refactor(inference_slicer): Update class and method docstrings
This commit is contained in:
SkalskiP
parent
07c4472eac
commit
bddd32dbb5
|
|
@ -0,0 +1,3 @@
|
|||
## InferenceSlicer
|
||||
|
||||
:::supervision.detection.tools.inference_slicer.InferenceSlicer
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
## InferenceSlicer
|
||||
|
||||
:::supervision.detection.tools.slicer.InferenceSlicer
|
||||
|
|
@ -4,4 +4,4 @@
|
|||
|
||||
## crop
|
||||
|
||||
:::supervision.utils.image.crop
|
||||
:::supervision.utils.image.crop_image
|
||||
|
|
|
|||
|
|
@ -37,6 +37,7 @@ nav:
|
|||
- Utils: detection/utils.md
|
||||
- Tools:
|
||||
- Polygon Zone: detection/tools/polygon_zone.md
|
||||
- Inference Slicer: detection/tools/inference_slicer.md
|
||||
- Trackers:
|
||||
- Core: tracker/core.md
|
||||
- Dataset:
|
||||
|
|
|
|||
|
|
@ -16,8 +16,8 @@ from supervision.dataset.core import (
|
|||
from supervision.detection.annotate import BoxAnnotator, MaskAnnotator
|
||||
from supervision.detection.core import Detections
|
||||
from supervision.detection.line_counter import LineZone, LineZoneAnnotator
|
||||
from supervision.detection.tools.inference_slicer import InferenceSlicer
|
||||
from supervision.detection.tools.polygon_zone import PolygonZone, PolygonZoneAnnotator
|
||||
from supervision.detection.tools.slicer import InferenceSlicer
|
||||
from supervision.detection.utils import (
|
||||
box_iou_batch,
|
||||
filter_polygons_by_area,
|
||||
|
|
|
|||
|
|
@ -11,7 +11,8 @@ def move_detections(detections: Detections, offset: np.array) -> Detections:
|
|||
"""
|
||||
Args:
|
||||
detections (sv.Detections): Detections object to be moved.
|
||||
offset (np.array): An array of shape `(2,)` containing offset values in format is `[dx, dy]`.
|
||||
offset (np.array): An array of shape `(2,)` containing offset values in format
|
||||
is `[dx, dy]`.
|
||||
Returns:
|
||||
(sv.Detections) repositioned Detections object.
|
||||
"""
|
||||
|
|
@ -21,7 +22,26 @@ def move_detections(detections: Detections, offset: np.array) -> Detections:
|
|||
|
||||
class InferenceSlicer:
|
||||
"""
|
||||
Slicing inference(SAHI) method for small target detection.
|
||||
InferenceSlicer performs slicing-based inference for small target detection. This
|
||||
method, often referred to as Slicing Adaptive Inference (SAHI), involves dividing a
|
||||
larger image into smaller slices, performing inference on each slice, and then
|
||||
merging the detections.
|
||||
|
||||
Attributes:
|
||||
slice_wh (Tuple[int, int]): Dimensions of each slice in the format
|
||||
`(width, height)`.
|
||||
overlap_ratio_wh (Tuple[float, float]): Overlap ratio between consecutive
|
||||
slices in the format `(width_ratio, height_ratio)`.
|
||||
iou_threshold (Optional[float]): Intersection over Union (IoU) threshold used
|
||||
for non-max suppression.
|
||||
callback (Callable): A function that performs inference on a given image slice
|
||||
and returns detections.
|
||||
|
||||
Note:
|
||||
The class ensures that slices do not exceed the boundaries of the original
|
||||
image. As a result, the final slices in the row and column dimensions might be
|
||||
smaller than the specified slice dimensions if the image's width or height is
|
||||
not a multiple of the slice's width or height minus the overlap.
|
||||
"""
|
||||
|
||||
def __init__(
|
||||
|
|
@ -38,6 +58,37 @@ class InferenceSlicer:
|
|||
validate_inference_callback(callback=callback)
|
||||
|
||||
def __call__(self, image: np.ndarray) -> Detections:
|
||||
"""
|
||||
Performs slicing-based inference on the provided image using the specified
|
||||
callback.
|
||||
|
||||
Args:
|
||||
image (np.ndarray): The input image on which inference needs to be
|
||||
performed. The image should be in the format
|
||||
`(height, width, channels)`.
