@ -145,61 +145,61 @@ The rows index the label files, each corresponding to an image in your dataset,
2. The dataset has now been split into `k` folds, each having a list of `train` and `val` indices. We will construct a DataFrame to display these results more clearly.
2. The dataset has now been split into `k` folds, each having a list of `train` and `val` indices. We will construct a DataFrame to display these results more clearly.
```python
```python
folds = [f'split_{n}' for n in range(1, ksplit + 1)]
folds = [f'split_{n}' for n in range(1, ksplit + 1)]
# To avoid division by zero, we add a small value (1E-7) to the denominator
# To avoid division by zero, we add a small value (1E-7) to the denominator
ratio = val_totals / (train_totals + 1E-7)
ratio = val_totals / (train_totals + 1E-7)
fold_lbl_distrb.loc[f'split_{n}'] = ratio
fold_lbl_distrb.loc[f'split_{n}'] = ratio
```
```
The ideal scenario is for all class ratios to be reasonably similar for each split and across classes. This, however, will be subject to the specifics of your dataset.
The ideal scenario is for all class ratios to be reasonably similar for each split and across classes. This, however, will be subject to the specifics of your dataset.
4. Next, we create the directories and dataset YAML files for each split.
4. Next, we create the directories and dataset YAML files for each split.
results[k] = model.metrics # save output metrics for further analysis
results[k] = model.metrics # save output metrics for further analysis
```
```
In this updated section, I have replaced manual string joining with the built-in `Path` method for constructing directories, which makes the code more Pythonic. I have also improved the explanation and clarity of the instructions.
## Conclusion
## Conclusion
In this guide, we have explored the process of using K-Fold cross-validation for training the YOLO object detection model. We learned how to split our dataset into K partitions, ensuring a balanced class distribution across the different folds.
In this guide, we have explored the process of using K-Fold cross-validation for training the YOLO object detection model. We learned how to split our dataset into K partitions, ensuring a balanced class distribution across the different folds.
@ -260,4 +258,4 @@ Finally, we implemented the actual model training using each split in a loop, sa
This technique of K-Fold cross-validation is a robust way of making the most out of your available data, and it helps to ensure that your model performance is reliable and consistent across different data subsets. This results in a more generalizable and reliable model that is less likely to overfit to specific data patterns.
This technique of K-Fold cross-validation is a robust way of making the most out of your available data, and it helps to ensure that your model performance is reliable and consistent across different data subsets. This results in a more generalizable and reliable model that is less likely to overfit to specific data patterns.
Remember that although we used YOLO in this guide, these steps are mostly transferable to other machine learning models. Understanding these steps allows you to apply cross-validation effectively in your own machine learning projects. Happy coding!
Remember that although we used YOLO in this guide, these steps are mostly transferable to other machine learning models. Understanding these steps allows you to apply cross-validation effectively in your own machine learning projects. Happy coding!
@ -483,7 +483,7 @@ masks, classification probabilities, etc.) found in the results object
## Streaming Source `for`-loop
## Streaming Source `for`-loop
Here's a Python script using OpenCV (cv2) and YOLOv8 to run inference on video frames. This script assumes you have already installed the necessary packages (opencv-python and ultralytics).
Here's a Python script using OpenCV (`cv2`) and YOLOv8 to run inference on video frames. This script assumes you have already installed the necessary packages (`opencv-python` and `ultralytics`).
!!! example "Streaming for-loop"
!!! example "Streaming for-loop"
@ -524,3 +524,5 @@ Here's a Python script using OpenCV (cv2) and YOLOv8 to run inference on video f
cap.release()
cap.release()
cv2.destroyAllWindows()
cv2.destroyAllWindows()
```
```
This script will run predictions on each frame of the video, visualize the results, and display them in a window. The loop can be exited by pressing 'q'.
Object tracking is a task that involves identifying the location and class of objects, then assigning a unique ID to
Object tracking is a task that involves identifying the location and class of objects, then assigning a unique ID to that detection in video streams.
that detection in video streams.
The output of tracker is the same as detection with an added object ID.
The output of tracker is the same as detection with an added object ID.
## Available Trackers
## Available Trackers
The following tracking algorithms have been implemented and can be enabled by passing `tracker=tracker_type.yaml`
Ultralytics YOLO supports the following tracking algorithms. They can be enabled by passing the relevant YAML configuration file such as `tracker=tracker_type.yaml`:
As in the above usage, we support both the detection and segmentation models for tracking and the only thing you need to
As can be seen in the above usage, tracking is available for all Detect, Segment and Pose models run on videos or streaming sources.
do is loading the corresponding (detection or segmentation) model.
## Configuration
## Configuration
### Tracking
### Tracking Arguments
Tracking configuration shares properties with Predict mode, such as `conf`, `iou`, and `show`. For further configurations, refer to the [Predict](https://docs.ultralytics.com/modes/predict/) model page.
Tracking shares the configuration with predict, i.e `conf`, `iou`, `show`. More configurations please refer
to [predict page](https://docs.ultralytics.com/modes/predict/).
!!! example ""
!!! example ""
=== "Python"
=== "Python"
@ -66,21 +69,22 @@ to [predict page](https://docs.ultralytics.com/modes/predict/).
```python
```python
from ultralytics import YOLO
from ultralytics import YOLO
# Configure the tracking parameters and run the tracker
# Configure tracking parameters and run the tracker using the command line interface
yolo track model=yolov8n.pt source="https://youtu.be/Zgi9g1ksQHc" conf=0.3, iou=0.5 show
yolo track model=yolov8n.pt source="https://youtu.be/Zgi9g1ksQHc" conf=0.3, iou=0.5 show
```
```
### Tracker
### Tracker Selection
Ultralytics also allows you to use a modified tracker configuration file. To do this, simply make a copy of a tracker config file (for example, `custom_tracker.yaml`) from [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers) and modify any configurations (except the `tracker_type`) as per your needs.
