add box non_max_suppression

docs/source/data.rst

@@ -314,37 +314,5 @@ PatchWSIDataset
 
 Bounding box
 ------------
-
-Box mode
-~~~~~~~~
-.. autoclass:: monai.data.box_utils.BoxMode
+.. automodule:: monai.data.box_utils
     :members:
-.. autoclass:: monai.data.box_utils.CornerCornerModeTypeA
-.. autoclass:: monai.data.box_utils.CornerCornerModeTypeB
-.. autoclass:: monai.data.box_utils.CornerCornerModeTypeC
-.. autoclass:: monai.data.box_utils.CornerSizeMode
-.. autoclass:: monai.data.box_utils.CenterSizeMode
-
-Box mode converter
-~~~~~~~~~~~~~~~~~~
-.. autofunction:: monai.data.box_utils.get_boxmode
-.. autofunction:: monai.data.box_utils.convert_box_mode
-.. autofunction:: monai.data.box_utils.convert_box_to_standard_mode
-
-Box IoU
-~~~~~~~
-.. autofunction:: monai.data.box_utils.box_area
-.. autofunction:: monai.data.box_utils.box_iou
-.. autofunction:: monai.data.box_utils.box_giou
-.. autofunction:: monai.data.box_utils.box_pair_giou
-
-Box center
-~~~~~~~~~~
-.. autofunction:: monai.data.box_utils.box_centers
-.. autofunction:: monai.data.box_utils.centers_in_boxes
-.. autofunction:: monai.data.box_utils.boxes_center_distance
-
-Spatial crop box
-~~~~~~~~~~~~~~~~
-.. autofunction:: monai.data.box_utils.spatial_crop_boxes
-.. autofunction:: monai.data.box_utils.clip_boxes_to_image

monai/apps/detection/transforms/array.py

@@ -138,7 +138,7 @@ def __call__(self, boxes: NdarrayOrTensor) -> NdarrayOrTensor:
 
 class AffineBox(Transform):
     """
-    Applys affine matrix to the boxes
+    Applies affine matrix to the boxes
     """
 
     backend = [TransformBackends.TORCH, TransformBackends.NUMPY]
@@ -147,7 +147,7 @@ def __call__(self, boxes: NdarrayOrTensor, affine: Union[NdarrayOrTensor, None])
         """
         Args:
             boxes: source bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is assumed to be ``StandardMode``
-            affine: affine matric to be applied to the box coordinate
+            affine: affine matrix to be applied to the box coordinate
         """
         if affine is None:
             return boxes

monai/apps/detection/transforms/box_ops.py

@@ -15,15 +15,15 @@
 import torch
 
 from monai.config.type_definitions import NdarrayOrTensor
-from monai.data.box_utils import TO_REMOVE, get_spatial_dims
+from monai.data.box_utils import COMPUTE_DTYPE, TO_REMOVE, get_spatial_dims
 from monai.transforms.utils import create_scale
 from monai.utils.misc import ensure_tuple, ensure_tuple_rep
 from monai.utils.type_conversion import convert_data_type, convert_to_dst_type
 
 
 def _apply_affine_to_points(points: torch.Tensor, affine: torch.Tensor, include_shift: bool = True) -> torch.Tensor:
     """
-    This internal function applies affine matrixs to the point coordinate
+    This internal function applies affine matrices to the point coordinate
 
     Args:
         points: point coordinates, Nx2 or Nx3 torch tensor or ndarray, representing [x, y] or [x, y, z]
@@ -56,7 +56,7 @@ def _apply_affine_to_points(points: torch.Tensor, affine: torch.Tensor, include_
 
 def apply_affine_to_boxes(boxes: NdarrayOrTensor, affine: NdarrayOrTensor) -> NdarrayOrTensor:
     """
-    This function applies affine matrixs to the boxes
+    This function applies affine matrices to the boxes
 
     Args:
         boxes: bounding boxes, Nx4 or Nx6 torch tensor or ndarray. The box mode is assumed to be StandardMode
@@ -71,9 +71,8 @@ def apply_affine_to_boxes(boxes: NdarrayOrTensor, affine: NdarrayOrTensor) -> Nd
 
