Python mmcv.imresize方法代码示例

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def _resize_img(self, results):
        """Resize images with ``results['scale']``."""
        for key in results.get('img_fields', ['img']):
            if self.keep_ratio:
                img, scale_factor = mmcv.imrescale(
                    results[key], results['scale'], return_scale=True)
                # the w_scale and h_scale has minor difference
                # a real fix should be done in the mmcv.imrescale in the future
                new_h, new_w = img.shape[:2]
                h, w = results[key].shape[:2]
                w_scale = new_w / w
                h_scale = new_h / h
            else:
                img, w_scale, h_scale = mmcv.imresize(
                    results[key], results['scale'], return_scale=True)
            results[key] = img

            scale_factor = np.array([w_scale, h_scale, w_scale, h_scale],
                                    dtype=np.float32)
            results['img_shape'] = img.shape
            # in case that there is no padding
            results['pad_shape'] = img.shape
            results['scale_factor'] = scale_factor
            results['keep_ratio'] = self.keep_ratio 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
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 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def __call__(self, img, scale, flip=False, keep_ratio=True):
        if keep_ratio:
            img, scale_factor = mmcv.imrescale(img, scale, return_scale=True)
        else:
            img, w_scale, h_scale = mmcv.imresize(
                img, scale, return_scale=True)
            scale_factor = np.array(
                [w_scale, h_scale, w_scale, h_scale], dtype=np.float32)
        img_shape = img.shape
        img = mmcv.imnormalize(img, self.mean, self.std, self.to_rgb)
        if flip:
            img = mmcv.imflip(img)
        if self.size_divisor is not None:
            img = mmcv.impad_to_multiple(img, self.size_divisor)
            pad_shape = img.shape
        else:
            pad_shape = img_shape
        img = img.transpose(2, 0, 1)
        return img, img_shape, pad_shape, scale_factor 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def mask_target_single(pos_proposals, pos_assigned_gt_inds, gt_masks, cfg):
    mask_size = cfg.mask_size
    num_pos = pos_proposals.size(0)
    mask_targets = []
    if num_pos > 0:
        proposals_np = pos_proposals.cpu().numpy()
        pos_assigned_gt_inds = pos_assigned_gt_inds.cpu().numpy()
        for i in range(num_pos):
            # import pdb
            # pdb.set_trace()
            gt_mask = gt_masks[pos_assigned_gt_inds[i]]
            bbox = proposals_np[i, :].astype(np.int32)
            x1, y1, x2, y2 = bbox
            w = np.maximum(x2 - x1 + 1, 1)
            h = np.maximum(y2 - y1 + 1, 1)
            # mask is uint8 both before and after resizing
            target = mmcv.imresize(gt_mask[y1:y1 + h, x1:x1 + w],
                                   (mask_size, mask_size))
            mask_targets.append(target)
        mask_targets = torch.from_numpy(np.stack(mask_targets)).float().to(
            pos_proposals.device)
    else:
        mask_targets = pos_proposals.new_zeros((0, mask_size, mask_size))
    return mask_targets 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def mask_target_single(pos_proposals, pos_assigned_gt_inds, gt_masks, cfg):
    mask_size = cfg.mask_size
    num_pos = pos_proposals.size(0)
    mask_targets = []
    if num_pos > 0:
        proposals_np = pos_proposals.cpu().numpy()
        pos_assigned_gt_inds = pos_assigned_gt_inds.cpu().numpy()
        for i in range(num_pos):
            gt_mask = gt_masks[pos_assigned_gt_inds[i]]
            bbox = proposals_np[i, :].astype(np.int32)
            x1, y1, x2, y2 = bbox
            w = np.maximum(x2 - x1 + 1, 1)
            h = np.maximum(y2 - y1 + 1, 1)
            # mask is uint8 both before and after resizing
            target = mmcv.imresize(gt_mask[y1:y1 + h, x1:x1 + w],
                                   (mask_size, mask_size))
            mask_targets.append(target)
        mask_targets = torch.from_numpy(np.stack(mask_targets)).float().to(
            pos_proposals.device)
    else:
        mask_targets = pos_proposals.new_zeros((0, mask_size, mask_size))
    return mask_targets 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def test_imresize(self):
