HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

Fix mkdocs.yml raw image URLs (#14213)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-07-05 02:25:02 +02:00 • committed by GitHub
parent d5db9c916f
commit 5d479c73c2
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
69 changed files with 4767 additions and 223 deletions
Download patch file Download diff file Expand all files Collapse all files

182
docs/en/help/FAQ.md
View file

@ -6,45 +6,45 @@ keywords: Ultralytics, YOLO, FAQ, object detection, hardware requirements, fine-
# Ultralytics YOLO Frequently Asked Questions (FAQ)
This FAQ section addresses some common questions and issues users might encounter while working with [Ultralytics](https://ultralytics.com) YOLO repositories.
This FAQ section addresses common questions and issues users might encounter while working with [Ultralytics](https://ultralytics.com) YOLO repositories.
## FAQ
### 1. What is Ultralytics and what does it offer?
### What is Ultralytics and what does it offer?
Ultralytics is a computer vision AI company that develops and maintains state-of-the-art object detection and image segmentation models, primarily focusing on the YOLO (You Only Look Once) family of models. Ultralytics offers:
Ultralytics is a computer vision AI company specializing in state-of-the-art object detection and image segmentation models, with a focus on the YOLO (You Only Look Once) family. Their offerings include:
- [Open-source implementations of YOLOv5 and YOLOv8](https://docs.ultralytics.com/models/yolov5/)
- [Pre-trained models for various computer vision tasks](https://docs.ultralytics.com/models/)
- [A Python package for easy integration of YOLO models into projects](https://docs.ultralytics.com/usage/python/)
- [Tools for training, testing, and deploying models](https://docs.ultralytics.com/modes/)
- [Extensive documentation and community support](https://docs.ultralytics.com/)
- Open-source implementations of [YOLOv5](https://docs.ultralytics.com/models/yolov5/) and [YOLOv8](https://docs.ultralytics.com/models/yolov8/)
- A wide range of [pre-trained models](https://docs.ultralytics.com/models/) for various computer vision tasks
- A comprehensive [Python package](https://docs.ultralytics.com/usage/python/) for seamless integration of YOLO models into projects
- Versatile [tools](https://docs.ultralytics.com/modes/) for training, testing, and deploying models
- [Extensive documentation](https://docs.ultralytics.com/) and a supportive community
### 2. How do I install the Ultralytics package?
### How do I install the Ultralytics package?
To install the Ultralytics package, you can use pip, the Python package manager. Open a terminal or command prompt and run:
Installing the Ultralytics package is straightforward using pip:
```
pip install ultralytics
```
For the latest development version, you can install directly from the GitHub repository:
For the latest development version, install directly from the GitHub repository:
```
pip install git+https://github.com/ultralytics/ultralytics.git
```
For more details, refer to the [quickstart guide](https://docs.ultralytics.com/quickstart/).
Detailed installation instructions can be found in the [quickstart guide](https://docs.ultralytics.com/quickstart/).
### 3. What are the system requirements for running Ultralytics models?
### What are the system requirements for running Ultralytics models?
Minimum requirements:
- Python 3.7 or later
- PyTorch 1.7 or later
- Python 3.7+
- PyTorch 1.7+
- CUDA-compatible GPU (for GPU acceleration)
Recommended:
Recommended setup:
- Python 3.8+
- PyTorch 1.10+
@ -52,9 +52,9 @@ Recommended:
- 8GB+ RAM
- 50GB+ free disk space (for dataset storage and model training)
For more information, visit [YOLO Common Issues](https://docs.ultralytics.com/guides/yolo-common-issues/).
For troubleshooting common issues, visit the [YOLO Common Issues](https://docs.ultralytics.com/guides/yolo-common-issues/) page.
### 4. How can I train a custom YOLOv8 model on my own dataset?
### How can I train a custom YOLOv8 model on my own dataset?
To train a custom YOLOv8 model:
@ -73,19 +73,19 @@ model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training)
results = model.train(data="path/to/your/data.yaml", epochs=100, imgsz=640)
```
For detailed instructions, refer to the [training guide](https://docs.ultralytics.com/modes/train/).
For a more in-depth guide, including data preparation and advanced training options, refer to the comprehensive [training guide](https://docs.ultralytics.com/modes/train/).
### 5. What pretrained models are available in Ultralytics?
### What pretrained models are available in Ultralytics?
Ultralytics offers a range of pretrained YOLOv8 models for various tasks:
Ultralytics offers a diverse range of pretrained YOLOv8 models for various tasks:
- Object Detection: YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x
- Instance Segmentation: YOLOv8n-seg, YOLOv8s-seg, YOLOv8m-seg, YOLOv8l-seg, YOLOv8x-seg
- Classification: YOLOv8n-cls, YOLOv8s-cls, YOLOv8m-cls, YOLOv8l-cls, YOLOv8x-cls
These models vary in size and complexity, offering different trade-offs between speed and accuracy. Learn more about [pretrained models](https://docs.ultralytics.com/models/yolov8/).
These models vary in size and complexity, offering different trade-offs between speed and accuracy. Explore the full range of [pretrained models](https://docs.ultralytics.com/models/yolov8/) to find the best fit for your project.
### 6. How do I perform inference using a trained Ultralytics model?
### How do I perform inference using a trained Ultralytics model?
To perform inference with a trained model:
@ -105,34 +105,34 @@ for r in results:
print(r.probs) # print class probabilities
```
For more details, visit the [prediction guide](https://docs.ultralytics.com/modes/predict/).
For advanced inference options, including batch processing and video inference, check out the detailed [prediction guide](https://docs.ultralytics.com/modes/predict/).
### 7. Can Ultralytics models be deployed on edge devices or in production environments?
### Can Ultralytics models be deployed on edge devices or in production environments?
Yes, Ultralytics models can be deployed on various platforms:
Absolutely! Ultralytics models are designed for versatile deployment across various platforms:
- Edge devices: Use TensorRT, ONNX, or OpenVINO for optimized inference on devices like NVIDIA Jetson or Intel Neural Compute Stick.
- Mobile: Convert models to TFLite or Core ML for deployment on Android or iOS devices.
- Cloud: Deploy models using frameworks like TensorFlow Serving or PyTorch Serve.
- Web: Use ONNX.js or TensorFlow.js for in-browser inference.
- Edge devices: Optimize inference on devices like NVIDIA Jetson or Intel Neural Compute Stick using TensorRT, ONNX, or OpenVINO.
- Mobile: Deploy on Android or iOS devices by converting models to TFLite or Core ML.
- Cloud: Leverage frameworks like TensorFlow Serving or PyTorch Serve for scalable cloud deployments.
- Web: Implement in-browser inference using ONNX.js or TensorFlow.js.
Ultralytics provides export functions to convert models to various formats for deployment. Learn more about [deployment options](https://docs.ultralytics.com/guides/model-deployment-options/).
Ultralytics provides export functions to convert models to various formats for deployment. Explore the wide range of [deployment options](https://docs.ultralytics.com/guides/model-deployment-options/) to find the best solution for your use case.
### 8. What's the difference between YOLOv5 and YOLOv8?
### What's the difference between YOLOv5 and YOLOv8?
Key differences include:
Key distinctions include:
- Architecture: YOLOv8 has an improved backbone and head design.
- Performance: YOLOv8 generally offers better accuracy and speed.
- Tasks: YOLOv8 natively supports object detection, instance segmentation, and classification.
- Codebase: YOLOv8 is implemented in a more modular and extensible manner.
- Training: YOLOv8 includes advanced training techniques like multi-dataset training and hyperparameter evolution.
- Architecture: YOLOv8 features an improved backbone and head design for enhanced performance.
- Performance: YOLOv8 generally offers superior accuracy and speed compared to YOLOv5.
- Tasks: YOLOv8 natively supports object detection, instance segmentation, and classification in a unified framework.
- Codebase: YOLOv8 is implemented with a more modular and extensible architecture, facilitating easier customization and extension.
- Training: YOLOv8 incorporates advanced training techniques like multi-dataset training and hyperparameter evolution for improved results.
For a detailed comparison, visit [YOLOv5 vs YOLOv8](https://www.ultralytics.com/yolo).
For an in-depth comparison of features and performance metrics, visit the [YOLOv5 vs YOLOv8](https://www.ultralytics.com/yolo) comparison page.
### 9. How can I contribute to the Ultralytics open-source project?
### How can I contribute to the Ultralytics open-source project?
To contribute:
Contributing to Ultralytics is a great way to improve the project and expand your skills. Here's how you can get involved:
1. Fork the Ultralytics repository on GitHub.
2. Create a new branch for your feature or bug fix.
@ -140,90 +140,90 @@ To contribute:
4. Submit a pull request with a clear description of your changes.
5. Participate in the code review process.
You can also contribute by reporting bugs, suggesting features, or improving documentation. Refer to the [contributing guide](https://docs.ultralytics.com/help/contributing/).
You can also contribute by reporting bugs, suggesting features, or improving documentation. For detailed guidelines and best practices, refer to the [contributing guide](https://docs.ultralytics.com/help/contributing/).
### 10. How do I install the Ultralytics package in Python?
### How do I install the Ultralytics package in Python?
To install the Ultralytics package in Python, you can use pip by running the following command in your terminal or command prompt:
Installing the Ultralytics package in Python is simple. Use pip by running the following command in your terminal or command prompt:
```bash
pip install ultralytics
```
If you want the latest development version, you can install it directly from the GitHub repository:
For the cutting-edge development version, install directly from the GitHub repository:
```bash
pip install git+https://github.com/ultralytics/ultralytics.git
```
For additional instructions and details, you can refer to the [quickstart guide](https://docs.ultralytics.com/quickstart/).
For environment-specific installation instructions and troubleshooting tips, consult the comprehensive [quickstart guide](https://docs.ultralytics.com/quickstart/).
### 11. What are the main features of Ultralytics YOLO?
### What are the main features of Ultralytics YOLO?
Ultralytics YOLO offers several advanced features to enhance object detection and image segmentation tasks:
Ultralytics YOLO boasts a rich set of features for advanced object detection and image segmentation:
- **Real-Time Detection:** Efficient detection and classification of objects in real-time.
- **Pre-Trained Models:** Access to a variety of pretrained models that balance speed and accuracy ([Pretrained Models](https://docs.ultralytics.com/models/yolov8/)).
- **Custom Training:** Easily fine-tune models on custom datasets ([Training Guide](https://docs.ultralytics.com/modes/train/)).
- **Wide Deployment Options:** Models can be exported to various formats like TensorRT, ONNX, and CoreML for deployment on different platforms ([Deployment Options](https://docs.ultralytics.com/guides/model-deployment-options/)).
- **Extensive Documentation:** Comprehensive documentation and community support to help users at all levels ([Documentation](https://docs.ultralytics.com/)).
- Real-Time Detection: Efficiently detect and classify objects in real-time scenarios.
- Pre-Trained Models: Access a variety of [pretrained models](https://docs.ultralytics.com/models/yolov8/) that balance speed and accuracy for different use cases.
- Custom Training: Easily fine-tune models on custom datasets with the flexible [training pipeline](https://docs.ultralytics.com/modes/train/).
- Wide [Deployment Options](https://docs.ultralytics.com/guides/model-deployment-options/): Export models to various formats like TensorRT, ONNX, and CoreML for deployment across different platforms.
- Extensive Documentation: Benefit from comprehensive [documentation](https://docs.ultralytics.com/) and a supportive community to guide you through your computer vision journey.
For further information, you can explore the [YOLO models page](https://docs.ultralytics.com/models/yolov8/).
Explore the [YOLO models page](https://docs.ultralytics.com/models/yolov8/) for an in-depth look at the capabilities and architectures of different YOLO versions.
### 12. How can I improve the performance of my YOLO model?
### How can I improve the performance of my YOLO model?
Improving the performance of your YOLO model can be achieved through several techniques:
Enhancing your YOLO model's performance can be achieved through several techniques:
1. **Hyperparameter Tuning:** Experiment with different hyperparameters to optimize model performance ([Hyperparameter Tuning Guide](https://docs.ultralytics.com/guides/hyperparameter-tuning/)).
2. **Data Augmentation:** Use techniques like flip, scale, rotate, and color adjustments to enhance your training dataset.
3. **Transfer Learning:** Start with a pre-trained model and fine-tune it on your specific dataset ([Train YOLOv8](https://docs.ultralytics.com/modes/train/)).
4. **Export to Efficient Formats:** Export your model to optimized formats like TensorRT or ONNX for faster inference ([Export](../modes/export.md)).
5. **Benchmarking:** Use the benchmarking tools available to measure and improve the inference speed and accuracy ([Benchmark Mode](https://docs.ultralytics.com/modes/benchmark/)).
1. Hyperparameter Tuning: Experiment with different hyperparameters using the [Hyperparameter Tuning Guide](https://docs.ultralytics.com/guides/hyperparameter-tuning/) to optimize model performance.
2. Data Augmentation: Implement techniques like flip, scale, rotate, and color adjustments to enhance your training dataset and improve model generalization.
3. Transfer Learning: Leverage pre-trained models and fine-tune them on your specific dataset using the [Train YOLOv8](https://docs.ultralytics.com/modes/train/) guide.
4. Export to Efficient Formats: Convert your model to optimized formats like TensorRT or ONNX for faster inference using the [Export guide](../modes/export.md).
5. Benchmarking: Utilize the [Benchmark Mode](https://docs.ultralytics.com/modes/benchmark/) to measure and improve inference speed and accuracy systematically.
### 13. Can I deploy Ultralytics YOLO models on mobile and edge devices?
### Can I deploy Ultralytics YOLO models on mobile and edge devices?
Yes, you can deploy Ultralytics YOLO models on mobile and edge devices by converting them to supported formats. Here are some options:
Yes, Ultralytics YOLO models are designed for versatile deployment, including mobile and edge devices:
- **Mobile:** Convert models to TFLite or CoreML for integration into Android or iOS apps ([TFLite Integration Guide](https://docs.ultralytics.com/integrations/tflite/) and [CoreML Integration Guide](https://docs.ultralytics.com/integrations/coreml/)).
- **Edge Devices:** Use TensorRT or ONNX for optimized inference on devices like NVIDIA Jetson or other edge hardware ([Edge TPU Integration Guide](https://docs.ultralytics.com/integrations/edge-tpu/)).
- Mobile: Convert models to TFLite or CoreML for seamless integration into Android or iOS apps. Refer to the [TFLite Integration Guide](https://docs.ultralytics.com/integrations/tflite/) and [CoreML Integration Guide](https://docs.ultralytics.com/integrations/coreml/) for platform-specific instructions.
- Edge Devices: Optimize inference on devices like NVIDIA Jetson or other edge hardware using TensorRT or ONNX. The [Edge TPU Integration Guide](https://docs.ultralytics.com/integrations/edge-tpu/) provides detailed steps for edge deployment.
For detailed instructions on different deployment options, visit the [deployment options guide](https://docs.ultralytics.com/guides/model-deployment-options/).
For a comprehensive overview of deployment strategies across various platforms, consult the [deployment options guide](https://docs.ultralytics.com/guides/model-deployment-options/).
### 14. How can I perform inference using a trained Ultralytics YOLO model?
### How can I perform inference using a trained Ultralytics YOLO model?
To perform inference using a trained Ultralytics YOLO model, follow these steps:
Performing inference with a trained Ultralytics YOLO model is straightforward:
1. **Load the Model:**
1. Load the Model:
```python
from ultralytics import YOLO
```python
from ultralytics import YOLO
model = YOLO("path/to/your/model.pt")
```
model = YOLO("path/to/your/model.pt")
```
2. **Run Inference:**
2. Run Inference:
```python
results = model("path/to/image.jpg")
```python
results = model("path/to/image.jpg")
for r in results:
print(r.boxes) # print bounding box predictions
print(r.masks) # print mask predictions
print(r.probs) # print class probabilities
```
for r in results:
print(r.boxes) # print bounding box predictions
print(r.masks) # print mask predictions
print(r.probs) # print class probabilities
```
For more detailed instructions, check out the [prediction guide](https://docs.ultralytics.com/modes/predict/).
For advanced inference techniques, including batch processing, video inference, and custom preprocessing, refer to the detailed [prediction guide](https://docs.ultralytics.com/modes/predict/).
### 15. Where can I find examples and tutorials for using Ultralytics?
### Where can I find examples and tutorials for using Ultralytics?
You can find examples and tutorials in several places:
Ultralytics provides a wealth of resources to help you get started and master their tools:
- 📚 [Official documentation](https://docs.ultralytics.com/)
- 💻 [GitHub repository](https://github.com/ultralytics/ultralytics)
- ✍️ [Ultralytics blog](https://www.ultralytics.com/blog)
- 💬 [Community forums](https://community.ultralytics.com/)
- 🎥 [YouTube channel](https://youtube.com/ultralytics?sub_confirmation=1)
- 📚 [Official documentation](https://docs.ultralytics.com/): Comprehensive guides, API references, and best practices.
- 💻 [GitHub repository](https://github.com/ultralytics/ultralytics): Source code, example scripts, and community contributions.
- ✍️ [Ultralytics blog](https://www.ultralytics.com/blog): In-depth articles, use cases, and technical insights.
- 💬 [Community forums](https://community.ultralytics.com/): Connect with other users, ask questions, and share your experiences.
- 🎥 [YouTube channel](https://youtube.com/ultralytics?sub_confirmation=1): Video tutorials, demos, and webinars on various Ultralytics topics.
These resources provide code examples, use cases, and step-by-step guides for various tasks using Ultralytics models.
These resources provide code examples, real-world use cases, and step-by-step guides for various tasks using Ultralytics models.
If you have any more questions or need assistance, don't hesitate to consult the Ultralytics documentation or reach out to the community through [GitHub Issues](https://github.com/ultralytics/ultralytics/issues) or the official [discussion forum](https://github.com/orgs/ultralytics/discussions).
If you need further assistance, don't hesitate to consult the Ultralytics documentation or reach out to the community through [GitHub Issues](https://github.com/ultralytics/ultralytics/issues) or the official [discussion forum](https://github.com/orgs/ultralytics/discussions).