of the
+                dataset.
+            outfile_prefix (str): The filename prefix of the json files. If the
+                prefix is "somepath/xxx", the json files will be named
+                "somepath/xxx.bbox.json", "somepath/xxx.segm.json",
+                "somepath/xxx.proposal.json".
+
+        Returns:
+            dict[str: str]: Possible keys are "bbox", "segm", "proposal", and \
+                values are corresponding filenames.
+        """
+        result_files = dict()
+        if isinstance(results[0], list):
+            json_results = self._det2json(results)
+            result_files['bbox'] = f'{outfile_prefix}.bbox.json'
+            result_files['proposal'] = f'{outfile_prefix}.bbox.json'
+            mmcv.dump(json_results, result_files['bbox'])
+        elif isinstance(results[0], tuple):
+            json_results = self._segm2json(results)
+            result_files['bbox'] = f'{outfile_prefix}.bbox.json'
+            result_files['proposal'] = f'{outfile_prefix}.bbox.json'
+            result_files['segm'] = f'{outfile_prefix}.segm.json'
+            mmcv.dump(json_results[0], result_files['bbox'])
+            mmcv.dump(json_results[1], result_files['segm'])
+        elif isinstance(results[0], np.ndarray):
+            json_results = self._proposal2json(results)
+            result_files['proposal'] = f'{outfile_prefix}.proposal.json'
+            mmcv.dump(json_results, result_files['proposal'])
+        else:
+            raise TypeError('invalid type of results')
+        return result_files
+
+    def fast_eval_recall(self, results, proposal_nums, iou_thrs, logger=None):
+        gt_bboxes = []
+        for i in range(len(self.img_ids)):
+            ann_ids = self.coco.get_ann_ids(img_ids=self.img_ids[i])
+            ann_info = self.coco.load_anns(ann_ids)
+            if len(ann_info) == 0:
+                gt_bboxes.append(np.zeros((0, 4)))
+                continue
+            bboxes = []
+            for ann in ann_info:
+                if ann.get('ignore', False) or ann['iscrowd']:
+                    continue
+                x1, y1, w, h = ann['bbox']
+                bboxes.append([x1, y1, x1 + w, y1 + h])
+            bboxes = np.array(bboxes, dtype=np.float32)
+            if bboxes.shape[0] == 0:
+                bboxes = np.zeros((0, 4))
+            gt_bboxes.append(bboxes)
+
+        recalls = eval_recalls(
+            gt_bboxes, results, proposal_nums, iou_thrs, logger=logger)
+        ar = recalls.mean(axis=1)
+        return ar
+
+    def format_results(self, results, jsonfile_prefix=None, **kwargs):
+        """Format the results to json (standard format for COCO evaluation).
+
+        Args:
+            results (list[tuple | numpy.ndarray]): Testing results of the
+                dataset.
+            jsonfile_prefix (str | None): The prefix of json files. It includes
+                the file path and the prefix of filename, e.g., "a/b/prefix".
+                If not specified, a temp file will be created. Default: None.
+
+        Returns:
+            tuple: (result_files, tmp_dir), result_files is a dict containing \
+                the json filepaths, tmp_dir is the temporal directory created \
+                for saving json files when jsonfile_prefix is not specified.
+        """
+        assert isinstance(results, list), 'results must be a list'
+        assert len(results) == len(self), (
+            'The length of results is not equal to the dataset len: {} != {}'.
+            format(len(results), len(self)))
+
+        if jsonfile_prefix is None:
+            tmp_dir = tempfile.TemporaryDirectory()
+            jsonfile_prefix = osp.join(tmp_dir.name, 'results')
+        else:
+            tmp_dir = None
+        result_files = self.results2json(results, jsonfile_prefix)
+        return result_files, tmp_dir
+
+    def evaluate(self,
+                 results,
+                 metric='bbox',
+                 logger=None,
+                 jsonfile_prefix=None,
+                 classwise=False,
+                 proposal_nums=(100, 300, 1000),
+                 iou_thrs=None,
+                 metric_items=None):
+        """Evaluation in COCO protocol.
+
+        Args:
+            results (list[list | tuple]): Testing results of the dataset.
+            metric (str | list[str]): Metrics to be evaluated. Options are
+                'bbox', 'segm', 'proposal', 'proposal_fast'.