     # some operation does not support torch.float16
     # convert to float32
-    compute_dtype = torch.float32
 
-    boxes_t = boxes_t.to(dtype=compute_dtype)
+    boxes_t = boxes_t.to(dtype=COMPUTE_DTYPE)
     affine_t, *_ = convert_to_dst_type(src=affine, dst=boxes_t)
 
     spatial_dims = get_spatial_dims(boxes=boxes_t)

monai/apps/detection/transforms/dictionary.py

@@ -176,20 +176,20 @@ def inverse(self, data: Mapping[Hashable, NdarrayOrTensor]) -> Dict[Hashable, Nd
 
 class AffineBoxToImageCoordinated(MapTransform, InvertibleTransform):
     """
-    Dictionary-based transfrom that converts box in world coordinate to image coordinate.
+    Dictionary-based transform that converts box in world coordinate to image coordinate.
 
     Args:
         box_keys: Keys to pick box data for transformation. The box mode is assumed to be ``StandardMode``.
         box_ref_image_keys: The single key that represents the reference image to which ``box_keys`` are attached.
         remove_empty: whether to remove the boxes that are actually empty
         allow_missing_keys: don't raise exception if key is missing.
-        image_meta_key: explicitly indicate the key of the corresponding meta data dictionary.
+        image_meta_key: explicitly indicate the key of the corresponding metadata dictionary.
             for example, for data with key `image`, the metadata by default is in `image_meta_dict`.
-            the meta data is a dictionary object which contains: filename, affine, original_shape, etc.
+            the metadata is a dictionary object which contains: filename, affine, original_shape, etc.
             it is a string, map to the `box_ref_image_key`.
             if None, will try to construct meta_keys by `box_ref_image_key_{meta_key_postfix}`.
-        image_meta_key_postfix: if image_meta_keys=None, use `box_ref_image_key_{postfix}` to fetch the meta data according
-            to the key data, default is `meta_dict`, the meta data is a dictionary object.
+        image_meta_key_postfix: if image_meta_keys=None, use `box_ref_image_key_{postfix}` to fetch the metadata according
+            to the key data, default is `meta_dict`, the metadata is a dictionary object.
             For example, to handle key `image`,  read/write affine matrices from the
             metadata `image_meta_dict` dictionary's `affine` field.
         affine_lps_to_ras: default ``False``. Yet if 1) the image is read by ITKReader,
@@ -255,7 +255,7 @@ def inverse(self, data: Mapping[Hashable, NdarrayOrTensor]) -> Dict[Hashable, Nd
 
 class ZoomBoxd(MapTransform, InvertibleTransform):
     """
-    Dictionary-based transfrom that zooms input boxes and images with the given zoom scale.
+    Dictionary-based transform that zooms input boxes and images with the given zoom scale.
 
     Args:
         image_keys: Keys to pick image data for transformation.
@@ -384,7 +384,7 @@ def inverse(self, data: Mapping[Hashable, NdarrayOrTensor]) -> Dict[Hashable, Nd
 
 class RandZoomBoxd(RandomizableTransform, MapTransform, InvertibleTransform):
     """
-    Dictionary-based transfrom that randomly zooms input boxes and images with given probability within given zoom range.
+    Dictionary-based transform that randomly zooms input boxes and images with given probability within given zoom range.
 
     Args:
         image_keys: Keys to pick image data for transformation.
@@ -547,7 +547,7 @@ def inverse(self, data: Mapping[Hashable, NdarrayOrTensor]) -> Dict[Hashable, Nd
 
 class FlipBoxd(MapTransform, InvertibleTransform):
     """
-    Dictionary-based transfrom that flip boxes and images.
+    Dictionary-based transform that flip boxes and images.
 
     Args:
         image_keys: Keys to pick image data for transformation.
@@ -611,7 +611,7 @@ def inverse(self, data: Mapping[Hashable, NdarrayOrTensor]) -> Dict[Hashable, Nd
 
 class RandFlipBoxd(RandomizableTransform, MapTransform, InvertibleTransform):
     """
-    Dictionary-based transfrom that randomly flip boxes and images with the given probabilities.
+    Dictionary-based transform that randomly flip boxes and images with the given probabilities.
 
     Args:
         image_keys: Keys to pick image data for transformation.