Python mmcv.parallel.DataContainer() Examples

def __call__(self, results):
        """Call function to collect keys in results. The keys in ``meta_keys``
        will be converted to :obj:mmcv.DataContainer.

        Args:
            results (dict): Result dict contains the data to collect.

        Returns:
            dict: The result dict contains the following keys
                - keys in``self.keys``
                - ``img_metas``
        """

        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_metas'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data 

def __call__(self, results):
        """Call function to convert data in results to
        :obj:`mmcv.DataContainer`.

        Args:
            results (dict): Result dict contains the data to convert.

        Returns:
            dict: The result dict contains the data converted to
                :obj:`mmcv.DataContainer`.
        """

        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results 

def __call__(self, results):
        """Call function to transform and format common fields in results.

        Args:
            results (dict): Result dict contains the data to convert.

        Returns:
            dict: The result dict contains the data that is formatted with
                default bundle.
        """

        if 'img' in results:
            img = results['img']
            # add default meta keys
            results = self._add_default_meta_keys(results)
            if len(img.shape) < 3:
                img = np.expand_dims(img, -1)
            img = np.ascontiguousarray(img.transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results 

def __call__(self, results):
        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_meta'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data 

def __call__(self, results):
        if 'img' in results:
            img = np.ascontiguousarray(results['img'].transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results 

def __call__(self, results):
        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results 

def __call__(self, results):
        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_meta'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data 

def __call__(self, results):
        if 'img' in results:
            img = np.ascontiguousarray(results['img'].transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results 

def __call__(self, results):
        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results 

def __call__(self, results):
        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_meta'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data 

def __call__(self, results):
        if 'img' in results:
            img = np.ascontiguousarray(results['img'].transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results 

def __call__(self, results):
        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results 

def __call__(self, results):
        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_meta'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data 

def __call__(self, results):
        if 'img' in results:
            img = np.ascontiguousarray(results['img'].transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results 

def __call__(self, results):
        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results 

def __call__(self, results):
        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results 

def __call__(self, results):
        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_meta'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data 

def __call__(self, results):
        if 'img' in results:
            img = np.ascontiguousarray(results['img'].transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results 

def __call__(self, results):
        for field in self.fields:
            field = field.copy()
            key = field.pop('key')
            results[key] = DC(results[key], **field)
        return results 

def __call__(self, results):
        if 'img' in results:
            img = np.ascontiguousarray(results['img'].transpose(2, 0, 1))
            results['img'] = DC(to_tensor(img), stack=True)
        for key in ['proposals', 'gt_bboxes', 'gt_bboxes_ignore', 'gt_labels']:
            if key not in results:
                continue
            results[key] = DC(to_tensor(results[key]))
        if 'gt_masks' in results:
            results['gt_masks'] = DC(results['gt_masks'], cpu_only=True)
        if 'gt_semantic_seg' in results:
            results['gt_semantic_seg'] = DC(
                to_tensor(results['gt_semantic_seg'][None, ...]), stack=True)
        return results 

def __call__(self, results):
        data = {}
        img_meta = {}
        for key in self.meta_keys:
            img_meta[key] = results[key]
        data['img_meta'] = DC(img_meta, cpu_only=True)
        for key in self.keys:
            data[key] = results[key]
        return data 

def prepare_test_img(self, index):
        cat_ids = {v: i for i, v in enumerate(np.arange(1, 4, dtype=np.int32))} # 原来标注为1，现在设置为0
       
        img_id = self.img_infos[index]['id']
        file_name = self.coco.loadImgs(ids=[img_id])[0]['file_name']
        img_path = os.path.join(self.img_prefix, file_name)
        
        #print(img_path)
        img = cv2.imread(img_path)
        img_shape = img.shape
        height, width = img.shape[0], img.shape[1]
        
        #scale = random.choice([0.6, 0.8, 1.0, 1.2, 1.4])
        scale = 1
        new_height = int(height * scale)
        new_width  = int(width * scale)
        
        fix_res = True
        if fix_res:
            input_h, input_w = self.img_scales[0][1], self.img_scales[0][0]
            c = np.array([new_width / 2., new_height / 2.], dtype=np.float32)
            s = max(height, width) * 1.0
        else:
            input_h = (new_height | self.size_divisor) + 1
            input_w = (new_width | self.size_divisor) + 1
            c = np.array([new_width // 2, new_height // 2], dtype=np.float32)
            s = np.array([input_w, input_h], dtype=np.float32)
        
        trans_input = get_affine_transform(c, s, 0, [input_w, input_h])
        resized_image = cv2.resize(img, (new_width, new_height))
        
        # 先变换到resized_image
        inp_image = cv2.warpAffine(resized_image, trans_input, 
                                   (input_w, input_h),
                                   flags=cv2.INTER_LINEAR)
        inp_image = (inp_image.astype(np.float32) / 255.)
        inp_image = (inp_image - self.img_norm_cfg['mean']) / self.img_norm_cfg['std']
        
        #images = inp_image.transpose(2, 0, 1).reshape(1, 3, input_w, input_h)
        images = inp_image.transpose(2, 0, 1).reshape(3, input_w, input_h)
        
        flip_test = False
        if flip_test:
            images = np.concatenate((images, images[:, :, :, ::-1]), axis=0)
            
        images = torch.from_numpy(images).type(torch.FloatTensor)
        
        meta = {} 
        meta['c'] = c
        meta['s'] = s
        # meta['scale_factor'] = scale_factor
        # meta['img_shape'] = img.shape
        meta['scale_factor'] = scale
        #meta['flip_test'] = flip_test
        
        ret = {'img': DC(images, stack=True), 'img_meta':DC(meta, cpu_only=True)}
        return ret 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data 

def prepare_test_img(self, idx):
        """Prepare an image for testing (multi-scale and flipping)"""
        img_info = self.img_infos[idx]
        img = mmcv.imread(osp.join(self.img_prefix, img_info['filename']))
        if self.proposals is not None:
            proposal = self.proposals[idx][:self.num_max_proposals]
            if not (proposal.shape[1] == 4 or proposal.shape[1] == 5):
                raise AssertionError(
                    'proposals should have shapes (n, 4) or (n, 5), '
                    'but found {}'.format(proposal.shape))
        else:
            proposal = None

        def prepare_single(img, scale, flip, proposal=None):
            _img, img_shape, pad_shape, scale_factor = self.img_transform(
                img, scale, flip, keep_ratio=self.resize_keep_ratio)
            _img = to_tensor(_img)
            _img_meta = dict(
                ori_shape=(img_info['height'], img_info['width'], 3),
                img_shape=img_shape,
                pad_shape=pad_shape,
                scale_factor=scale_factor,
                flip=flip)
            if proposal is not None:
                if proposal.shape[1] == 5:
                    score = proposal[:, 4, None]
                    proposal = proposal[:, :4]
                else:
                    score = None
                _proposal = self.bbox_transform(proposal, img_shape,
                                                scale_factor, flip)
                _proposal = np.hstack(
                    [_proposal, score]) if score is not None else _proposal
                _proposal = to_tensor(_proposal)
            else:
                _proposal = None
            return _img, _img_meta, _proposal

        imgs = []
        img_metas = []
        proposals = []
        for scale in self.img_scales:
            _img, _img_meta, _proposal = prepare_single(
                img, scale, False, proposal)
            imgs.append(_img)
            img_metas.append(DC(_img_meta, cpu_only=True))
            proposals.append(_proposal)
            if self.flip_ratio > 0:
                _img, _img_meta, _proposal = prepare_single(
                    img, scale, True, proposal)
                imgs.append(_img)
                img_metas.append(DC(_img_meta, cpu_only=True))
                proposals.append(_proposal)
        data = dict(img=imgs, img_meta=img_metas)
        if self.proposals is not None:
            data['proposals'] = proposals
        return data