+            logger (logging.Logger | str | None): Logger used for printing
+                related information during evaluation. Default: None.
+            jsonfile_prefix (str | None): The prefix of json files. It includes
+                the file path and the prefix of filename, e.g., "a/b/prefix".
+                If not specified, a temp file will be created. Default: None.
+            classwise (bool): Whether to evaluating the AP for each class.
+            proposal_nums (Sequence[int]): Proposal number used for evaluating
+                recalls, such as recall@100, recall@1000.
+                Default: (100, 300, 1000).
+            iou_thrs (Sequence[float], optional): IoU threshold used for
+                evaluating recalls/mAPs. If set to a list, the average of all
+                IoUs will also be computed. If not specified, [0.50, 0.55,
+                0.60, 0.65, 0.70, 0.75, 0.80, 0.85, 0.90, 0.95] will be used.
+                Default: None.
+            metric_items (list[str] | str, optional): Metric items that will
+                be returned. If not specified, ``['AR@100', 'AR@300',
+                'AR@1000', 'AR_s@1000', 'AR_m@1000', 'AR_l@1000' ]`` will be
+                used when ``metric=='proposal'``, ``['mAP', 'mAP_50', 'mAP_75',
+                'mAP_s', 'mAP_m', 'mAP_l']`` will be used when
+                ``metric=='bbox' or metric=='segm'``.
+
+        Returns:
+            dict[str, float]: COCO style evaluation metric.
+        """
+
+        metrics = metric if isinstance(metric, list) else [metric]
+        allowed_metrics = ['bbox', 'segm', 'proposal', 'proposal_fast']
+        for metric in metrics:
+            if metric not in allowed_metrics:
+                raise KeyError(f'metric {metric} is not supported')
+        if iou_thrs is None:
+            iou_thrs = np.linspace(
+                .5, 0.95, int(np.round((0.95 - .5) / .05)) + 1, endpoint=True)
+        if metric_items is not None:
+            if not isinstance(metric_items, list):
+                metric_items = [metric_items]
+
+        result_files, tmp_dir = self.format_results(results, jsonfile_prefix)
+
+        eval_results = OrderedDict()
+        cocoGt = self.coco
+        for metric in metrics:
+            msg = f'Evaluating {metric}...'
+            if logger is None:
+                msg = '\n' + msg
+            print_log(msg, logger=logger)
+
+            if metric == 'proposal_fast':
+                ar = self.fast_eval_recall(
+                    results, proposal_nums, iou_thrs, logger='silent')
+                log_msg = []
+                for i, num in enumerate(proposal_nums):
+                    eval_results[f'AR@{num}'] = ar[i]
+                    log_msg.append(f'\nAR@{num}\t{ar[i]:.4f}')
+                log_msg = ''.join(log_msg)
+                print_log(log_msg, logger=logger)
+                continue
+
+            if metric not in result_files:
+                raise KeyError(f'{metric} is not in results')
+            try:
+                cocoDt = cocoGt.loadRes(result_files[metric])
+            except IndexError:
+                print_log(
+                    'The testing results of the whole dataset is empty.',
+                    logger=logger,
+                    level=logging.ERROR)
+                break
+
+            iou_type = 'bbox' if metric == 'proposal' else metric
+            cocoEval = COCOeval(cocoGt, cocoDt, iou_type)
+            cocoEval.params.catIds = self.cat_ids
+            cocoEval.params.imgIds = self.img_ids
+            cocoEval.params.maxDets = list(proposal_nums)
+            cocoEval.params.iouThrs = iou_thrs
+            # mapping of cocoEval.stats
+            coco_metric_names = {
+                'mAP': 0,
+                'mAP_50': 1,
+                'mAP_75': 2,
+                'mAP_s': 3,
+                'mAP_m': 4,
+                'mAP_l': 5,
+                'AR@100': 6,
+                'AR@300': 7,
+                'AR@1000': 8,
+                'AR_s@1000': 9,
+                'AR_m@1000': 10,
+                'AR_l@1000': 11
+            }
+            if metric_items is not None:
+                for metric_item in metric_items:
+                    if metric_item not in coco_metric_names:
+                        raise KeyError(
+                            f'metric item {metric_item} is not supported')
+
+            if metric == 'proposal':
+                cocoEval.params.useCats = 0
+                cocoEval.evaluate()
+                cocoEval.accumulate()
+                cocoEval.summarize()
+                if metric_items is None:
+                    metric_items = [
+                        'AR@100', 'AR@300', 'AR@1000', 'AR_s@1000',
+                        'AR_m@1000', 'AR_l@1000'
+                    ]
+
+                for item in metric_items:
+                    val = float(
+                        f'{cocoEval.stats[coco_metric_names[item]]:.3f}')
+                    eval_results[item] = val
+            else:
+                cocoEval.evaluate()
+                cocoEval.accumulate()
+                cocoEval.summarize()
+                if classwise:  # Compute per-category AP
+                    # Compute per-category AP
+                    # from https://github.com/facebookresearch/detectron2/
+                    precisions = cocoEval.eval['precision']
+                    # precision: (iou, recall, cls, area range, max dets)
+                    assert len(self.cat_ids) == precisions.shape[2]
+
+                    results_per_category = []
+                    for idx, catId in enumerate(self.cat_ids):
+                        # area range index 0: all area ranges
+                        # max dets index -1: typically 100 per image
+                        nm = self.coco.loadCats(catId)[0]
+                        precision = precisions[:, :, idx, 0, -1]
+                        precision = precision[precision > -1]
+                        if precision.size:
+                            ap = np.mean(precision)
+                        else:
+                            ap = float('nan')
+                        results_per_category.append(
+                            (f'{nm["name"]}', f'{float(ap):0.3f}'))
+
+                    num_columns = min(6, len(results_per_category) * 2)
+                    results_flatten = list(
+                        itertools.chain(*results_per_category))
+                    headers = ['category', 'AP'] * (num_columns // 2)
+                    results_2d = itertools.zip_longest(*[
+                        results_flatten[i::num_columns]
+                        for i in range(num_columns)
+                    ])
+                    table_data = [headers]
+                    table_data += [result for result in results_2d]
+                    table = AsciiTable(table_data)
+                    print_log('\n' + table.table, logger=logger)
+
+                if metric_items is None:
+                    metric_items = [
+                        'mAP', 'mAP_50', 'mAP_75', 'mAP_s', 'mAP_m', 'mAP_l'
+                    ]
+
+                for metric_item in metric_items:
+                    key = f'{metric}_{metric_item}'
+                    val = float(
+                        f'{cocoEval.stats[coco_metric_names[metric_item]]:.3f}'
+                    )
+                    eval_results[key] = val
+                ap = cocoEval.stats[:6]
+                eval_results[f'{metric}_mAP_copypaste'] = (
+                    f'{ap[0]:.3f} {ap[1]:.3f} {ap[2]:.3f} {ap[3]:.3f} '
+                    f'{ap[4]:.3f} {ap[5]:.3f}')
+        if tmp_dir is not None:
+            tmp_dir.cleanup()
+        return eval_results

PyTorch/NLP/Conformer-main/mmdetection/mmdet/datasets/custom.py

+import os.path as osp
+import warnings
+from collections import OrderedDict
+
+import mmcv
+import numpy as np
+from mmcv.utils import print_log
+from torch.utils.data import Dataset
+
+from mmdet.core import eval_map, eval_recalls
+from .builder import DATASETS
+from .pipelines import Compose
+
+
+@DATASETS.register_module()
+class CustomDataset(Dataset):
+    """Custom dataset for detection.
+
+    The annotation format is shown as follows. The `ann` field is optional for
+    testing.
+
+    .. code-block:: none
+
+        [
+            {
+                'filename': 'a.jpg',
+                'width': 1280,
+                'height': 720,
+                'ann': {
+                    'bboxes': <np.ndarray> (n, 4) in (x1, y1, x2, y2) order.
+                    'labels': <np.ndarray> (n, ),
+                    'bboxes_ignore': <np.ndarray> (k, 4), (optional field)
+                    'labels_ignore': <np.ndarray> (k, 4) (optional field)
+                }
+            },
+            ...
+        ]
+
+    Args:
+        ann_file (str): Annotation file path.
+        pipeline (list[dict]): Processing pipeline.
