Update YOLO11 Actions and Docs (#16596)
Signed-off-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Ultralytics Assistant
GitHub
parent
51e93d6111
commit
97f38409fb
124 changed files with 1948 additions and 1948 deletions
|
|
@ -1,14 +1,14 @@
|
|||
---
|
||||
comments: true
|
||||
description: Unlock seamless YOLOv8 tracking with DVCLive. Discover how to log, visualize, and analyze experiments for optimized ML model performance.
|
||||
keywords: YOLOv8, DVCLive, experiment tracking, machine learning, model training, data visualization, Git integration
|
||||
description: Unlock seamless YOLO11 tracking with DVCLive. Discover how to log, visualize, and analyze experiments for optimized ML model performance.
|
||||
keywords: YOLO11, DVCLive, experiment tracking, machine learning, model training, data visualization, Git integration
|
||||
---
|
||||
|
||||
# Advanced YOLOv8 Experiment Tracking with DVCLive
|
||||
# Advanced YOLO11 Experiment Tracking with DVCLive
|
||||
|
||||
Experiment tracking in [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) is critical to model development and evaluation. It involves recording and analyzing various parameters, metrics, and outcomes from numerous training runs. This process is essential for understanding model performance and making data-driven decisions to refine and optimize models.
|
||||
|
||||
Integrating DVCLive with [Ultralytics YOLOv8](https://www.ultralytics.com/) transforms the way experiments are tracked and managed. This integration offers a seamless solution for automatically logging key experiment details, comparing results across different runs, and visualizing data for in-depth analysis. In this guide, we'll understand how DVCLive can be used to streamline the process.
|
||||
Integrating DVCLive with [Ultralytics YOLO11](https://www.ultralytics.com/) transforms the way experiments are tracked and managed. This integration offers a seamless solution for automatically logging key experiment details, comparing results across different runs, and visualizing data for in-depth analysis. In this guide, we'll understand how DVCLive can be used to streamline the process.
|
||||
|
||||
## DVCLive
|
||||
|
||||
|
|
@ -18,9 +18,9 @@ Integrating DVCLive with [Ultralytics YOLOv8](https://www.ultralytics.com/) tran
|
|||
|
||||
[DVCLive](https://dvc.org/doc/dvclive), developed by DVC, is an innovative open-source tool for experiment tracking in machine learning. Integrating seamlessly with Git and DVC, it automates the logging of crucial experiment data like model parameters and training metrics. Designed for simplicity, DVCLive enables effortless comparison and analysis of multiple runs, enhancing the efficiency of machine learning projects with intuitive [data visualization](https://www.ultralytics.com/glossary/data-visualization) and analysis tools.
|
||||
|
||||
## YOLOv8 Training with DVCLive
|
||||
## YOLO11 Training with DVCLive
|
||||
|
||||
YOLOv8 training sessions can be effectively monitored with DVCLive. Additionally, DVC provides integral features for visualizing these experiments, including the generation of a report that enables the comparison of metric plots across all tracked experiments, offering a comprehensive view of the training process.
|
||||
YOLO11 training sessions can be effectively monitored with DVCLive. Additionally, DVC provides integral features for visualizing these experiments, including the generation of a report that enables the comparison of metric plots across all tracked experiments, offering a comprehensive view of the training process.
|
||||
|
||||
## Installation
|
||||
|
||||
|
|
@ -31,11 +31,11 @@ To install the required packages, run:
|
|||
=== "CLI"
|
||||
|
||||
```bash
|
||||
# Install the required packages for YOLOv8 and DVCLive
|
||||
# Install the required packages for YOLO11 and DVCLive
|
||||
pip install ultralytics dvclive
|
||||
```
|
||||
|
||||
For detailed instructions and best practices related to the installation process, be sure to check our [YOLOv8 Installation guide](../quickstart.md). While installing the required packages for YOLOv8, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips.
|
||||
For detailed instructions and best practices related to the installation process, be sure to check our [YOLO11 Installation guide](../quickstart.md). While installing the required packages for YOLO11, if you encounter any difficulties, consult our [Common Issues guide](../guides/yolo-common-issues.md) for solutions and tips.
|
||||
|
||||
## Configuring DVCLive
|
||||
|
||||
|
|
@ -66,27 +66,27 @@ In these commands, ensure to replace "you@example.com" with the email address as
|
|||
|
||||
## Usage
|
||||
|
||||
Before diving into the usage instructions, be sure to check out the range of [YOLOv8 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements.
|
||||
Before diving into the usage instructions, be sure to check out the range of [YOLO11 models offered by Ultralytics](../models/index.md). This will help you choose the most appropriate model for your project requirements.