We also support using a modified tracker config file, just copy a config file i.e `custom_tracker.yaml`
from [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers) and modify
any configurations(expect the `tracker_type`) you need to.
!!! example ""
!!! example ""
=== "Python"
=== "Python"
@ -88,14 +92,126 @@ any configurations(expect the `tracker_type`) you need to.
```python
```python
from ultralytics import YOLO
from ultralytics import YOLO
# Load the model and run the tracker with a custom configuration file
Please refer to [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers)
For a comprehensive list of tracking arguments, refer to the [ultralytics/cfg/trackers](https://github.com/ultralytics/ultralytics/tree/main/ultralytics/cfg/trackers) page.
page
## Python Examples
### Persisting Tracks Loop
Here is a Python script using OpenCV (`cv2`) and YOLOv8 to run object tracking on video frames. This script still assumes you have already installed the necessary packages (`opencv-python` and `ultralytics`).
!!! example "Streaming for-loop with tracking"
```python
import cv2
from ultralytics import YOLO
# Load the YOLOv8 model
model = YOLO('yolov8n.pt')
# Open the video file
video_path = "path/to/your/video/file.mp4"
cap = cv2.VideoCapture(video_path)
# Loop through the video frames
while cap.isOpened():
# Read a frame from the video
success, frame = cap.read()
if success:
# Run YOLOv8 tracking on the frame, persisting tracks between frames
results = model.track(frame, persist=True)
# Visualize the results on the frame
annotated_frame = results[0].plot()
# Display the annotated frame
cv2.imshow("YOLOv8 Tracking", annotated_frame)
# Break the loop if 'q' is pressed
if cv2.waitKey(1) & 0xFF == ord("q"):
break
else:
# Break the loop if the end of the video is reached
break
# Release the video capture object and close the display window
cap.release()
cv2.destroyAllWindows()
```
Please note the change from `model(frame)` to `model.track(frame)`, which enables object tracking instead of simple detection. This modified script will run the tracker on each frame of the video, visualize the results, and display them in a window. The loop can be exited by pressing 'q'.
### Multithreaded Tracking
Multithreaded tracking provides the capability to run object tracking on multiple video streams simultaneously. This is particularly useful when handling multiple video inputs, such as from multiple surveillance cameras, where concurrent processing can greatly enhance efficiency and performance.
In the provided Python script, we make use of Python's `threading` module to run multiple instances of the tracker concurrently. Each thread is responsible for running the tracker on one video file, and all the threads run simultaneously in the background.
To ensure that each thread receives the correct parameters (the video file and the model to use), we define a function `run_tracker_in_thread` that accepts these parameters and contains the main tracking loop. This function reads the video frame by frame, runs the tracker, and displays the results.
Two different models are used in this example: `yolov8n.pt` and `yolov8n-seg.pt`, each tracking objects in a different video file. The video files are specified in `video_file1` and `video_file2`.
The `daemon=True` parameter in `threading.Thread` means that these threads will be closed as soon as the main program finishes. We then start the threads with `start()` and use `join()` to make the main thread wait until both tracker threads have finished.
Finally, after all threads have completed their task, the windows displaying the results are closed using `cv2.destroyAllWindows()`.
"Speed: 0.6ms preprocess, 60.9ms inference, 301.3ms postprocess per image at shape (1, 3, 640, 640)\n",
"Speed: 13.7ms preprocess, 365.8ms inference, 431.7ms postprocess per image at shape (1, 3, 384, 640)\n",
"Results saved to \u001b[1mruns/detect/predict\u001b[0m\n"
"Results saved to \u001b[1mruns/detect/predict\u001b[0m\n"
]
]
}
}
@ -139,7 +139,7 @@
},
},
"source": [
"source": [
"# 2. Val\n",
"# 2. Val\n",
"Validate a model's accuracy on the [COCO](https://cocodataset.org/#home) dataset's `val` or `test` splits. The latest YOLOv8 [models](https://github.com/ultralytics/ultralytics#models) are downloaded automatically the first time they are used. See [YOLOv8 Val Docs](https://docs.ultralytics.com/modes/val/) for more information."
"Validate a model's accuracy on the [COCO](https://docs.ultralytics.com/datasets/detect/coco/) dataset's `val` or `test` splits. The latest YOLOv8 [models](https://github.com/ultralytics/ultralytics#models) are downloaded automatically the first time they are used. See [YOLOv8 Val Docs](https://docs.ultralytics.com/modes/val/) for more information."
" Class Images Instances Box(P R mAP50 mAP50-95): 100% 4/4 [00:04<00:00, 1.21s/it]\n",
"/usr/local/lib/python3.10/dist-packages/torch/optim/lr_scheduler.py:139: UserWarning: Detected call of `lr_scheduler.step()` before `optimizer.step()`. In PyTorch 1.1.0 and later, you should call them in the opposite order: `optimizer.step()` before `lr_scheduler.step()`. Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate\n",
" all 128 929 0.631 0.549 0.614 0.455\n",
" warnings.warn(\"Detected call of `lr_scheduler.step()` before `optimizer.step()`. \"\n",
" Class Images Instances Box(P R mAP50 mAP50-95): 100% 1/1 [00:00<00:00, 2.21it/s]\n",
Glenn Jocher
1 year ago
committed by
GitHub