Reference for ultralytics/engine/results.py
Note
This file is available at https://github.com/ultralytics/ultralytics/blob/main/ultralytics/engine/results.py. If you spot a problem please help fix it by contributing a Pull Request 🛠️. Thank you 🙏!
ultralytics.engine.results.BaseTensor
Bases: SimpleClass
Base tensor class with additional methods for easy manipulation and device handling.
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor | ndarray
|
Prediction data such as bounding boxes, masks, or keypoints. |
orig_shape |
Tuple[int, int]
|
Original shape of the image, typically in the format (height, width). |
Methods:
Name | Description |
---|---|
cpu |
Return a copy of the tensor stored in CPU memory. |
numpy |
Returns a copy of the tensor as a numpy array. |
cuda |
Moves the tensor to GPU memory, returning a new instance if necessary. |
to |
Return a copy of the tensor with the specified device and dtype. |
Examples:
>>> import torch
>>> data = torch.tensor([[1, 2, 3], [4, 5, 6]])
>>> orig_shape = (720, 1280)
>>> base_tensor = BaseTensor(data, orig_shape)
>>> cpu_tensor = base_tensor.cpu()
>>> numpy_array = base_tensor.numpy()
>>> gpu_tensor = base_tensor.cuda()
Parameters:
Name | Type | Description | Default |
---|---|---|---|
data |
Tensor | ndarray
|
Prediction data such as bounding boxes, masks, or keypoints. |
required |
orig_shape |
Tuple[int, int]
|
Original shape of the image in (height, width) format. |
required |
Examples:
>>> import torch
>>> data = torch.tensor([[1, 2, 3], [4, 5, 6]])
>>> orig_shape = (720, 1280)
>>> base_tensor = BaseTensor(data, orig_shape)
Source code in ultralytics/engine/results.py
shape
property
__getitem__
Returns a new BaseTensor instance containing the specified indexed elements of the data tensor.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
idx |
int | List[int] | Tensor
|
Index or indices to select from the data tensor. |
required |
Returns:
Type | Description |
---|---|
BaseTensor
|
A new BaseTensor instance containing the indexed data. |
Examples:
>>> data = torch.tensor([[1, 2, 3], [4, 5, 6]])
>>> base_tensor = BaseTensor(data, orig_shape=(720, 1280))
>>> result = base_tensor[0] # Select the first row
>>> print(result.data)
tensor([1, 2, 3])
Source code in ultralytics/engine/results.py
__len__
Returns the length of the underlying data tensor.
Returns:
Type | Description |
---|---|
int
|
The number of elements in the first dimension of the data tensor. |
Examples:
>>> data = torch.tensor([[1, 2, 3], [4, 5, 6]])
>>> base_tensor = BaseTensor(data, orig_shape=(720, 1280))
>>> len(base_tensor)
2
Source code in ultralytics/engine/results.py
cpu
Returns a copy of the tensor stored in CPU memory.
Returns:
Type | Description |
---|---|
BaseTensor
|
A new BaseTensor object with the data tensor moved to CPU memory. |
Examples:
>>> data = torch.tensor([[1, 2, 3], [4, 5, 6]]).cuda()
>>> base_tensor = BaseTensor(data, orig_shape=(720, 1280))
>>> cpu_tensor = base_tensor.cpu()
>>> isinstance(cpu_tensor, BaseTensor)
True
>>> cpu_tensor.data.device
device(type='cpu')
Source code in ultralytics/engine/results.py
cuda
Moves the tensor to GPU memory.
Returns:
Type | Description |
---|---|
BaseTensor
|
A new BaseTensor instance with the data moved to GPU memory if it's not already a numpy array, otherwise returns self. |
Examples:
>>> import torch
>>> from ultralytics.engine.results import BaseTensor
>>> data = torch.tensor([[1, 2, 3], [4, 5, 6]])
>>> base_tensor = BaseTensor(data, orig_shape=(720, 1280))
>>> gpu_tensor = base_tensor.cuda()
>>> print(gpu_tensor.data.device)
cuda:0
Source code in ultralytics/engine/results.py
numpy
Returns a copy of the tensor as a numpy array.
Returns:
Type | Description |
---|---|
ndarray
|
A numpy array containing the same data as the original tensor. |
Examples:
>>> data = torch.tensor([[1, 2, 3], [4, 5, 6]])
>>> orig_shape = (720, 1280)
>>> base_tensor = BaseTensor(data, orig_shape)
>>> numpy_array = base_tensor.numpy()
>>> print(type(numpy_array))
<class 'numpy.ndarray'>
Source code in ultralytics/engine/results.py
to
Return a copy of the tensor with the specified device and dtype.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
*args |
Any
|
Variable length argument list to be passed to torch.Tensor.to(). |
()
|
**kwargs |
Any
|
Arbitrary keyword arguments to be passed to torch.Tensor.to(). |
{}
|
Returns:
Type | Description |
---|---|
BaseTensor
|
A new BaseTensor instance with the data moved to the specified device and/or dtype. |
Examples:
>>> base_tensor = BaseTensor(torch.randn(3, 4), orig_shape=(480, 640))
>>> cuda_tensor = base_tensor.to("cuda")
>>> float16_tensor = base_tensor.to(dtype=torch.float16)
Source code in ultralytics/engine/results.py
ultralytics.engine.results.Results
Results(
orig_img,
path,
names,
boxes=None,
masks=None,
probs=None,
keypoints=None,
obb=None,
speed=None,
)
Bases: SimpleClass
A class for storing and manipulating inference results.