|
||||
|
||||
### Training YOLOv8 Models with DVCLive
|
||||
### Training YOLO11 Models with DVCLive
|
||||
|
||||
Start by running your YOLOv8 training sessions. You can use different model configurations and training parameters to suit your project needs. For instance:
|
||||
Start by running your YOLO11 training sessions. You can use different model configurations and training parameters to suit your project needs. For instance:
|
||||
|
||||
```bash
|
||||
# Example training commands for YOLOv8 with varying configurations
|
||||
yolo train model=yolov8n.pt data=coco8.yaml epochs=5 imgsz=512
|
||||
yolo train model=yolov8n.pt data=coco8.yaml epochs=5 imgsz=640
|
||||
# Example training commands for YOLO11 with varying configurations
|
||||
yolo train model=yolo11n.pt data=coco8.yaml epochs=5 imgsz=512
|
||||
yolo train model=yolo11n.pt data=coco8.yaml epochs=5 imgsz=640
|
||||
```
|
||||
|
||||
Adjust the model, data, [epochs](https://www.ultralytics.com/glossary/epoch), and imgsz parameters according to your specific requirements. For a detailed understanding of the model training process and best practices, refer to our [YOLOv8 Model Training guide](../modes/train.md).
|
||||
Adjust the model, data, [epochs](https://www.ultralytics.com/glossary/epoch), and imgsz parameters according to your specific requirements. For a detailed understanding of the model training process and best practices, refer to our [YOLO11 Model Training guide](../modes/train.md).
|
||||
|
||||
### Monitoring Experiments with DVCLive
|
||||
|
||||
DVCLive enhances the training process by enabling the tracking and visualization of key metrics. When installed, Ultralytics YOLOv8 automatically integrates with DVCLive for experiment tracking, which you can later analyze for performance insights. For a comprehensive understanding of the specific performance metrics used during training, be sure to explore [our detailed guide on performance metrics](../guides/yolo-performance-metrics.md).
|
||||
DVCLive enhances the training process by enabling the tracking and visualization of key metrics. When installed, Ultralytics YOLO11 automatically integrates with DVCLive for experiment tracking, which you can later analyze for performance insights. For a comprehensive understanding of the specific performance metrics used during training, be sure to explore [our detailed guide on performance metrics](../guides/yolo-performance-metrics.md).
|
||||
|
||||
### Analyzing Results
|
||||
|
||||
After your YOLOv8 training sessions are complete, you can leverage DVCLive's powerful visualization tools for in-depth analysis of the results. DVCLive's integration ensures that all training metrics are systematically logged, facilitating a comprehensive evaluation of your model's performance.
|
||||
After your YOLO11 training sessions are complete, you can leverage DVCLive's powerful visualization tools for in-depth analysis of the results. DVCLive's integration ensures that all training metrics are systematically logged, facilitating a comprehensive evaluation of your model's performance.
|
||||
|
||||
To start the analysis, you can extract the experiment data using DVC's API and process it with Pandas for easier handling and visualization:
|
||||
|
||||
|
|
@ -108,7 +108,7 @@ df.reset_index(drop=True, inplace=True)
|
|||
print(df)
|
||||
```
|
||||
|
||||
The output of the code snippet above provides a clear tabular view of the different experiments conducted with YOLOv8 models. Each row represents a different training run, detailing the experiment's name, the number of epochs, image size (imgsz), the specific model used, and the mAP50-95(B) metric. This metric is crucial for evaluating the model's [accuracy](https://www.ultralytics.com/glossary/accuracy), with higher values indicating better performance.
|
||||
The output of the code snippet above provides a clear tabular view of the different experiments conducted with YOLO11 models. Each row represents a different training run, detailing the experiment's name, the number of epochs, image size (imgsz), the specific model used, and the mAP50-95(B) metric. This metric is crucial for evaluating the model's [accuracy](https://www.ultralytics.com/glossary/accuracy), with higher values indicating better performance.
|
||||
|
||||
#### Visualizing Results with Plotly
|
||||
|
||||
|
|
@ -164,7 +164,7 @@ Based on your analysis, iterate on your experiments. Adjust model configurations
|
|||
|
||||
## Summary
|
||||
|
||||
This guide has led you through the process of integrating DVCLive with Ultralytics' YOLOv8. You have learned how to harness the power of DVCLive for detailed experiment monitoring, effective visualization, and insightful analysis in your machine learning endeavors.
|
||||
This guide has led you through the process of integrating DVCLive with Ultralytics' YOLO11. You have learned how to harness the power of DVCLive for detailed experiment monitoring, effective visualization, and insightful analysis in your machine learning endeavors.
|
||||
|
||||
For further details on usage, visit [DVCLive's official documentation](https://dvc.org/doc/dvclive/ml-frameworks/yolo).
|
||||
|
||||
|
|
@ -172,9 +172,9 @@ Additionally, explore more integrations and capabilities of Ultralytics by visit
|
|||
|
||||
## FAQ
|
||||
|
||||
### How do I integrate DVCLive with Ultralytics YOLOv8 for experiment tracking?
|
||||
### How do I integrate DVCLive with Ultralytics YOLO11 for experiment tracking?
|
||||
|
||||
Integrating DVCLive with Ultralytics YOLOv8 is straightforward. Start by installing the necessary packages:
|
||||
Integrating DVCLive with Ultralytics YOLO11 is straightforward. Start by installing the necessary packages:
|
||||
|
||||
!!! example "Installation"
|
||||
|
||||
|
|
@ -198,21 +198,21 @@ Next, initialize a Git repository and configure DVCLive in your project:
|
|||
git commit -m "DVC init"
|
||||
```
|
||||
|
||||
Follow our [YOLOv8 Installation guide](../quickstart.md) for detailed setup instructions.
|
||||
Follow our [YOLO11 Installation guide](../quickstart.md) for detailed setup instructions.
|
||||
|
||||
### Why should I use DVCLive for tracking YOLOv8 experiments?
|
||||
### Why should I use DVCLive for tracking YOLO11 experiments?
|
||||
|
||||
Using DVCLive with YOLOv8 provides several advantages, such as:
|
||||
Using DVCLive with YOLO11 provides several advantages, such as:
|
||||
|
||||
- **Automated Logging**: DVCLive automatically records key experiment details like model parameters and metrics.
|
||||
- **Easy Comparison**: Facilitates comparison of results across different runs.
|
||||
- **Visualization Tools**: Leverages DVCLive's robust data visualization capabilities for in-depth analysis.
|
||||
|
||||
For further details, refer to our guide on [YOLOv8 Model Training](../modes/train.md) and [YOLO Performance Metrics](../guides/yolo-performance-metrics.md) to maximize your experiment tracking efficiency.
|
||||
For further details, refer to our guide on [YOLO11 Model Training](../modes/train.md) and [YOLO Performance Metrics](../guides/yolo-performance-metrics.md) to maximize your experiment tracking efficiency.
|
||||
|
||||
### How can DVCLive improve my results analysis for YOLOv8 training sessions?
|
||||
### How can DVCLive improve my results analysis for YOLO11 training sessions?
|
||||
|
||||
After completing your YOLOv8 training sessions, DVCLive helps in visualizing and analyzing the results effectively. Example code for loading and displaying experiment data:
|
||||
After completing your YOLO11 training sessions, DVCLive helps in visualizing and analyzing the results effectively. Example code for loading and displaying experiment data:
|
||||
|
||||
```python
|
||||
import dvc.api
|
||||
|
|
@ -241,11 +241,11 @@ fig = parallel_coordinates(df, columns, color="metrics.mAP50-95(B)")
|
|||
fig.show()
|
||||
```
|
||||
|
||||
Refer to our guide on [YOLOv8 Training with DVCLive](#yolov8-training-with-dvclive) for more examples and best practices.
|
||||
Refer to our guide on [YOLO11 Training with DVCLive](#yolo11-training-with-dvclive) for more examples and best practices.
|
||||
|
||||
### What are the steps to configure my environment for DVCLive and YOLOv8 integration?
|
||||
### What are the steps to configure my environment for DVCLive and YOLO11 integration?
|
||||
|
||||
To configure your environment for a smooth integration of DVCLive and YOLOv8, follow these steps:
|
||||
To configure your environment for a smooth integration of DVCLive and YOLO11, follow these steps:
|
||||
|
||||
1. **Install Required Packages**: Use `pip install ultralytics dvclive`.
|
||||
2. **Initialize Git Repository**: Run `git init -q`.
|
||||
|
|
@ -254,9 +254,9 @@ To configure your environment for a smooth integration of DVCLive and YOLOv8, fo
|
|||
|
||||
These steps ensure proper version control and setup for experiment tracking. For in-depth configuration details, visit our [Configuration guide](../quickstart.md).
|
||||
|
||||
### How do I visualize YOLOv8 experiment results using DVCLive?
|
||||
### How do I visualize YOLO11 experiment results using DVCLive?
|
||||
|
||||
DVCLive offers powerful tools to visualize the results of YOLOv8 experiments. Here's how you can generate comparative plots:
|
||||
DVCLive offers powerful tools to visualize the results of YOLO11 experiments. Here's how you can generate comparative plots:
|
||||
|
||||
!!! example "Generate Comparative Plots"
|
||||
|
||||
|
|
@ -275,4 +275,4 @@ from IPython.display import HTML
|
|||
HTML(filename="./dvc_plots/index.html")
|
||||
```
|
||||
|
||||
These visualizations help identify trends and optimize model performance. Check our detailed guides on [YOLOv8 Experiment Analysis](#analyzing-results) for comprehensive steps and examples.
|
||||
These visualizations help identify trends and optimize model performance. Check our detailed guides on [YOLO11 Experiment Analysis](#analyzing-results) for comprehensive steps and examples.
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue