mmcv.ops.pixel_group¶
- mmcv.ops.pixel_group(score: Union[numpy.ndarray, torch.Tensor], mask: Union[numpy.ndarray, torch.Tensor], embedding: Union[numpy.ndarray, torch.Tensor], kernel_label: Union[numpy.ndarray, torch.Tensor], kernel_contour: Union[numpy.ndarray, torch.Tensor], kernel_region_num: int, distance_threshold: float) → List[List[float]][source]¶
Group pixels into text instances, which is widely used text detection methods.
- Parameters
score (np.array or torch.Tensor) – The foreground score with size hxw.
mask (np.array or Tensor) – The foreground mask with size hxw.
embedding (np.array or torch.Tensor) – The embedding with size hxwxc to distinguish instances.
kernel_label (np.array or torch.Tensor) – The instance kernel index with size hxw.
kernel_contour (np.array or torch.Tensor) – The kernel contour with size hxw.
kernel_region_num (int) – The instance kernel region number.
distance_threshold (float) – The embedding distance threshold between kernel and pixel in one instance.
- Returns
The instance coordinates and attributes list. Each element consists of averaged confidence, pixel number, and coordinates (x_i, y_i for all pixels) in order.
- Return type