description: Enhance YOLO11 performance using Neural Magic's DeepSparse Engine. Learn how to deploy and benchmark YOLO11 models on CPUs for efficient object detection.
keywords: YOLO11, DeepSparse, Neural Magic, model optimization, object detection, inference speed, CPU performance, sparsity, pruning, quantization
When deploying [object detection](https://www.ultralytics.com/glossary/object-detection) models like [Ultralytics YOLO11](https://www.ultralytics.com/) on various hardware, you can bump into unique issues like optimization. This is where YOLO11's integration with Neural Magic's DeepSparse Engine steps in. It transforms the way YOLO11 models are executed and enables GPU-level performance directly on CPUs.
This guide shows you how to deploy YOLO11 using Neural Magic's DeepSparse, how to run inferences, and also how to benchmark performance to ensure it is optimized.
[Neural Magic's DeepSparse](https://neuralmagic.com/deepsparse/) is an inference run-time designed to optimize the execution of neural networks on CPUs. It applies advanced techniques like sparsity, pruning, and quantization to dramatically reduce computational demands while maintaining accuracy. DeepSparse offers an agile solution for efficient and scalable [neural network](https://www.ultralytics.com/glossary/neural-network-nn) execution across various devices.
- **Enhanced Inference Speed**: Achieves up to 525 FPS (on YOLO11n), significantly speeding up YOLO11's inference capabilities compared to traditional methods.
- **Optimized Model Efficiency**: Uses pruning and quantization to enhance YOLO11's efficiency, reducing model size and computational requirements while maintaining [accuracy](https://www.ultralytics.com/glossary/accuracy).
- **High Performance on Standard CPUs**: Delivers GPU-like performance on CPUs, providing a more accessible and cost-effective option for various applications.
- **Streamlined Integration and Deployment**: Offers user-friendly tools for easy integration of YOLO11 into applications, including image and video annotation features.
Neural Magic's Deep Sparse technology is inspired by the human brain's efficiency in neural network computation. It adopts two key principles from the brain as follows:
- **Sparsity**: The process of sparsification involves pruning redundant information from [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) networks, leading to smaller and faster models without compromising accuracy. This technique reduces the network's size and computational needs significantly.
- **Locality of Reference**: DeepSparse uses a unique execution method, breaking the network into Tensor Columns. These columns are executed depth-wise, fitting entirely within the CPU's cache. This approach mimics the brain's efficiency, minimizing data movement and maximizing the CPU's cache use.
For more details on how Neural Magic's DeepSparse technology work, check out [their blog post](https://neuralmagic.com/blog/how-neural-magics-deep-sparse-technology-works/).
SparseZoo, an open-source model repository by Neural Magic, offers [a collection of pre-sparsified YOLO11 model checkpoints](https://sparsezoo.neuralmagic.com/?modelSet=computer_vision&searchModels=yolo). With SparseML, seamlessly integrated with Ultralytics, users can effortlessly fine-tune these sparse checkpoints on their specific datasets using a straightforward command-line interface.
Checkout [Neural Magic's SparseML YOLO11 documentation](https://github.com/neuralmagic/sparseml/tree/main/integrations/ultralytics-yolov8) for more details.
Deploying YOLO11 with Neural Magic's DeepSparse involves a few straightforward steps. 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. Here's how you can get started.
DeepSparse Engine requires YOLO11 models in ONNX format. Exporting your model to this format is essential for compatibility with DeepSparse. Use the following command to export YOLO11 models:
It's important to check that your YOLO11 model is performing optimally on DeepSparse. You can benchmark your model's performance to analyze throughput and latency:
Running the annotate command processes your specified image, detecting objects, and saving the annotated image with bounding boxes and classifications. The annotated image will be stored in an annotation-results folder. This helps provide a visual representation of the model's detection capabilities.
After running the eval command, you will receive detailed output metrics such as [precision](https://www.ultralytics.com/glossary/precision), [recall](https://www.ultralytics.com/glossary/recall), and mAP (mean Average Precision). This provides a comprehensive view of your model's performance on the dataset. This functionality is particularly useful for fine-tuning and optimizing your YOLO11 models for specific use cases, ensuring high accuracy and efficiency.
This guide explored integrating Ultralytics' YOLO11 with Neural Magic's DeepSparse Engine. It highlighted how this integration enhances YOLO11's performance on CPU platforms, offering GPU-level efficiency and advanced neural network sparsity techniques.
For more detailed information and advanced usage, visit [Neural Magic's DeepSparse documentation](https://docs.neuralmagic.com/products/deepsparse/). Also, check out Neural Magic's documentation on the integration with YOLO11 [here](https://github.com/neuralmagic/deepsparse/tree/main/src/deepsparse/yolov8#yolov8-inference-pipelines) and watch a great session on it [here](https://www.youtube.com/watch?v=qtJ7bdt52x8).
Additionally, for a broader understanding of various YOLO11 integrations, visit the [Ultralytics integration guide page](../integrations/index.md), where you can discover a range of other exciting integration possibilities.
Neural Magic's DeepSparse Engine is an inference runtime designed to optimize the execution of neural networks on CPUs through advanced techniques such as sparsity, pruning, and quantization. By integrating DeepSparse with YOLO11, you can achieve GPU-like performance on standard CPUs, significantly enhancing inference speed, model efficiency, and overall performance while maintaining accuracy. For more details, check out the [Neural Magic's DeepSparse section](#neural-magics-deepsparse).
Installing the required packages for deploying YOLO11 with Neural Magic's DeepSparse is straightforward. You can easily install them using the CLI. Here's the command you need to run:
Once installed, follow the steps provided in the [Installation section](#step-1-installation) to set up your environment and start using DeepSparse with YOLO11.
This command will export your YOLO11 model (`yolo11n.pt`) to a format (`yolo11n.onnx`) that can be utilized by the DeepSparse Engine. More information about model export can be found in the [Model Export section](#step-2-exporting-yolo11-to-onnx-format).
Benchmarking YOLO11 performance on DeepSparse helps you analyze throughput and latency to ensure your model is optimized. You can use the following CLI command to run a benchmark:
This command will provide you with vital performance metrics. For more details, see the [Benchmarking Performance section](#step-4-benchmarking-performance).
- **Optimized Model Efficiency:** Uses sparsity, pruning, and quantization techniques to reduce model size and computational needs while maintaining accuracy.
- **High Performance on Standard CPUs:** Offers GPU-like performance on cost-effective CPU hardware.
- **Streamlined Integration:** User-friendly tools for easy deployment and integration.
For a deeper dive into these advantages, visit the [Benefits of Integrating Neural Magic's DeepSparse with YOLO11 section](#benefits-of-integrating-neural-magics-deepsparse-with-yolo11).
