xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-23 05:24:22 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

ultralytics 8.1.12 new Results.show() and Results.save() (#8166)

Browse Source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher 2024-02-13 02:35:22 +01:00 committed by GitHub
parent ebf65075dd
commit 52604084de
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
3 changed files with 107 additions and 47 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
ultralytics/__init__.py
View File

@ -1,6 +1,6 @@
# Ultralytics YOLO 🚀, AGPL-3.0 license
__version__ = "8.1.11"
__version__ = "8.1.12"
from ultralytics.data.explorer.explorer import Explorer
from ultralytics.models import RTDETR, SAM, YOLO

130
ultralytics/engine/results.py
View File

@ -67,30 +67,45 @@ class Results(SimpleClass):
"""
A class for storing and manipulating inference results.
Args:
orig_img (numpy.ndarray): The original image as a numpy array.
path (str): The path to the image file.
names (dict): A dictionary of class names.
boxes (torch.tensor, optional): A 2D tensor of bounding box coordinates for each detection.
masks (torch.tensor, optional): A 3D tensor of detection masks, where each mask is a binary image.
probs (torch.tensor, optional): A 1D tensor of probabilities of each class for classification task.
keypoints (List[List[float]], optional): A list of detected keypoints for each object.
Attributes:
orig_img (numpy.ndarray): The original image as a numpy array.
orig_shape (tuple): The original image shape in (height, width) format.
boxes (Boxes, optional): A Boxes object containing the detection bounding boxes.
masks (Masks, optional): A Masks object containing the detection masks.
probs (Probs, optional): A Probs object containing probabilities of each class for classification task.
keypoints (Keypoints, optional): A Keypoints object containing detected keypoints for each object.
speed (dict): A dictionary of preprocess, inference, and postprocess speeds in milliseconds per image.
names (dict): A dictionary of class names.
path (str): The path to the image file.
_keys (tuple): A tuple of attribute names for non-empty attributes.
orig_img (numpy.ndarray): Original image as a numpy array.
orig_shape (tuple): Original image shape in (height, width) format.
boxes (Boxes, optional): Object containing detection bounding boxes.
masks (Masks, optional): Object containing detection masks.
probs (Probs, optional): Object containing class probabilities for classification tasks.
keypoints (Keypoints, optional): Object containing detected keypoints for each object.
speed (dict): Dictionary of preprocess, inference, and postprocess speeds (ms/image).
names (dict): Dictionary of class names.
path (str): Path to the image file.
Methods:
update(boxes=None, masks=None, probs=None, obb=None): Updates object attributes with new detection results.
cpu(): Returns a copy of the Results object with all tensors on CPU memory.
numpy(): Returns a copy of the Results object with all tensors as numpy arrays.
cuda(): Returns a copy of the Results object with all tensors on GPU memory.
to(*args, **kwargs): Returns a copy of the Results object with tensors on a specified device and dtype.
new(): Returns a new Results object with the same image, path, and names.
plot(...): Plots detection results on an input image, returning an annotated image.
verbose(): Returns a log string for each task, detailing detections and classifications.
save_txt(txt_file, save_conf=False): Saves detection results to a text file.
save_crop(save_dir, file_name=Path("im.jpg")): Saves cropped detection images.
tojson(normalize=False): Converts detection results to JSON format.
"""
def __init__(self, orig_img, path, names, boxes=None, masks=None, probs=None, keypoints=None, obb=None) -> None:
"""Initialize the Results class."""
"""
Initialize the Results class.
Args:
orig_img (numpy.ndarray): The original image as a numpy array.
path (str): The path to the image file.
names (dict): A dictionary of class names.
boxes (torch.tensor, optional): A 2D tensor of bounding box coordinates for each detection.
masks (torch.tensor, optional): A 3D tensor of detection masks, where each mask is a binary image.
probs (torch.tensor, optional): A 1D tensor of probabilities of each class for classification task.
keypoints (torch.tensor, optional): A 2D tensor of keypoint coordinates for each detection.
obb (torch.tensor, optional): A 2D tensor of oriented bounding box coordinates for each detection.
"""
self.orig_img = orig_img
self.orig_shape = orig_img.shape[:2]
self.boxes = Boxes(boxes, self.orig_shape) if boxes is not None else None # native size boxes
@ -181,6 +196,9 @@ class Results(SimpleClass):
boxes=True,
masks=True,
probs=True,
show=False,
save=False,
filename=None,
):
"""
Plots the detection results on an input RGB image. Accepts a numpy array (cv2) or a PIL Image.
@ -199,6 +217,9 @@ class Results(SimpleClass):
boxes (bool): Whether to plot the bounding boxes.
masks (bool): Whether to plot the masks.
probs (bool): Whether to plot classification probability
show (bool): Whether to display the annotated image directly.
save (bool): Whether to save the annotated image to `filename`.
filename (str): Filename to save image to if save is True.
Returns:
(numpy.ndarray): A numpy array of the annotated image.
@ -268,8 +289,27 @@ class Results(SimpleClass):
for k in reversed(self.keypoints.data):
annotator.kpts(k, self.orig_shape, radius=kpt_radius, kpt_line=kpt_line)
# Show results
if show:
annotator.show(self.path)
# Save results
if save:
annotator.save(filename)
return annotator.result()
def show(self, *args, **kwargs):
"""Show annotated results image."""
self.plot(show=True, *args, **kwargs)
def save(self, filename=None, *args, **kwargs):
"""Save annotated results image."""
if not filename:
filename = f"results_{Path(self.path).name}"
self.plot(save=True, filename=filename, *args, **kwargs)
return filename
def verbose(self):
"""Return log string for each task."""
log_string = ""
@ -377,33 +417,41 @@ class Results(SimpleClass):
class Boxes(BaseTensor):
"""
A class for storing and manipulating detection boxes.
Args:
boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing the detection boxes,
with shape (num_boxes, 6) or (num_boxes, 7). The last two columns contain confidence and class values.
If present, the third last column contains track IDs.
orig_shape (tuple): Original image size, in the format (height, width).
Manages detection boxes, providing easy access and manipulation of box coordinates, confidence scores, class
identifiers, and optional tracking IDs. Supports multiple formats for box coordinates, including both absolute and
normalized forms.
Attributes:
xyxy (torch.Tensor | numpy.ndarray): The boxes in xyxy format.
conf (torch.Tensor | numpy.ndarray): The confidence values of the boxes.
cls (torch.Tensor | numpy.ndarray): The class values of the boxes.
id (torch.Tensor | numpy.ndarray): The track IDs of the boxes (if available).
xywh (torch.Tensor | numpy.ndarray): The boxes in xywh format.
xyxyn (torch.Tensor | numpy.ndarray): The boxes in xyxy format normalized by original image size.
xywhn (torch.Tensor | numpy.ndarray): The boxes in xywh format normalized by original image size.
data (torch.Tensor): The raw bboxes tensor (alias for `boxes`).
data (torch.Tensor): The raw tensor containing detection boxes and their associated data.
orig_shape (tuple): The original image size as a tuple (height, width), used for normalization.
is_track (bool): Indicates whether tracking IDs are included in the box data.
Properties:
xyxy (torch.Tensor | numpy.ndarray): Boxes in [x1, y1, x2, y2] format.
conf (torch.Tensor | numpy.ndarray): Confidence scores for each box.
cls (torch.Tensor | numpy.ndarray): Class labels for each box.
id (torch.Tensor | numpy.ndarray, optional): Tracking IDs for each box, if available.
xywh (torch.Tensor | numpy.ndarray): Boxes in [x, y, width, height] format, calculated on demand.
xyxyn (torch.Tensor | numpy.ndarray): Normalized [x1, y1, x2, y2] boxes, relative to `orig_shape`.
xywhn (torch.Tensor | numpy.ndarray): Normalized [x, y, width, height] boxes, relative to `orig_shape`.
Methods:
cpu(): Move the object to CPU memory.
numpy(): Convert the object to a numpy array.
cuda(): Move the object to CUDA memory.
to(*args, **kwargs): Move the object to the specified device.
cpu(): Moves the boxes to CPU memory.
numpy(): Converts the boxes to a numpy array format.
cuda(): Moves the boxes to CUDA (GPU) memory.
to(device, dtype=None): Moves the boxes to the specified device.
"""
def __init__(self, boxes, orig_shape) -> None:
"""Initialize the Boxes class."""
"""
Initialize the Boxes class.
Args:
boxes (torch.Tensor | numpy.ndarray): A tensor or numpy array containing the detection boxes, with
shape (num_boxes, 6) or (num_boxes, 7). The last two columns contain confidence and class values.
If present, the third last column contains track IDs.
orig_shape (tuple): Original image size, in the format (height, width).
"""
if boxes.ndim == 1:
boxes = boxes[None, :]
n = boxes.shape[-1]
@ -607,7 +655,7 @@ class OBB(BaseTensor):
conf (torch.Tensor | numpy.ndarray): The confidence values of the boxes.
cls (torch.Tensor | numpy.ndarray): The class values of the boxes.
id (torch.Tensor | numpy.ndarray): The track IDs of the boxes (if available).
xyxyxyxyn (torch.Tensor | numpy.ndarray): The rotated boxes in xyxyxyxy format normalized by original image size.
xyxyxyxyn (torch.Tensor | numpy.ndarray): The rotated boxes in xyxyxyxy format normalized by orig image size.
xyxyxyxy (torch.Tensor | numpy.ndarray): The rotated boxes in xyxyxyxy format.
xyxy (torch.Tensor | numpy.ndarray): The horizontal boxes in xyxyxyxy format.
data (torch.Tensor): The raw OBB tensor (alias for `boxes`).