This class encapsulates the functionality for handling detection, segmentation, pose estimation, and classification results from YOLO models.
Attributes:
Name | Type | Description |
---|---|---|
orig_img |
ndarray
|
Original image as a numpy array. |
orig_shape |
Tuple[int, int]
|
Original image shape in (height, width) format. |
boxes |
Boxes | None
|
Object containing detection bounding boxes. |
masks |
Masks | None
|
Object containing detection masks. |
probs |
Probs | None
|
Object containing class probabilities for classification tasks. |
keypoints |
Keypoints | None
|
Object containing detected keypoints for each object. |
obb |
OBB | None
|
Object containing oriented bounding boxes. |
speed |
Dict[str, float | None]
|
Dictionary of preprocess, inference, and postprocess speeds. |
names |
Dict[int, str]
|
Dictionary mapping class IDs to class names. |
path |
str
|
Path to the image file. |
_keys |
Tuple[str, ...]
|
Tuple of attribute names for internal use. |
Methods:
Name | Description |
---|---|
update |
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 |
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. |
show |
Shows annotated results on screen. |
save |
Saves annotated results to file. |
verbose |
Returns a log string for each task, detailing detections and classifications. |
save_txt |
Saves detection results to a text file. |
save_crop |
Saves cropped detection images. |
tojson |
Converts detection results to JSON format. |
Examples:
>>> results = model("path/to/image.jpg")
>>> for result in results:
... print(result.boxes) # Print detection boxes
... result.show() # Display the annotated image
... result.save(filename="result.jpg") # Save annotated image
Parameters:
Name | Type | Description | Default |
---|---|---|---|
orig_img |
ndarray
|
The original image as a numpy array. |
required |
path |
str
|
The path to the image file. |
required |
names |
Dict
|
A dictionary of class names. |
required |
boxes |
Tensor | None
|
A 2D tensor of bounding box coordinates for each detection. |
None
|
masks |
Tensor | None
|
A 3D tensor of detection masks, where each mask is a binary image. |
None
|
probs |
Tensor | None
|
A 1D tensor of probabilities of each class for classification task. |
None
|
keypoints |
Tensor | None
|
A 2D tensor of keypoint coordinates for each detection. |
None
|
obb |
Tensor | None
|
A 2D tensor of oriented bounding box coordinates for each detection. |
None
|
speed |
Dict | None
|
A dictionary containing preprocess, inference, and postprocess speeds (ms/image). |
None
|
Examples:
>>> results = model("path/to/image.jpg")
>>> result = results[0] # Get the first result
>>> boxes = result.boxes # Get the boxes for the first result
>>> masks = result.masks # Get the masks for the first result
Notes
For the default pose model, keypoint indices for human body pose estimation are: 0: Nose, 1: Left Eye, 2: Right Eye, 3: Left Ear, 4: Right Ear 5: Left Shoulder, 6: Right Shoulder, 7: Left Elbow, 8: Right Elbow 9: Left Wrist, 10: Right Wrist, 11: Left Hip, 12: Right Hip 13: Left Knee, 14: Right Knee, 15: Left Ankle, 16: Right Ankle
Source code in ultralytics/engine/results.py
__getitem__
Return a Results object for a specific index of inference results.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
idx |
int | slice
|
Index or slice to retrieve from the Results object. |
required |
Returns:
Type | Description |
---|---|
Results
|
A new Results object containing the specified subset of inference results. |
Examples:
>>> results = model("path/to/image.jpg") # Perform inference
>>> single_result = results[0] # Get the first result
>>> subset_results = results[1:4] # Get a slice of results
Source code in ultralytics/engine/results.py
__len__
Return the number of detections in the Results object.
Returns:
Type | Description |
---|---|
int
|
The number of detections, determined by the length of the first non-empty attribute (boxes, masks, probs, keypoints, or obb). |
Examples:
Source code in ultralytics/engine/results.py
cpu
Returns a copy of the Results object with all its tensors moved to CPU memory.
This method creates a new Results object with all tensor attributes (boxes, masks, probs, keypoints, obb) transferred to CPU memory. It's useful for moving data from GPU to CPU for further processing or saving.
Returns:
Type | Description |
---|---|
Results
|
A new Results object with all tensor attributes on CPU memory. |
Examples:
>>> results = model("path/to/image.jpg") # Perform inference
>>> cpu_result = results[0].cpu() # Move the first result to CPU
>>> print(cpu_result.boxes.device) # Output: cpu
Source code in ultralytics/engine/results.py
cuda
Moves all tensors in the Results object to GPU memory.
Returns:
Type | Description |
---|---|
Results
|
A new Results object with all tensors moved to CUDA device. |
Examples:
>>> results = model("path/to/image.jpg")
>>> cuda_results = results[0].cuda() # Move first result to GPU
>>> for result in results:
... result_cuda = result.cuda() # Move each result to GPU
Source code in ultralytics/engine/results.py
new
Creates a new Results object with the same image, path, names, and speed attributes.
Returns:
Type | Description |
---|---|
Results
|
A new Results object with copied attributes from the original instance. |
Examples:
Source code in ultralytics/engine/results.py
numpy
Converts all tensors in the Results object to numpy arrays.