|
||||
|
||||
Returns:
|
||||
Detections: A collection of detections for the entire image after merging
|
||||
results from all slices and applying NMS.
|
||||
|
||||
Example:
|
||||
```python
|
||||
>>> import cv2
|
||||
>>> import supervision as sv
|
||||
>>> from ultralytics import YOLO
|
||||
|
||||
>>> image = cv2.imread(SOURCE_IMAGE_PATH)
|
||||
>>> model = YOLO(...)
|
||||
|
||||
>>> def callback(image_slice: np.ndarray) -> sv.Detections:
|
||||
... result = model(image_slice)[0]
|
||||
... return sv.Detections.from_ultralytics(result)
|
||||
|
||||
>>> slicer = sv.InferenceSlicer(callback = callback)
|
||||
|
||||
>>> detections = slicer(image)
|
||||
```
|
||||
"""
|
||||
detections_list = []
|
||||
resolution_wh = (image.shape[1], image.shape[0])
|
||||
offsets = self._generate_offset(
|
||||
|
|
@ -62,18 +113,29 @@ class InferenceSlicer:
|
|||
overlap_ratio_wh: Tuple[float, float],
|
||||
) -> np.ndarray:
|
||||
"""
|
||||
Generate offset coordinates for slicing an image based on the given resolution, slice dimensions, and overlap ratios.
|
||||
Generate offset coordinates for slicing an image based on the given resolution,
|
||||
slice dimensions, and overlap ratios.
|
||||
|
||||
Args:
|
||||
resolution_wh (Tuple[int, int]): A tuple representing the width and height of the image to be sliced.
|
||||
slice_wh (Tuple[int, int]): A tuple representing the desired width and height of each slice.
|
||||
overlap_ratio_wh (Tuple[float, float]): A tuple representing the desired overlap ratio for width and height between consecutive slices. Each value should be in the range [0, 1), where 0 means no overlap and a value close to 1 means high overlap.
|
||||
resolution_wh (Tuple[int, int]): A tuple representing the width and height
|
||||
of the image to be sliced.
|
||||
slice_wh (Tuple[int, int]): A tuple representing the desired width and
|
||||
height of each slice.
|
||||
overlap_ratio_wh (Tuple[float, float]): A tuple representing the desired
|
||||
overlap ratio for width and height between consecutive slices. Each
|
||||
value should be in the range [0, 1), where 0 means no overlap and a
|
||||
value close to 1 means high overlap.
|
||||
|
||||
Returns:
|
||||
np.ndarray: An array of shape `(n, 4)` containing coordinates for each slice in the format `[xmin, ymin, xmax, ymax]`.
|
||||
np.ndarray: An array of shape `(n, 4)` containing coordinates for each
|
||||
slice in the format `[xmin, ymin, xmax, ymax]`.
|
||||
|
||||
Note:
|
||||
The function ensures that slices do not exceed the boundaries of the original image. As a result, the final slices in the row and column dimensions might be smaller than the specified slice dimensions if the image's width or height is not a multiple of the slice's width or height minus the overlap.
|
||||
The function ensures that slices do not exceed the boundaries of the
|
||||
original image. As a result, the final slices in the row and column
|
||||
dimensions might be smaller than the specified slice dimensions if the
|
||||
image's width or height is not a multiple of the slice's width or
|
||||
height minus the overlap.
|
||||
"""
|
||||
slice_width, slice_height = slice_wh
|
||||
image_width, image_height = resolution_wh
|
||||
|
|
@ -380,9 +380,10 @@ def process_roboflow_result(
|
|||
def move_boxes(xyxy: np.ndarray, offset: np.ndarray) -> np.ndarray:
|
||||
"""
|
||||
Args:
|
||||
xyxy (np.ndarray): An array of shape `(n, 4)` containing the bounding boxes coordinates in format
|
||||
`[x1, y1, x2, y2]`
|
||||
offset (np.array): An array of shape `(2,)` containing offset values in format is `[dx, dy]`.
|
||||
xyxy (np.ndarray): An array of shape `(n, 4)` containing the bounding boxes
|
||||
coordinates in format `[x1, y1, x2, y2]`
|
||||
offset (np.array): An array of shape `(2,)` containing offset values in format
|
||||
is `[dx, dy]`.
|
||||
|
||||
Returns:
|
||||
(np.ndarray) repositioned bounding boxes
|
||||
|
|
|
|||
Loading…
Reference in New Issue