22
ultralytics/utils/plotting.py
View File

@ -329,10 +329,18 @@ class Annotator:
"""Return annotated image as array."""
return np.asarray(self.im)
# Object Counting Annotator
def show(self, title=None):
"""Show the annotated image."""
(self.im if isinstance(self.im, Image.Image) else Image.fromarray(self.im[..., ::-1])).show(title)
def save(self, filename="image.jpg"):
"""Save the annotated image to 'filename'."""
(self.im if isinstance(self.im, Image.Image) else Image.fromarray(self.im[..., ::-1])).save(filename)
def draw_region(self, reg_pts=None, color=(0, 255, 0), thickness=5):
"""
Draw region line
Draw region line.
Args:
reg_pts (list): Region Points (for line 2 points, for region 4 points)
color (tuple): Region Color value
@ -342,7 +350,8 @@ class Annotator:
def draw_centroid_and_tracks(self, track, color=(255, 0, 255), track_thickness=2):
"""
Draw centroid point and track trails
Draw centroid point and track trails.
Args:
track (list): object tracking points for trails display
color (tuple): tracks line color
@ -354,7 +363,8 @@ class Annotator:
def count_labels(self, counts=0, count_txt_size=2, color=(255, 255, 255), txt_color=(0, 0, 0)):
"""
Plot counts for object counter
Plot counts for object counter.
Args:
counts (int): objects counts value
count_txt_size (int): text size for counts display
@ -383,7 +393,9 @@ class Annotator:
@staticmethod
def estimate_pose_angle(a, b, c):
"""Calculate the pose angle for object
"""
Calculate the pose angle for object.
Args:
a (float) : The value of pose point a
b (float): The value of pose point b