Returns:
Type | Description |
---|---|
Results
|
A new Results object with all tensors converted to numpy arrays. |
Examples:
>>> results = model("path/to/image.jpg")
>>> numpy_result = results[0].numpy()
>>> type(numpy_result.boxes.data)
<class 'numpy.ndarray'>
Notes
This method creates a new Results object, leaving the original unchanged. It's useful for interoperability with numpy-based libraries or when CPU-based operations are required.
Source code in ultralytics/engine/results.py
plot
plot(
conf=True,
line_width=None,
font_size=None,
font="Arial.ttf",
pil=False,
img=None,
im_gpu=None,
kpt_radius=5,
kpt_line=True,
labels=True,
boxes=True,
masks=True,
probs=True,
show=False,
save=False,
filename=None,
color_mode="class",
)
Plots detection results on an input RGB image.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
conf |
bool
|
Whether to plot detection confidence scores. |
True
|
line_width |
float | None
|
Line width of bounding boxes. If None, scaled to image size. |
None
|
font_size |
float | None
|
Font size for text. If None, scaled to image size. |
None
|
font |
str
|
Font to use for text. |
'Arial.ttf'
|
pil |
bool
|
Whether to return the image as a PIL Image. |
False
|
img |
ndarray | None
|
Image to plot on. If None, uses original image. |
None
|
im_gpu |
Tensor | None
|
Normalized image on GPU for faster mask plotting. |
None
|
kpt_radius |
int
|
Radius of drawn keypoints. |
5
|
kpt_line |
bool
|
Whether to draw lines connecting keypoints. |
True
|
labels |
bool
|
Whether to plot labels of bounding boxes. |
True
|
boxes |
bool
|
Whether to plot bounding boxes. |
True
|
masks |
bool
|
Whether to plot masks. |
True
|
probs |
bool
|
Whether to plot classification probabilities. |
True
|
show |
bool
|
Whether to display the annotated image. |
False
|
save |
bool
|
Whether to save the annotated image. |
False
|
filename |
str | None
|
Filename to save image if save is True. |
None
|
color_mode |
bool
|
Specify the color mode, e.g., 'instance' or 'class'. Default to 'class'. |
'class'
|
Returns:
Type | Description |
---|---|
ndarray
|
Annotated image as a numpy array. |
Examples:
Source code in ultralytics/engine/results.py
446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 |
|
save
Saves annotated inference results image to file.
This method plots the detection results on the original image and saves the annotated image to a file. It
utilizes the plot
method to generate the annotated image and then saves it to the specified filename.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
filename |
str | Path | None
|
The filename to save the annotated image. If None, a default filename is generated based on the original image path. |
None
|
*args |
Any
|
Variable length argument list to be passed to the |
()
|
**kwargs |
Any
|
Arbitrary keyword arguments to be passed to the |
{}
|
Examples:
>>> results = model("path/to/image.jpg")
>>> for result in results:
... result.save("annotated_image.jpg")
>>> # Or with custom plot arguments
>>> for result in results:
... result.save("annotated_image.jpg", conf=False, line_width=2)
Source code in ultralytics/engine/results.py
save_crop
Saves cropped detection images to specified directory.
This method saves cropped images of detected objects to a specified directory. Each crop is saved in a subdirectory named after the object's class, with the filename based on the input file_name.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
save_dir |
str | Path
|
Directory path where cropped images will be saved. |
required |
file_name |
str | Path
|
Base filename for the saved cropped images. Default is Path("im.jpg"). |
Path('im.jpg')
|
Notes
- This method does not support Classify or Oriented Bounding Box (OBB) tasks.
- Crops are saved as 'save_dir/class_name/file_name.jpg'.
- The method will create necessary subdirectories if they don't exist.
- Original image is copied before cropping to avoid modifying the original.
Examples:
>>> results = model("path/to/image.jpg")
>>> for result in results:
... result.save_crop(save_dir="path/to/crops", file_name="detection")
Source code in ultralytics/engine/results.py
save_txt
Save detection results to a text file.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
txt_file |
str | Path
|
Path to the output text file. |
required |
save_conf |
bool
|
Whether to include confidence scores in the output. |
False
|
Returns:
Type | Description |
---|---|
str
|
Path to the saved text file. |
Examples:
>>> from ultralytics import YOLO
>>> model = YOLO("yolov8n.pt")
>>> results = model("path/to/image.jpg")
>>> for result in results:
... result.save_txt("output.txt")
Notes
- The file will contain one line per detection or classification with the following structure:
- For detections:
class confidence x_center y_center width height
- For classifications:
confidence class_name
- For masks and keypoints, the specific formats will vary accordingly.
- The function will create the output directory if it does not exist.
- If save_conf is False, the confidence scores will be excluded from the output.
- Existing contents of the file will not be overwritten; new results will be appended.
Source code in ultralytics/engine/results.py
show
Display the image with annotated inference results.
This method plots the detection results on the original image and displays it. It's a convenient way to visualize the model's predictions directly.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
*args |
Any
|
Variable length argument list to be passed to the |
()
|
**kwargs |
Any
|
Arbitrary keyword arguments to be passed to the |
{}
|
Examples:
>>> results = model("path/to/image.jpg")
>>> results[0].show() # Display the first result
>>> for result in results:
... result.show() # Display all results
Source code in ultralytics/engine/results.py
summary
Converts inference results to a summarized dictionary with optional normalization for box coordinates.
This method creates a list of detection dictionaries, each containing information about a single detection or classification result. For classification tasks, it returns the top class and its confidence. For detection tasks, it includes class information, bounding box coordinates, and optionally mask segments and keypoints.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
normalize |
bool
|
Whether to normalize bounding box coordinates by image dimensions. Defaults to False. |
False
|
decimals |
int
|
Number of decimal places to round the output values to. Defaults to 5. |
5
|
Returns:
Type | Description |
---|---|
List[Dict]
|
A list of dictionaries, each containing summarized information for a single detection or classification result. The structure of each dictionary varies based on the task type (classification or detection) and available information (boxes, masks, keypoints). |
Examples:
Source code in ultralytics/engine/results.py
to
Moves all tensors in the Results object to the specified device and dtype.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
*args |
Any
|
Variable length argument list to be passed to torch.Tensor.to(). |
()
|
**kwargs |
Any
|
Arbitrary keyword arguments to be passed to torch.Tensor.to(). |
{}
|
Returns:
Type | Description |
---|---|
Results
|
A new Results object with all tensors moved to the specified device and dtype. |
Examples:
>>> results = model("path/to/image.jpg")
>>> result_cuda = results[0].to("cuda") # Move first result to GPU
>>> result_cpu = results[0].to("cpu") # Move first result to CPU
>>> result_half = results[0].to(dtype=torch.float16) # Convert first result to half precision
Source code in ultralytics/engine/results.py
to_csv
Converts detection results to a CSV format.
This method serializes the detection results into a CSV format. It includes information about detected objects such as bounding boxes, class names, confidence scores, and optionally segmentation masks and keypoints.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
normalize |
bool
|
Whether to normalize the bounding box coordinates by the image dimensions. If True, coordinates will be returned as float values between 0 and 1. Defaults to False. |
False
|
decimals |
int
|
Number of decimal places to round the output values to. Defaults to 5. |
5
|
*args |
Any
|
Variable length argument list to be passed to pandas.DataFrame.to_csv(). |
()
|
**kwargs |
Any
|
Arbitrary keyword arguments to be passed to pandas.DataFrame.to_csv(). |
{}
|
Returns:
Type | Description |
---|---|
str
|
CSV containing all the information in results in an organized way. |
Examples:
Source code in ultralytics/engine/results.py
to_df
Converts detection results to a Pandas Dataframe.
This method converts the detection results into Pandas Dataframe format. It includes information about detected objects such as bounding boxes, class names, confidence scores, and optionally segmentation masks and keypoints.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
normalize |
bool
|
Whether to normalize the bounding box coordinates by the image dimensions. If True, coordinates will be returned as float values between 0 and 1. Defaults to False. |
False
|
decimals |
int
|
Number of decimal places to round the output values to. Defaults to 5. |
5
|
Returns:
Type | Description |
---|---|
DataFrame
|
A Pandas Dataframe containing all the information in results in an organized way. |
Examples:
Source code in ultralytics/engine/results.py
to_json
Converts detection results to JSON format.
This method serializes the detection results into a JSON-compatible format. It includes information about detected objects such as bounding boxes, class names, confidence scores, and optionally segmentation masks and keypoints.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
normalize |
bool
|
Whether to normalize the bounding box coordinates by the image dimensions. If True, coordinates will be returned as float values between 0 and 1. Defaults to False. |
False
|
decimals |
int
|
Number of decimal places to round the output values to. Defaults to 5. |
5
|
Returns:
Type | Description |
---|---|
str
|
A JSON string containing the serialized detection results. |
Examples:
>>> results = model("path/to/image.jpg")
>>> json_result = results[0].to_json()
>>> print(json_result)
Notes
- For classification tasks, the JSON will contain class probabilities instead of bounding boxes.
- For object detection tasks, the JSON will include bounding box coordinates, class names, and confidence scores.
- If available, segmentation masks and keypoints will also be included in the JSON output.
- The method uses the
summary
method internally to generate the data structure before converting it to JSON.
Source code in ultralytics/engine/results.py
to_xml
Converts detection results to XML format.
This method serializes the detection results into an XML format. It includes information about detected objects such as bounding boxes, class names, confidence scores, and optionally segmentation masks and keypoints.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
normalize |
bool
|
Whether to normalize the bounding box coordinates by the image dimensions. If True, coordinates will be returned as float values between 0 and 1. Defaults to False. |
False
|
decimals |
int
|
Number of decimal places to round the output values to. Defaults to 5. |
5
|
*args |
Any
|
Variable length argument list to be passed to pandas.DataFrame.to_xml(). |
()
|
**kwargs |
Any
|
Arbitrary keyword arguments to be passed to pandas.DataFrame.to_xml(). |
{}
|
Returns:
Type | Description |
---|---|
str
|
An XML string containing all the information in results in an organized way. |
Examples:
Source code in ultralytics/engine/results.py
tojson
Deprecated version of to_json().
update
Updates the Results object with new detection data.
This method allows updating the boxes, masks, probabilities, and oriented bounding boxes (OBB) of the Results object. It ensures that boxes are clipped to the original image shape.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
boxes |
Tensor | None
|
A tensor of shape (N, 6) containing bounding box coordinates and confidence scores. The format is (x1, y1, x2, y2, conf, class). |
None
|
masks |
Tensor | None
|
A tensor of shape (N, H, W) containing segmentation masks. |
None
|
probs |
Tensor | None
|
A tensor of shape (num_classes,) containing class probabilities. |
None
|
obb |
Tensor | None
|
A tensor of shape (N, 5) containing oriented bounding box coordinates. |
None
|
Examples:
>>> results = model("image.jpg")
>>> new_boxes = torch.tensor([[100, 100, 200, 200, 0.9, 0]])
>>> results[0].update(boxes=new_boxes)
Source code in ultralytics/engine/results.py
verbose
Returns a log string for each task in the results, detailing detection and classification outcomes.
This method generates a human-readable string summarizing the detection and classification results. It includes the number of detections for each class and the top probabilities for classification tasks.
Returns:
Type | Description |
---|---|
str
|
A formatted string containing a summary of the results. For detection tasks, it includes the number of detections per class. For classification tasks, it includes the top 5 class probabilities. |
Examples:
>>> results = model("path/to/image.jpg")
>>> for result in results:
... print(result.verbose())
2 persons, 1 car, 3 traffic lights,
dog 0.92, cat 0.78, horse 0.64,
Notes
- If there are no detections, the method returns "(no detections), " for detection tasks.
- For classification tasks, it returns the top 5 class probabilities and their corresponding class names.
- The returned string is comma-separated and ends with a comma and a space.
Source code in ultralytics/engine/results.py
ultralytics.engine.results.Boxes
Bases: BaseTensor
A class for managing and manipulating detection boxes.
This class provides functionality for handling detection boxes, including their coordinates, confidence scores, class labels, and optional tracking IDs. It supports various box formats and offers methods for easy manipulation and conversion between different coordinate systems.
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor | ndarray
|
The raw tensor containing detection boxes and associated data. |
orig_shape |
Tuple[int, int]
|
The original image dimensions (height, width). |
is_track |
bool
|
Indicates whether tracking IDs are included in the box data. |
xyxy |
Tensor | ndarray
|
Boxes in [x1, y1, x2, y2] format. |
conf |
Tensor | ndarray
|
Confidence scores for each box. |
cls |
Tensor | ndarray
|
Class labels for each box. |
id |
Tensor | ndarray
|
Tracking IDs for each box (if available). |
xywh |
Tensor | ndarray
|
Boxes in [x, y, width, height] format. |
xyxyn |
Tensor | ndarray
|
Normalized [x1, y1, x2, y2] boxes relative to orig_shape. |
xywhn |
Tensor | ndarray
|
Normalized [x, y, width, height] boxes relative to orig_shape. |
Methods:
Name | Description |
---|---|
cpu |
Returns a copy of the object with all tensors on CPU memory. |
numpy |
Returns a copy of the object with all tensors as numpy arrays. |
cuda |
Returns a copy of the object with all tensors on GPU memory. |
to |
Returns a copy of the object with tensors on specified device and dtype. |
Examples:
>>> import torch
>>> boxes_data = torch.tensor([[100, 50, 150, 100, 0.9, 0], [200, 150, 300, 250, 0.8, 1]])
>>> orig_shape = (480, 640) # height, width
>>> boxes = Boxes(boxes_data, orig_shape)
>>> print(boxes.xyxy)
>>> print(boxes.conf)
>>> print(boxes.cls)
>>> print(boxes.xywhn)
This class manages detection boxes, providing easy access and manipulation of box coordinates, confidence scores, class identifiers, and optional tracking IDs. It supports multiple formats for box coordinates, including both absolute and normalized forms.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
boxes |
Tensor | ndarray
|
A tensor or numpy array with detection boxes of shape (num_boxes, 6) or (num_boxes, 7). Columns should contain [x1, y1, x2, y2, confidence, class, (optional) track_id]. |
required |
orig_shape |
Tuple[int, int]
|
The original image shape as (height, width). Used for normalization. |
required |
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor
|
The raw tensor containing detection boxes and their associated data. |
orig_shape |
Tuple[int, int]
|
The original image size, used for normalization. |
is_track |
bool
|
Indicates whether tracking IDs are included in the box data. |
Examples:
>>> import torch
>>> boxes = torch.tensor([[100, 50, 150, 100, 0.9, 0]])
>>> orig_shape = (480, 640)
>>> detection_boxes = Boxes(boxes, orig_shape)
>>> print(detection_boxes.xyxy)
tensor([[100., 50., 150., 100.]])
Source code in ultralytics/engine/results.py
cls
property
Returns the class ID tensor representing category predictions for each bounding box.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor or numpy array containing the class IDs for each detection box. The shape is (N,), where N is the number of boxes. |
Examples:
conf
property
Returns the confidence scores for each detection box.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A 1D tensor or array containing confidence scores for each detection, with shape (N,) where N is the number of detections. |
Examples:
id
property
Returns the tracking IDs for each detection box if available.
Returns:
Type | Description |
---|---|
Tensor | None
|
A tensor containing tracking IDs for each box if tracking is enabled, otherwise None. Shape is (N,) where N is the number of boxes. |
Examples:
>>> results = model.track("path/to/video.mp4")
>>> for result in results:
... boxes = result.boxes
... if boxes.is_track:
... track_ids = boxes.id
... print(f"Tracking IDs: {track_ids}")
... else:
... print("Tracking is not enabled for these boxes.")
Notes
- This property is only available when tracking is enabled (i.e., when
is_track
is True). - The tracking IDs are typically used to associate detections across multiple frames in video analysis.
xywh
cached
property
Convert bounding boxes from [x1, y1, x2, y2] format to [x, y, width, height] format.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
Boxes in [x_center, y_center, width, height] format, where x_center, y_center are the coordinates of the center point of the bounding box, width, height are the dimensions of the bounding box and the shape of the returned tensor is (N, 4), where N is the number of boxes. |
Examples:
xywhn
cached
property
Returns normalized bounding boxes in [x, y, width, height] format.
