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, True).squeeze(1)
resized_masks = (targets >= 0.5).cpu().numpy()
else:
resized_masks = []
return BitmapMasks(resized_masks, *out_shape)
def crop_and_resize(self,
bboxes,
out_shape,
inds,
device='cpu',
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:
ndarray: the cropped and resized masks.
"""
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, True).squeeze(1)
resized_masks = (targets >= 0.5).cpu().numpy()
else:
resized_masks = []
return BitmapMasks(resized_masks, *out_shape)