        resized_img = mmcv.imresize(self.img, (1000, 600))
        assert resized_img.shape == (600, 1000, 3)
        resized_img, w_scale, h_scale = mmcv.imresize(self.img, (1000, 600),
                                                      True)
        assert (resized_img.shape == (600, 1000, 3) and w_scale == 2.5
                and h_scale == 2.0)
        resized_img_dst = np.empty((600, 1000, 3), dtype=self.img.dtype)
        resized_img = mmcv.imresize(self.img, (1000, 600), out=resized_img_dst)
        assert id(resized_img_dst) == id(resized_img)
        assert_array_equal(resized_img_dst,
                           mmcv.imresize(self.img, (1000, 600)))
        for mode in ['nearest', 'bilinear', 'bicubic', 'area', 'lanczos']:
            resized_img = mmcv.imresize(
                self.img, (1000, 600), interpolation=mode)
            assert resized_img.shape == (600, 1000, 3) 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def __call__(self, img, scale, flip=False, keep_ratio=True):
        if keep_ratio:
            img, scale_factor = mmcv.imrescale(img, scale, return_scale=True)
        else:
            img, w_scale, h_scale = mmcv.imresize(
                img, scale, return_scale=True)
            scale_factor = np.array([w_scale, h_scale, w_scale, h_scale],
                                    dtype=np.float32)
        img_shape = img.shape
        img = mmcv.imnormalize(img, self.mean, self.std, self.to_rgb)
        if flip:
            img = mmcv.imflip(img)
        if self.size_divisor is not None:
            img = mmcv.impad_to_multiple(img, self.size_divisor)
            pad_shape = img.shape
        else:
            pad_shape = img_shape
        img = img.transpose(2, 0, 1)
        return img, img_shape, pad_shape, scale_factor 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def mask_target_single(pos_proposals, pos_assigned_gt_inds, gt_masks, cfg):
    mask_size = _pair(cfg.mask_size)
    num_pos = pos_proposals.size(0)
    mask_targets = []
    if num_pos > 0:
        proposals_np = pos_proposals.cpu().numpy()
        pos_assigned_gt_inds = pos_assigned_gt_inds.cpu().numpy()
        for i in range(num_pos):
            gt_mask = gt_masks[pos_assigned_gt_inds[i]]
            bbox = proposals_np[i, :].astype(np.int32)
            x1, y1, x2, y2 = bbox
            w = np.maximum(x2 - x1 + 1, 1)
            h = np.maximum(y2 - y1 + 1, 1)
            # mask is uint8 both before and after resizing
            # mask_size (h, w) to (w, h)
            target = mmcv.imresize(gt_mask[y1:y1 + h, x1:x1 + w],
                                   mask_size[::-1])
            mask_targets.append(target)
        mask_targets = torch.from_numpy(np.stack(mask_targets)).float().to(
            pos_proposals.device)
    else:
        mask_targets = pos_proposals.new_zeros((0, ) + mask_size)
    return mask_targets 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def __call__(self, results):
        if results['keep_ratio']:
            gt_seg = mmcv.imrescale(
                results['gt_semantic_seg'],
                results['scale'],
                interpolation='nearest')
        else:
            gt_seg = mmcv.imresize(
                results['gt_semantic_seg'],
                results['scale'],
                interpolation='nearest')
        if results['flip']:
            gt_seg = mmcv.imflip(gt_seg)
        if gt_seg.shape != results['pad_shape']:
            gt_seg = mmcv.impad(gt_seg, results['pad_shape'][:2])
        if self.scale_factor != 1:
            gt_seg = mmcv.imrescale(
                gt_seg, self.scale_factor, interpolation='nearest')
        results['gt_semantic_seg'] = gt_seg
        return results 

# 需要导入模块: import mmcv [as 别名]
# 或者: from mmcv import imresize [as 别名]
def _resize_masks(self, results):
        for key in results.get('mask_fields', []):
            if results[key] is None:
                continue
            if self.keep_ratio:
                masks = [
                    mmcv.imrescale(
                        mask, results['scale_factor'], interpolation='nearest')
                    for mask in results[key]
                ]
            else:
                mask_size = (results['img_shape'][1], results['img_shape'][0])
                masks = [
                    mmcv.imresize(mask, mask_size, interpolation='nearest')
                    for mask in results[key]
                ]
            results[key] = masks