This property calculates and returns the normalized bounding box coordinates in the format [x_center, y_center, width, height], where all values are relative to the original image dimensions.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
Normalized bounding boxes with shape (N, 4), where N is the number of boxes. Each row contains [x_center, y_center, width, height] values normalized to [0, 1] based on the original image dimensions. |
Examples:
xyxy
property
Returns bounding boxes in [x1, y1, x2, y2] format.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor or numpy array of shape (n, 4) containing bounding box coordinates in [x1, y1, x2, y2] format, where n is the number of boxes. |
Examples:
xyxyn
cached
property
Returns normalized bounding box coordinates relative to the original image size.
This property calculates and returns the bounding box coordinates in [x1, y1, x2, y2] format, normalized to the range [0, 1] based on the original image dimensions.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
Normalized bounding box coordinates with shape (N, 4), where N is the number of boxes. Each row contains [x1, y1, x2, y2] values normalized to [0, 1]. |
Examples:
ultralytics.engine.results.Masks
Bases: BaseTensor
A class for storing and manipulating detection masks.
This class extends BaseTensor and provides functionality for handling segmentation masks, including methods for converting between pixel and normalized coordinates.
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor | ndarray
|
The raw tensor or array containing mask data. |
orig_shape |
tuple
|
Original image shape in (height, width) format. |
xy |
List[ndarray]
|
A list of segments in pixel coordinates. |
xyn |
List[ndarray]
|
A list of normalized segments. |
Methods:
Name | Description |
---|---|
cpu |
Returns a copy of the Masks object with the mask tensor on CPU memory. |
numpy |
Returns a copy of the Masks object with the mask tensor as a numpy array. |
cuda |
Returns a copy of the Masks object with the mask tensor on GPU memory. |
to |
Returns a copy of the Masks object with the mask tensor on specified device and dtype. |
Examples:
>>> masks_data = torch.rand(1, 160, 160)
>>> orig_shape = (720, 1280)
>>> masks = Masks(masks_data, orig_shape)
>>> pixel_coords = masks.xy
>>> normalized_coords = masks.xyn
Parameters:
Name | Type | Description | Default |
---|---|---|---|
masks |
Tensor | ndarray
|
Detection masks with shape (num_masks, height, width). |
required |
orig_shape |
tuple
|
The original image shape as (height, width). Used for normalization. |
required |
Examples:
>>> import torch
>>> from ultralytics.engine.results import Masks
>>> masks = torch.rand(10, 160, 160) # 10 masks of 160x160 resolution
>>> orig_shape = (720, 1280) # Original image shape
>>> mask_obj = Masks(masks, orig_shape)
Source code in ultralytics/engine/results.py
xy
cached
property
Returns the [x, y] pixel coordinates for each segment in the mask tensor.
This property calculates and returns a list of pixel coordinates for each segmentation mask in the Masks object. The coordinates are scaled to match the original image dimensions.
Returns:
Type | Description |
---|---|
List[ndarray]
|
A list of numpy arrays, where each array contains the [x, y] pixel coordinates for a single segmentation mask. Each array has shape (N, 2), where N is the number of points in the segment. |
Examples:
xyn
cached
property
Returns normalized xy-coordinates of the segmentation masks.
This property calculates and caches the normalized xy-coordinates of the segmentation masks. The coordinates are normalized relative to the original image shape.
Returns:
Type | Description |
---|---|
List[ndarray]
|
A list of numpy arrays, where each array contains the normalized xy-coordinates of a single segmentation mask. Each array has shape (N, 2), where N is the number of points in the mask contour. |
Examples:
ultralytics.engine.results.Keypoints
Bases: BaseTensor
A class for storing and manipulating detection keypoints.
This class encapsulates functionality for handling keypoint data, including coordinate manipulation, normalization, and confidence values.
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor
|
The raw tensor containing keypoint data. |
orig_shape |
Tuple[int, int]
|
The original image dimensions (height, width). |
has_visible |
bool
|
Indicates whether visibility information is available for keypoints. |
xy |
Tensor
|
Keypoint coordinates in [x, y] format. |
xyn |
Tensor
|
Normalized keypoint coordinates in [x, y] format, relative to orig_shape. |
conf |
Tensor
|
Confidence values for each keypoint, if available. |
Methods:
Name | Description |
---|---|
cpu |
Returns a copy of the keypoints tensor on CPU memory. |
numpy |
Returns a copy of the keypoints tensor as a numpy array. |
cuda |
Returns a copy of the keypoints tensor on GPU memory. |
to |
Returns a copy of the keypoints tensor with specified device and dtype. |
Examples:
>>> import torch
>>> from ultralytics.engine.results import Keypoints
>>> keypoints_data = torch.rand(1, 17, 3) # 1 detection, 17 keypoints, (x, y, conf)
>>> orig_shape = (480, 640) # Original image shape (height, width)
>>> keypoints = Keypoints(keypoints_data, orig_shape)
>>> print(keypoints.xy.shape) # Access xy coordinates
>>> print(keypoints.conf) # Access confidence values
>>> keypoints_cpu = keypoints.cpu() # Move keypoints to CPU
This method processes the input keypoints tensor, handling both 2D and 3D formats. For 3D tensors (x, y, confidence), it masks out low-confidence keypoints by setting their coordinates to zero.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
keypoints |
Tensor
|
A tensor containing keypoint data. Shape can be either: - (num_objects, num_keypoints, 2) for x, y coordinates only - (num_objects, num_keypoints, 3) for x, y coordinates and confidence scores |
required |
orig_shape |
Tuple[int, int]
|
The original image dimensions (height, width). |
required |
Examples:
>>> kpts = torch.rand(1, 17, 3) # 1 object, 17 keypoints (COCO format), x,y,conf
>>> orig_shape = (720, 1280) # Original image height, width
>>> keypoints = Keypoints(kpts, orig_shape)
Source code in ultralytics/engine/results.py
conf
cached
property
Returns confidence values for each keypoint.
Returns:
Type | Description |
---|---|
Tensor | None
|
A tensor containing confidence scores for each keypoint if available, otherwise None. Shape is (num_detections, num_keypoints) for batched data or (num_keypoints,) for single detection. |
Examples:
xy
cached
property
Returns x, y coordinates of keypoints.
Returns:
Type | Description |
---|---|
Tensor
|
A tensor containing the x, y coordinates of keypoints with shape (N, K, 2), where N is the number of detections and K is the number of keypoints per detection. |
Examples:
>>> results = model("image.jpg")
>>> keypoints = results[0].keypoints
>>> xy = keypoints.xy
>>> print(xy.shape) # (N, K, 2)
>>> print(xy[0]) # x, y coordinates of keypoints for first detection
Notes
- The returned coordinates are in pixel units relative to the original image dimensions.
- If keypoints were initialized with confidence values, only keypoints with confidence >= 0.5 are returned.
- This property uses LRU caching to improve performance on repeated access.
xyn
cached
property
Returns normalized coordinates (x, y) of keypoints relative to the original image size.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor or array of shape (N, K, 2) containing normalized keypoint coordinates, where N is the number of instances, K is the number of keypoints, and the last dimension contains [x, y] values in the range [0, 1]. |
Examples:
ultralytics.engine.results.Probs
Bases: BaseTensor
A class for storing and manipulating classification probabilities.
This class extends BaseTensor and provides methods for accessing and manipulating classification probabilities, including top-1 and top-5 predictions.
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor | ndarray
|
The raw tensor or array containing classification probabilities. |
orig_shape |
tuple | None
|
The original image shape as (height, width). Not used in this class. |
top1 |
int
|
Index of the class with the highest probability. |
top5 |
List[int]
|
Indices of the top 5 classes by probability. |
top1conf |
Tensor | ndarray
|
Confidence score of the top 1 class. |
top5conf |
Tensor | ndarray
|
Confidence scores of the top 5 classes. |
Methods:
Name | Description |
---|---|
cpu |
Returns a copy of the probabilities tensor on CPU memory. |
numpy |
Returns a copy of the probabilities tensor as a numpy array. |
cuda |
Returns a copy of the probabilities tensor on GPU memory. |
to |
Returns a copy of the probabilities tensor with specified device and dtype. |
Examples:
>>> probs = torch.tensor([0.1, 0.3, 0.6])
>>> p = Probs(probs)
>>> print(p.top1)
2
>>> print(p.top5)
[2, 1, 0]
>>> print(p.top1conf)
tensor(0.6000)
>>> print(p.top5conf)
tensor([0.6000, 0.3000, 0.1000])
This class stores and manages classification probabilities, providing easy access to top predictions and their confidences.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
probs |
Tensor | ndarray
|
A 1D tensor or array of classification probabilities. |
required |
orig_shape |
tuple | None
|
The original image shape as (height, width). Not used in this class but kept for consistency with other result classes. |
None
|
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor | ndarray
|
The raw tensor or array containing classification probabilities. |
top1 |
int
|
Index of the top 1 class. |
top5 |
List[int]
|
Indices of the top 5 classes. |
top1conf |
Tensor | ndarray
|
Confidence of the top 1 class. |
top5conf |
Tensor | ndarray
|
Confidences of the top 5 classes. |
Examples:
>>> import torch
>>> probs = torch.tensor([0.1, 0.3, 0.2, 0.4])
>>> p = Probs(probs)
>>> print(p.top1)
3
>>> print(p.top1conf)
tensor(0.4000)
>>> print(p.top5)
[3, 1, 2, 0]
Source code in ultralytics/engine/results.py
top1
cached
property
top1conf
cached
property
Returns the confidence score of the highest probability class.
This property retrieves the confidence score (probability) of the class with the highest predicted probability from the classification results.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor containing the confidence score of the top 1 class. |
Examples:
top5
cached
property
top5conf
cached
property
Returns confidence scores for the top 5 classification predictions.
This property retrieves the confidence scores corresponding to the top 5 class probabilities predicted by the model. It provides a quick way to access the most likely class predictions along with their associated confidence levels.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor or array containing the confidence scores for the top 5 predicted classes, sorted in descending order of probability. |
Examples:
ultralytics.engine.results.OBB
Bases: BaseTensor
A class for storing and manipulating Oriented Bounding Boxes (OBB).
This class provides functionality to handle oriented bounding boxes, including conversion between different formats, normalization, and access to various properties of the boxes.
