Merge pull request #1260 from roboflow/final-changes-before-supervision-0.21.0-release
final changes before `supervision-0.21.0`
This commit is contained in:
Piotr Skalski
GitHub
commit
6a199c5d7e
|
|
@ -1,3 +1,83 @@
|
|||
### 0.21.0 <small>Jun 5, 2024</small>
|
||||
|
||||
- Added [#500](https://github.com/roboflow/supervision/pull/500): [`sv.Detections.with_nmm`](https://supervision.roboflow.com/develop/detection/core/#supervision.detection.core.Detections.with_nmm) to perform non-maximum merging on the current set of object detections.
|
||||
|
||||
- Added [#1221](https://github.com/roboflow/supervision/pull/1221): [`sv.Detections.from_lmm`](https://supervision.roboflow.com/develop/detection/core/#supervision.detection.core.Detections.from_lmm) allowing to parse Large Multimodal Model (LMM) text result into [`sv.Detections`](https://supervision.roboflow.com/develop/detection/core/) object. For now `from_lmm` supports only [PaliGemma](https://colab.research.google.com/github/roboflow-ai/notebooks/blob/main/notebooks/how-to-finetune-paligemma-on-detection-dataset.ipynb) result parsing.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
paligemma_result = "<loc0256><loc0256><loc0768><loc0768> cat"
|
||||
detections = sv.Detections.from_lmm(
|
||||
sv.LMM.PALIGEMMA,
|
||||
paligemma_result,
|
||||
resolution_wh=(1000, 1000),
|
||||
classes=['cat', 'dog']
|
||||
)
|
||||
detections.xyxy
|
||||
# array([[250., 250., 750., 750.]])
|
||||
|
||||
detections.class_id
|
||||
# array([0])
|
||||
```
|
||||
|
||||
- Added [#1236](https://github.com/roboflow/supervision/pull/1236): [`sv.VertexLabelAnnotator`](https://supervision.roboflow.com/develop/keypoint/annotators/#supervision.keypoint.annotators.EdgeAnnotator.annotate) allowing to annotate every vertex of a keypoint skeleton with custom text and color.
|
||||
|
||||
```python
|
||||
import supervision as sv
|
||||
|
||||
image = ...
|
||||
key_points = sv.KeyPoints(...)
|
||||
|
||||
edge_annotator = sv.EdgeAnnotator(
|
||||
color=sv.Color.GREEN,
|
||||
thickness=5
|
||||
)
|
||||
annotated_frame = edge_annotator.annotate(
|
||||
scene=image.copy(),
|
||||
key_points=key_points
|
||||
)
|
||||
```
|
||||
|
||||
- Added [#1147](https://github.com/roboflow/supervision/pull/1147): [`sv.KeyPoints.from_inference`](https://supervision.roboflow.com/develop/keypoint/core/#supervision.keypoint.core.KeyPoints.from_inference) allowing to create [`sv.KeyPoints`](https://supervision.roboflow.com/develop/keypoint/core/#supervision.keypoint.core.KeyPoints) from [Inference](https://github.com/roboflow/inference) result.
|
||||
|
||||
- Added [#1138](https://github.com/roboflow/supervision/pull/1138): [`sv.KeyPoints.from_yolo_nas`](https://supervision.roboflow.com/develop/keypoint/core/#supervision.keypoint.core.KeyPoints.from_yolo_nas) allowing to create [`sv.KeyPoints`](https://supervision.roboflow.com/develop/keypoint/core/#supervision.keypoint.core.KeyPoints) from [YOLO-NAS](https://github.com/Deci-AI/super-gradients/blob/master/YOLONAS.md) result.
|
||||
|
||||
- Added [#1163](https://github.com/roboflow/supervision/pull/1163): [`sv.mask_to_rle`](https://supervision.roboflow.com/develop/datasets/utils/#supervision.dataset.utils.rle_to_mask) and [`sv.rle_to_mask`](https://supervision.roboflow.com/develop/datasets/utils/#supervision.dataset.utils.rle_to_mask) allowing for easy conversion between mask and rle formats.
|
||||
|
||||
- Changed [#1236](https://github.com/roboflow/supervision/pull/1236): [`sv.InferenceSlicer`](https://supervision.roboflow.com/develop/detection/tools/inference_slicer/) allowing to select overlap filtering strategy (`NONE`, `NON_MAX_SUPPRESSION` and `NON_MAX_MERGE`).
|
||||
|
||||
- Changed [#1178](https://github.com/roboflow/supervision/pull/1178): [`sv.InferenceSlicer`](https://supervision.roboflow.com/develop/detection/tools/inference_slicer/) adding instance segmentation model support.
|
||||
|
||||
```python
|
||||
import cv2
|
||||
import numpy as np
|
||||
import supervision as sv
|
||||
from inference import get_model
|
||||
|
||||
model = get_model(model_id="yolov8x-seg-640")
|
||||
image = cv2.imread(<SOURCE_IMAGE_PATH>)
|
||||
|
||||
def callback(image_slice: np.ndarray) -> sv.Detections:
|
||||
results = model.infer(image_slice)[0]
|
||||
return sv.Detections.from_inference(results)
|
||||
|
||||
slicer = sv.InferenceSlicer(callback = callback)
|
||||
detections = slicer(image)
|
||||
|
||||
mask_annotator = sv.MaskAnnotator()
|
||||
label_annotator = sv.LabelAnnotator()
|
||||
|
||||
annotated_image = mask_annotator.annotate(
|
||||
scene=image, detections=detections)
|
||||
annotated_image = label_annotator.annotate(
|
||||
scene=annotated_image, detections=detections)
|
||||
```
|
||||
|
||||
- Changed [#1228](https://github.com/roboflow/supervision/pull/1228): [`sv.LineZone`](https://supervision.roboflow.com/develop/detection/tools/line_zone/) making it 10-20 times faster, depending on the use case.
|
||||
|
||||
- Changed [#1163](https://github.com/roboflow/supervision/pull/1163): [`sv.DetectionDataset.from_coco`](https://supervision.roboflow.com/develop/datasets/core/#supervision.dataset.core.DetectionDataset.from_coco) and [`sv.DetectionDataset.as_coco`](https://supervision.roboflow.com/develop/datasets/core/#supervision.dataset.core.DetectionDataset.as_coco) adding support for run-length encoding (RLE) mask format.
|
||||
|
||||
### 0.20.0 <small>April 24, 2024</small>
|
||||
|
||||
- Added [#1128](https://github.com/roboflow/supervision/pull/1128): [`sv.KeyPoints`](/0.20.0/keypoint/core/#supervision.keypoint.core.KeyPoints) to provide initial support for pose estimation and broader keypoint detection models.
|
||||
|
|
|
|||
|
|
@ -35,15 +35,15 @@ extra_css:
|
|||
|
||||
|
||||
nav:
|
||||
- Home: index.md
|
||||
- How to:
|
||||
- Supervision: index.md
|
||||
- Learn:
|
||||
- Detect and Annotate: how_to/detect_and_annotate.md
|
||||
- Save Detections: how_to/save_detections.md
|
||||
- Filter Detections: how_to/filter_detections.md
|
||||
- Detect Small Objects: how_to/detect_small_objects.md
|
||||
- Track Objects on Video: how_to/track_objects.md
|
||||
|
||||
- API:
|
||||
- Reference - Code API:
|
||||
- Detection and Segmentation:
|
||||
- Core: detection/core.md
|
||||
- Annotators: detection/annotators.md
|
||||
|
|
@ -79,7 +79,7 @@ nav:
|
|||
- Contributing: contributing.md
|
||||
- Code of Conduct: code_of_conduct.md
|
||||
- License: license.md
|
||||
- Changelog:
|
||||
- Release Notes:
|
||||
- Changelog: changelog.md
|
||||
- Deprecated: deprecated.md
|
||||
|
||||
|
|
|
|||
|
|
@ -1,6 +1,6 @@
|
|||
[tool.poetry]
|
||||
name = "supervision"
|
||||
version = "0.21.0rc5"
|
||||
version = "0.21.0"
|
||||
description = "A set of easy-to-use utils that will come in handy in any Computer Vision project"
|
||||
authors = ["Piotr Skalski <piotr.skalski92@gmail.com>"]
|
||||
maintainers = ["Piotr Skalski <piotr.skalski92@gmail.com>"]
|
||||
|
|
|
|||
|
|
@ -1239,7 +1239,9 @@ class Detections:
|
|||
Raises:
|
||||
AssertionError: If `confidence` is None or `class_id` is None and
|
||||
class_agnostic is False.
|
||||
"""
|
||||
|
||||
{ align=center width="800" }
|
||||
""" # noqa: E501 // docs
|
||||
if len(self) == 0:
|
||||
return self
|
||||
|
||||
|
|
|
|||
|
|
@ -41,7 +41,7 @@ def from_paligemma(
|
|||
) -> Tuple[np.ndarray, Optional[np.ndarray], np.ndarray]:
|
||||
w, h = resolution_wh
|
||||
pattern = re.compile(
|
||||
r"(?<!<loc\d{4}>)<loc(\d{4})><loc(\d{4})><loc(\d{4})><loc(\d{4})> ([\w\s]+)"
|
||||
r"(?<!<loc\d{4}>)<loc(\d{4})><loc(\d{4})><loc(\d{4})><loc(\d{4})> ([\w\s\-]+)"
|
||||
)
|
||||
matches = pattern.findall(result)
|
||||
matches = np.array(matches) if matches else np.empty((0, 5))
|
||||
|
|
|
|||
|
|
@ -155,6 +155,25 @@ def clip_boxes(xyxy: np.ndarray, resolution_wh: Tuple[int, int]) -> np.ndarray:
|
|||
np.ndarray: A numpy array of shape `(N, 4)` where each row
|
||||
corresponds to a bounding box with coordinates clipped to fit
|
||||
within the frame resolution.
|
||||
|
||||
Examples:
|
||||
```python
|
||||
import numpy as np
|
||||
import supervision as sv
|
||||
|
||||
xyxy = np.array([
|
||||
[10, 20, 300, 200],
|
||||
[15, 25, 350, 450],
|
||||
[-10, -20, 30, 40]
|
||||
])
|
||||
|
||||
sv.clip_boxes(xyxy=xyxy, resolution_wh=(320, 240))
|
||||
# array([
|
||||
# [ 10, 20, 300, 200],
|
||||
# [ 15, 25, 320, 240],
|
||||
# [ 0, 0, 30, 40]
|
||||
# ])
|
||||
```
|
||||
"""
|
||||
result = np.copy(xyxy)
|
||||
width, height = resolution_wh
|
||||
|
|
@ -181,6 +200,23 @@ def pad_boxes(xyxy: np.ndarray, px: int, py: Optional[int] = None) -> np.ndarray
|
|||
np.ndarray: A numpy array of shape `(N, 4)` where each row corresponds to a
|
||||
bounding box with coordinates padded according to the provided padding
|
||||
values.
|
||||
|
||||
Examples:
|
||||
```python
|
||||
import numpy as np
|
||||
import supervision as sv
|
||||
|
||||
xyxy = np.array([
|
||||
[10, 20, 30, 40],
|
||||
[15, 25, 35, 45]
|
||||
])
|
||||
|
||||
sv.pad_boxes(xyxy=xyxy, px=5, py=10)
|
||||
# array([
|
||||
# [ 5, 10, 35, 50],
|
||||
# [10, 15, 40, 55]
|
||||
# ])
|
||||
```
|
||||
"""
|
||||
if py is None:
|
||||
py = px
|
||||
|
|
@ -553,7 +589,7 @@ def scale_boxes(
|
|||
[30, 30, 40, 40]
|
||||
])
|
||||
|
||||
scaled_bb = sv.scale_boxes(xyxy=xyxy, factor=1.5)
|
||||
sv.scale_boxes(xyxy=xyxy, factor=1.5)
|
||||
# array([
|
||||
# [ 7.5, 7.5, 22.5, 22.5],
|
||||
# [27.5, 27.5, 42.5, 42.5]
|
||||
|
|
|
|||
|
|
@ -76,7 +76,27 @@ from supervision.detection.lmm import from_paligemma
|
|||
None,
|
||||
np.array(["black cat"]).astype(np.dtype("U")),
|
||||
),
|
||||
), # correct response; no classes
|
||||
), # correct response; class name with space; no classes
|
||||
(
|
||||
"<loc0256><loc0256><loc0768><loc0768> black-cat",
|
||||
(1000, 1000),
|
||||
None,
|
||||
(
|
||||
np.array([[250.0, 250.0, 750.0, 750.0]]),
|
||||
None,
|
||||
np.array(["black-cat"]).astype(np.dtype("U")),
|
||||
),
|
||||
), # correct response; class name with hyphen; no classes
|
||||
(
|
||||
"<loc0256><loc0256><loc0768><loc0768> black_cat",
|
||||
(1000, 1000),
|
||||
None,
|
||||
(
|
||||
np.array([[250.0, 250.0, 750.0, 750.0]]),
|
||||
None,
|
||||
np.array(["black_cat"]).astype(np.dtype("U")),
|
||||
),
|
||||
), # correct response; class name with underscore; no classes
|
||||
(
|
||||
"<loc0256><loc0256><loc0768><loc0768> cat ;",
|
||||
(1000, 1000),
|
||||
|
|
|
|||
Loading…
Reference in New Issue