+        classes (str | Sequence[str], optional): Specify classes to load.
+            If is None, ``cls.CLASSES`` will be used. Default: None.
+        data_root (str, optional): Data root for ``ann_file``,
+            ``img_prefix``, ``seg_prefix``, ``proposal_file`` if specified.
+        test_mode (bool, optional): If set True, annotation will not be loaded.
+        filter_empty_gt (bool, optional): If set true, images without bounding
+            boxes of the dataset's classes will be filtered out. This option
+            only works when `test_mode=False`, i.e., we never filter images
+            during tests.
+    """
+
+    CLASSES = None
+
+    def __init__(self,
+                 ann_file,
+                 pipeline,
+                 classes=None,
+                 data_root=None,
+                 img_prefix='',
+                 seg_prefix=None,
+                 proposal_file=None,
+                 test_mode=False,
+                 filter_empty_gt=True):
+        self.ann_file = ann_file
+        self.data_root = data_root
+        self.img_prefix = img_prefix
+        self.seg_prefix = seg_prefix
+        self.proposal_file = proposal_file
+        self.test_mode = test_mode
+        self.filter_empty_gt = filter_empty_gt
+        self.CLASSES = self.get_classes(classes)
+
+        # join paths if data_root is specified
+        if self.data_root is not None:
+            if not osp.isabs(self.ann_file):
+                self.ann_file = osp.join(self.data_root, self.ann_file)
+            if not (self.img_prefix is None or osp.isabs(self.img_prefix)):
+                self.img_prefix = osp.join(self.data_root, self.img_prefix)
+            if not (self.seg_prefix is None or osp.isabs(self.seg_prefix)):
+                self.seg_prefix = osp.join(self.data_root, self.seg_prefix)
+            if not (self.proposal_file is None
+                    or osp.isabs(self.proposal_file)):
+                self.proposal_file = osp.join(self.data_root,
+                                              self.proposal_file)
+        # load annotations (and proposals)
+        self.data_infos = self.load_annotations(self.ann_file)
+
+        if self.proposal_file is not None:
+            self.proposals = self.load_proposals(self.proposal_file)
+        else:
+            self.proposals = None
+
+        # filter images too small and containing no annotations
+        if not test_mode:
+            valid_inds = self._filter_imgs()
+            self.data_infos = [self.data_infos[i] for i in valid_inds]
+            if self.proposals is not None:
+                self.proposals = [self.proposals[i] for i in valid_inds]
+            # set group flag for the sampler
+            self._set_group_flag()
+
+        # processing pipeline
+        self.pipeline = Compose(pipeline)
+
+    def __len__(self):
+        """Total number of samples of data."""
+        return len(self.data_infos)
+
+    def load_annotations(self, ann_file):
+        """Load annotation from annotation file."""
+        return mmcv.load(ann_file)
+
+    def load_proposals(self, proposal_file):
+        """Load proposal from proposal file."""
+        return mmcv.load(proposal_file)
+
+    def get_ann_info(self, idx):
+        """Get annotation by index.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Annotation info of specified index.
+        """
+
+        return self.data_infos[idx]['ann']
+
+    def get_cat_ids(self, idx):
+        """Get category ids by index.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            list[int]: All categories in the image of specified index.
+        """
+
+        return self.data_infos[idx]['ann']['labels'].astype(np.int).tolist()
+
+    def pre_pipeline(self, results):
+        """Prepare results dict for pipeline."""
+        results['img_prefix'] = self.img_prefix
+        results['seg_prefix'] = self.seg_prefix
+        results['proposal_file'] = self.proposal_file
+        results['bbox_fields'] = []
+        results['mask_fields'] = []
+        results['seg_fields'] = []
+
+    def _filter_imgs(self, min_size=32):
+        """Filter images too small."""
+        if self.filter_empty_gt:
+            warnings.warn(
+                'CustomDataset does not support filtering empty gt images.')
+        valid_inds = []
+        for i, img_info in enumerate(self.data_infos):
+            if min(img_info['width'], img_info['height']) >= min_size:
+                valid_inds.append(i)
+        return valid_inds
+
+    def _set_group_flag(self):
+        """Set flag according to image aspect ratio.
+
+        Images with aspect ratio greater than 1 will be set as group 1,
+        otherwise group 0.
+        """
+        self.flag = np.zeros(len(self), dtype=np.uint8)
+        for i in range(len(self)):
+            img_info = self.data_infos[i]
+            if img_info['width'] / img_info['height'] > 1:
+                self.flag[i] = 1
+
+    def _rand_another(self, idx):
+        """Get another random index from the same group as the given index."""
+        pool = np.where(self.flag == self.flag[idx])[0]
+        return np.random.choice(pool)
+
+    def __getitem__(self, idx):
+        """Get training/test data after pipeline.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Training/test data (with annotation if `test_mode` is set \
+                True).
+        """
+
+        if self.test_mode:
+            return self.prepare_test_img(idx)
+        while True:
+            data = self.prepare_train_img(idx)
+            if data is None:
+                idx = self._rand_another(idx)
+                continue
+            return data
+
+    def prepare_train_img(self, idx):
+        """Get training data and annotations after pipeline.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Training data and annotation after pipeline with new keys \
+                introduced by pipeline.
+        """
+
+        img_info = self.data_infos[idx]
+        ann_info = self.get_ann_info(idx)
+        results = dict(img_info=img_info, ann_info=ann_info)
+        if self.proposals is not None:
+            results['proposals'] = self.proposals[idx]
+        self.pre_pipeline(results)
+        return self.pipeline(results)
+
+    def prepare_test_img(self, idx):
+        """Get testing data  after pipeline.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            dict: Testing data after pipeline with new keys intorduced by \
+                piepline.
+        """
+
+        img_info = self.data_infos[idx]
+        results = dict(img_info=img_info)
+        if self.proposals is not None:
+            results['proposals'] = self.proposals[idx]
+        self.pre_pipeline(results)
+        return self.pipeline(results)
+
+    @classmethod
+    def get_classes(cls, classes=None):
+        """Get class names of current dataset.
+
+        Args:
+            classes (Sequence[str] | str | None): If classes is None, use
+                default CLASSES defined by builtin dataset. If classes is a
+                string, take it as a file name. The file contains the name of
+                classes where each line contains one class name. If classes is
+                a tuple or list, override the CLASSES defined by the dataset.
+
+        Returns:
+            tuple[str] or list[str]: Names of categories of the dataset.
+        """
+        if classes is None:
+            return cls.CLASSES
+
+        if isinstance(classes, str):
+            # take it as a file path
+            class_names = mmcv.list_from_file(classes)
+        elif isinstance(classes, (tuple, list)):
+            class_names = classes
+        else:
+            raise ValueError(f'Unsupported type {type(classes)} of classes.')
+
+        return class_names
+
+    def format_results(self, results, **kwargs):
+        """Place holder to format result to dataset specific output."""
+        pass
+
+    def evaluate(self,
+                 results,
+                 metric='mAP',
+                 logger=None,
+                 proposal_nums=(100, 300, 1000),
+                 iou_thr=0.5,
+                 scale_ranges=None):
+        """Evaluate the dataset.
+
+        Args:
+            results (list): Testing results of the dataset.
+            metric (str | list[str]): Metrics to be evaluated.
+            logger (logging.Logger | None | str): Logger used for printing
+                related information during evaluation. Default: None.
+            proposal_nums (Sequence[int]): Proposal number used for evaluating
+                recalls, such as recall@100, recall@1000.
+                Default: (100, 300, 1000).
+            iou_thr (float | list[float]): IoU threshold. Default: 0.5.
+            scale_ranges (list[tuple] | None): Scale ranges for evaluating mAP.
+                Default: None.
+        """
+
+        if not isinstance(metric, str):
+            assert len(metric) == 1
+            metric = metric[0]
+        allowed_metrics = ['mAP', 'recall']
+        if metric not in allowed_metrics:
+            raise KeyError(f'metric {metric} is not supported')
+        annotations = [self.get_ann_info(i) for i in range(len(self))]
+        eval_results = OrderedDict()
+        iou_thrs = [iou_thr] if isinstance(iou_thr, float) else iou_thr
+        if metric == 'mAP':
+            assert isinstance(iou_thrs, list)
+            mean_aps = []
+            for iou_thr in iou_thrs:
+                print_log(f'\n{"-" * 15}iou_thr: {iou_thr}{"-" * 15}')
+                mean_ap, _ = eval_map(
+                    results,
+                    annotations,
+                    scale_ranges=scale_ranges,
+                    iou_thr=iou_thr,
+                    dataset=self.CLASSES,
+                    logger=logger)
+                mean_aps.append(mean_ap)
+                eval_results[f'AP{int(iou_thr * 100):02d}'] = round(mean_ap, 3)
+            eval_results['mAP'] = sum(mean_aps) / len(mean_aps)
+        elif metric == 'recall':
+            gt_bboxes = [ann['bboxes'] for ann in annotations]
+            recalls = eval_recalls(
+                gt_bboxes, results, proposal_nums, iou_thr, logger=logger)
+            for i, num in enumerate(proposal_nums):
+                for j, iou in enumerate(iou_thr):
+                    eval_results[f'recall@{num}@{iou}'] = recalls[i, j]
+            if recalls.shape[1] > 1:
+                ar = recalls.mean(axis=1)
+                for i, num in enumerate(proposal_nums):
+                    eval_results[f'AR@{num}'] = ar[i]
+        return eval_results

PyTorch/NLP/Conformer-main/mmdetection/mmdet/datasets/dataset_wrappers.py

+import bisect
+import math
+from collections import defaultdict
+
+import numpy as np
+from mmcv.utils import print_log
+from torch.utils.data.dataset import ConcatDataset as _ConcatDataset
+
+from .builder import DATASETS
+from .coco import CocoDataset
+
+
+@DATASETS.register_module()
+class ConcatDataset(_ConcatDataset):
+    """A wrapper of concatenated dataset.
+
+    Same as :obj:`torch.utils.data.dataset.ConcatDataset`, but
+    concat the group flag for image aspect ratio.
+
+    Args:
+        datasets (list[:obj:`Dataset`]): A list of datasets.
+        separate_eval (bool): Whether to evaluate the results
+            separately if it is used as validation dataset.
+            Defaults to True.
+    """
+
+    def __init__(self, datasets, separate_eval=True):
+        super(ConcatDataset, self).__init__(datasets)
+        self.CLASSES = datasets[0].CLASSES
+        self.separate_eval = separate_eval
+        if not separate_eval:
+            if any([isinstance(ds, CocoDataset) for ds in datasets]):
+                raise NotImplementedError(
+                    'Evaluating concatenated CocoDataset as a whole is not'
+                    ' supported! Please set "separate_eval=True"')
+            elif len(set([type(ds) for ds in datasets])) != 1:
+                raise NotImplementedError(
+                    'All the datasets should have same types')
+
+        if hasattr(datasets[0], 'flag'):
+            flags = []
+            for i in range(0, len(datasets)):
+                flags.append(datasets[i].flag)
+            self.flag = np.concatenate(flags)
+
+    def get_cat_ids(self, idx):
+        """Get category ids of concatenated dataset by index.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            list[int]: All categories in the image of specified index.
+        """
+
+        if idx < 0:
+            if -idx > len(self):
+                raise ValueError(
+                    'absolute value of index should not exceed dataset length')
+            idx = len(self) + idx
+        dataset_idx = bisect.bisect_right(self.cumulative_sizes, idx)
+        if dataset_idx == 0:
+            sample_idx = idx
+        else:
+            sample_idx = idx - self.cumulative_sizes[dataset_idx - 1]
+        return self.datasets[dataset_idx].get_cat_ids(sample_idx)
+
+    def evaluate(self, results, logger=None, **kwargs):
+        """Evaluate the results.
+
+        Args:
+            results (list[list | tuple]): Testing results of the dataset.
+            logger (logging.Logger | str | None): Logger used for printing
+                related information during evaluation. Default: None.
+
+        Returns:
+            dict[str: float]: AP results of the total dataset or each separate
+            dataset if `self.separate_eval=True`.
+        """
+        assert len(results) == self.cumulative_sizes[-1], \
+            ('Dataset and results have different sizes: '
+             f'{self.cumulative_sizes[-1]} v.s. {len(results)}')
+
+        # Check whether all the datasets support evaluation
+        for dataset in self.datasets:
+            assert hasattr(dataset, 'evaluate'), \
+                    f'{type(dataset)} does not implement evaluate function'
+
+        if self.separate_eval:
+            dataset_idx = -1
+            total_eval_results = dict()
+            for size, dataset in zip(self.cumulative_sizes, self.datasets):
+                start_idx = 0 if dataset_idx == -1 else \
+                    self.cumulative_sizes[dataset_idx]
+                end_idx = self.cumulative_sizes[dataset_idx + 1]
+
+                results_per_dataset = results[start_idx:end_idx]
+                print_log(
+                    f'\nEvaluateing {dataset.ann_file} with '
+                    f'{len(results_per_dataset)} images now',
+                    logger=logger)
+
+                eval_results_per_dataset = dataset.evaluate(
+                    results_per_dataset, logger=logger, **kwargs)
+                dataset_idx += 1
+                for k, v in eval_results_per_dataset.items():
+                    total_eval_results.update({f'{dataset_idx}_{k}': v})
+
+            return total_eval_results
+        elif any([isinstance(ds, CocoDataset) for ds in self.datasets]):
+            raise NotImplementedError(
+                'Evaluating concatenated CocoDataset as a whole is not'
+                ' supported! Please set "separate_eval=True"')
+        elif len(set([type(ds) for ds in self.datasets])) != 1:
+            raise NotImplementedError(
+                'All the datasets should have same types')
+        else:
+            original_data_infos = self.datasets[0].data_infos
+            self.datasets[0].data_infos = sum(
+                [dataset.data_infos for dataset in self.datasets], [])
+            eval_results = self.datasets[0].evaluate(
+                results, logger=logger, **kwargs)
+            self.datasets[0].data_infos = original_data_infos
+            return eval_results
+
+
+@DATASETS.register_module()
+class RepeatDataset(object):
+    """A wrapper of repeated dataset.
+
+    The length of repeated dataset will be `times` larger than the original
+    dataset. This is useful when the data loading time is long but the dataset
+    is small. Using RepeatDataset can reduce the data loading time between
+    epochs.
+
+    Args:
+        dataset (:obj:`Dataset`): The dataset to be repeated.
+        times (int): Repeat times.
+    """
+
+    def __init__(self, dataset, times):
+        self.dataset = dataset
+        self.times = times
+        self.CLASSES = dataset.CLASSES
+        if hasattr(self.dataset, 'flag'):
+            self.flag = np.tile(self.dataset.flag, times)
+
+        self._ori_len = len(self.dataset)
+
+    def __getitem__(self, idx):
+        return self.dataset[idx % self._ori_len]
+
+    def get_cat_ids(self, idx):
+        """Get category ids of repeat dataset by index.
+
+        Args:
+            idx (int): Index of data.
+
+        Returns:
+            list[int]: All categories in the image of specified index.
+        """
+
+        return self.dataset.get_cat_ids(idx % self._ori_len)
+
+    def __len__(self):
+        """Length after repetition."""
+        return self.times * self._ori_len
+
+
+# Modified from https://github.com/facebookresearch/detectron2/blob/41d475b75a230221e21d9cac5d69655e3415e3a4/detectron2/data/samplers/distributed_sampler.py#L57 # noqa
+@DATASETS.register_module()
+class ClassBalancedDataset(object):
+    """A wrapper of repeated dataset with repeat factor.
+
+    Suitable for training on class imbalanced datasets like LVIS. Following
+    the sampling strategy in the `paper <https://arxiv.org/abs/1908.03195>`_,
+    in each epoch, an image may appear multiple times based on its
+    "repeat factor".
+    The repeat factor for an image is a function of the frequency the rarest
+    category labeled in that image. The "frequency of category c" in [0, 1]
+    is defined by the fraction of images in the training set (without repeats)
+    in which category c appears.
+    The dataset needs to instantiate :func:`self.get_cat_ids` to support
+    ClassBalancedDataset.
+
+    The repeat factor is computed as followed.
+
+    1. For each category c, compute the fraction # of images
+       that contain it: :math:`f(c)`
+    2. For each category c, compute the category-level repeat factor:
+       :math:`r(c) = max(1, sqrt(t/f(c)))`
+    3. For each image I, compute the image-level repeat factor:
+       :math:`r(I) = max_{c in I} r(c)`
+
+    Args:
+        dataset (:obj:`CustomDataset`): The dataset to be repeated.
+        oversample_thr (float): frequency threshold below which data is
+            repeated. For categories with ``f_c >= oversample_thr``, there is
+            no oversampling. For categories with ``f_c < oversample_thr``, the
+            degree of oversampling following the square-root inverse frequency
+            heuristic above.
+        filter_empty_gt (bool, optional): If set true, images without bounding
+            boxes will not be oversampled. Otherwise, they will be categorized
+            as the pure background class and involved into the oversampling.
+            Default: True.
+    """
+
+    def __init__(self, dataset, oversample_thr, filter_empty_gt=True):
+        self.dataset = dataset
+        self.oversample_thr = oversample_thr
+        self.filter_empty_gt = filter_empty_gt
+        self.CLASSES = dataset.CLASSES
+
+        repeat_factors = self._get_repeat_factors(dataset, oversample_thr)
+        repeat_indices = []
+        for dataset_idx, repeat_factor in enumerate(repeat_factors):
+            repeat_indices.extend([dataset_idx] * math.ceil(repeat_factor))
+        self.repeat_indices = repeat_indices
+
+        flags = []
+        if hasattr(self.dataset, 'flag'):
+            for flag, repeat_factor in zip(self.dataset.flag, repeat_factors):
+                flags.extend([flag] * int(math.ceil(repeat_factor)))
+            assert len(flags) == len(repeat_indices)
+        self.flag = np.asarray(flags, dtype=np.uint8)
+
+    def _get_repeat_factors(self, dataset, repeat_thr):
+        """Get repeat factor for each images in the dataset.
+
+        Args:
+            dataset (:obj:`CustomDataset`): The dataset
+            repeat_thr (float): The threshold of frequency. If an image
+                contains the categories whose frequency below the threshold,
+                it would be repeated.
+
+        Returns:
+            list[float]: The repeat factors for each images in the dataset.
+        """
+
+        # 1. For each category c, compute the fraction # of images
+        #   that contain it: f(c)
+        category_freq = defaultdict(int)
+        num_images = len(dataset)
+        for idx in range(num_images):
+            cat_ids = set(self.dataset.get_cat_ids(idx))
+            if len(cat_ids) == 0 and not self.filter_empty_gt:
+                cat_ids = set([len(self.CLASSES)])
+            for cat_id in cat_ids:
+                category_freq[cat_id] += 1
+        for k, v in category_freq.items():
+            category_freq[k] = v / num_images
+
+        # 2. For each category c, compute the category-level repeat factor:
+        #    r(c) = max(1, sqrt(t/f(c)))
+        category_repeat = {
+            cat_id: max(1.0, math.sqrt(repeat_thr / cat_freq))
+            for cat_id, cat_freq in category_freq.items()
+        }
+
+        # 3. For each image I, compute the image-level repeat factor:
+        #    r(I) = max_{c in I} r(c)
+        repeat_factors = []
+        for idx in range(num_images):
+            cat_ids = set(self.dataset.get_cat_ids(idx))
+            if len(cat_ids) == 0 and not self.filter_empty_gt:
+                cat_ids = set([len(self.CLASSES)])
+            repeat_factor = 1
+            if len(cat_ids) > 0:
+                repeat_factor = max(
+                    {category_repeat[cat_id]
+                     for cat_id in cat_ids})
+            repeat_factors.append(repeat_factor)
+
+        return repeat_factors
+
+    def __getitem__(self, idx):
+        ori_index = self.repeat_indices[idx]
+        return self.dataset[ori_index]
+
+    def __len__(self):
+        """Length after repetition."""
+        return len(self.repeat_indices)

PyTorch/NLP/Conformer-main/mmdetection/mmdet/datasets/deepfashion.py

+from .builder import DATASETS
+from .coco import CocoDataset
+
+
+@DATASETS.register_module()
+class DeepFashionDataset(CocoDataset):
+
+    CLASSES = ('top', 'skirt', 'leggings', 'dress', 'outer', 'pants', 'bag',
+               'neckwear', 'headwear', 'eyeglass', 'belt', 'footwear', 'hair',
+               'skin', 'face')