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor
|
The raw OBB tensor containing box coordinates and associated data. |
orig_shape |
tuple
|
Original image size as (height, width). |
is_track |
bool
|
Indicates whether tracking IDs are included in the box data. |
xywhr |
Tensor | ndarray
|
Boxes in [x_center, y_center, width, height, rotation] format. |
conf |
Tensor | ndarray
|
Confidence scores for each box. |
cls |
Tensor | ndarray
|
Class labels for each box. |
id |
Tensor | ndarray
|
Tracking IDs for each box, if available. |
xyxyxyxy |
Tensor | ndarray
|
Boxes in 8-point [x1, y1, x2, y2, x3, y3, x4, y4] format. |
xyxyxyxyn |
Tensor | ndarray
|
Normalized 8-point coordinates relative to orig_shape. |
xyxy |
Tensor | ndarray
|
Axis-aligned bounding boxes in [x1, y1, x2, y2] format. |
Methods:
Name | Description |
---|---|
cpu |
Returns a copy of the OBB object with all tensors on CPU memory. |
numpy |
Returns a copy of the OBB object with all tensors as numpy arrays. |
cuda |
Returns a copy of the OBB object with all tensors on GPU memory. |
to |
Returns a copy of the OBB object with tensors on specified device and dtype. |
Examples:
>>> boxes = torch.tensor([[100, 50, 150, 100, 30, 0.9, 0]]) # xywhr, conf, cls
>>> obb = OBB(boxes, orig_shape=(480, 640))
>>> print(obb.xyxyxyxy)
>>> print(obb.conf)
>>> print(obb.cls)
This class stores and manipulates Oriented Bounding Boxes (OBB) for object detection tasks. It provides various properties and methods to access and transform the OBB data.
Parameters:
Name | Type | Description | Default |
---|---|---|---|
boxes |
Tensor | ndarray
|
A tensor or numpy array containing the detection boxes, with shape (num_boxes, 7) or (num_boxes, 8). The last two columns contain confidence and class values. If present, the third last column contains track IDs, and the fifth column contains rotation. |
required |
orig_shape |
Tuple[int, int]
|
Original image size, in the format (height, width). |
required |
Attributes:
Name | Type | Description |
---|---|---|
data |
Tensor | ndarray
|
The raw OBB tensor. |
orig_shape |
Tuple[int, int]
|
The original image shape. |
is_track |
bool
|
Whether the boxes include tracking IDs. |
Raises:
Type | Description |
---|---|
AssertionError
|
If the number of values per box is not 7 or 8. |
Examples:
>>> import torch
>>> boxes = torch.rand(3, 7) # 3 boxes with 7 values each
>>> orig_shape = (640, 480)
>>> obb = OBB(boxes, orig_shape)
>>> print(obb.xywhr) # Access the boxes in xywhr format
Source code in ultralytics/engine/results.py
cls
property
Returns the class values of the oriented bounding boxes.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor or numpy array containing the class values for each oriented bounding box. The shape is (N,), where N is the number of boxes. |
Examples:
conf
property
Returns the confidence scores for Oriented Bounding Boxes (OBBs).
This property retrieves the confidence values associated with each OBB detection. The confidence score represents the model's certainty in the detection.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor or numpy array of shape (N,) containing confidence scores for N detections, where each score is in the range [0, 1]. |
Examples:
id
property
Returns the tracking IDs of the oriented bounding boxes (if available).
Returns:
Type | Description |
---|---|
Tensor | ndarray | None
|
A tensor or numpy array containing the tracking IDs for each oriented bounding box. Returns None if tracking IDs are not available. |
Examples:
xywhr
property
Returns boxes in [x_center, y_center, width, height, rotation] format.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
A tensor or numpy array containing the oriented bounding boxes with format [x_center, y_center, width, height, rotation]. The shape is (N, 5) where N is the number of boxes. |
Examples:
xyxy
cached
property
Converts oriented bounding boxes (OBB) to axis-aligned bounding boxes in xyxy format.
This property calculates the minimal enclosing rectangle for each oriented bounding box and returns it in xyxy format (x1, y1, x2, y2). This is useful for operations that require axis-aligned bounding boxes, such as IoU calculation with non-rotated boxes.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
Axis-aligned bounding boxes in xyxy format with shape (N, 4), where N is the number of boxes. Each row contains [x1, y1, x2, y2] coordinates. |
Examples:
>>> import torch
>>> from ultralytics import YOLO
>>> model = YOLO("yolov8n-obb.pt")
>>> results = model("path/to/image.jpg")
>>> for result in results:
... obb = result.obb
... if obb is not None:
... xyxy_boxes = obb.xyxy
... print(xyxy_boxes.shape) # (N, 4)
Notes
- This method approximates the OBB by its minimal enclosing rectangle.
- The returned format is compatible with standard object detection metrics and visualization tools.
- The property uses caching to improve performance for repeated access.
xyxyxyxy
cached
property
Converts OBB format to 8-point (xyxyxyxy) coordinate format for rotated bounding boxes.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
Rotated bounding boxes in xyxyxyxy format with shape (N, 4, 2), where N is the number of boxes. Each box is represented by 4 points (x, y), starting from the top-left corner and moving clockwise. |
Examples:
xyxyxyxyn
cached
property
Converts rotated bounding boxes to normalized xyxyxyxy format.
Returns:
Type | Description |
---|---|
Tensor | ndarray
|
Normalized rotated bounding boxes in xyxyxyxy format with shape (N, 4, 2), where N is the number of boxes. Each box is represented by 4 points (x, y), normalized relative to the original image dimensions. |
Examples: