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

Optimize Docs images (#15900)

Browse source 
Signed-off-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Muhammad Rizwan Munawar 2024-08-30 05:52:10 +05:00 • committed by GitHub
parent 0f9f7b806c
commit cfebb5f26b
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
174 changed files with 537 additions and 537 deletions
Download patch file Download diff file Expand all files Collapse all files

10
docs/en/integrations/neural-magic.md
View file

@ -13,7 +13,7 @@ This guide shows you how to deploy YOLOv8 using Neural Magic's DeepSparse, how t
## Neural Magic's DeepSparse
<p align="center">
<img width="640" src="https://docs.neuralmagic.com/assets/images/nm-flows-55d56c0695a30bf9ecb716ea98977a95.png" alt="Neural Magic's DeepSparse Overview">
<img width="640" src="https://github.com/ultralytics/docs/releases/download/0/neural-magic-deepsparse-overview.avif" alt="Neural Magic's DeepSparse Overview">
</p>
[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 execution across various devices.
@ -25,13 +25,13 @@ Before diving into how to deploy YOLOV8 using DeepSparse, let's understand the b
- **Enhanced Inference Speed**: Achieves up to 525 FPS (on YOLOv8n), significantly speeding up YOLOv8's inference capabilities compared to traditional methods.
<p align="center">
<img width="640" src="https://neuralmagic.com/wp-content/uploads/2023/04/image1.png" alt="Enhanced Inference Speed">
<img width="640" src="https://github.com/ultralytics/docs/releases/download/0/enhanced-inference-speed.avif" alt="Enhanced Inference Speed">
</p>
- **Optimized Model Efficiency**: Uses pruning and quantization to enhance YOLOv8's efficiency, reducing model size and computational requirements while maintaining accuracy.
<p align="center">
<img width="640" src="https://neuralmagic.com/wp-content/uploads/2023/04/YOLOv8-charts-Page-1.drawio.png" alt="Optimized Model Efficiency">
<img width="640" src="https://github.com/ultralytics/docs/releases/download/0/optimized-model-efficiency.avif" alt="Optimized Model Efficiency">
</p>
- **High Performance on Standard CPUs**: Delivers GPU-like performance on CPUs, providing a more accessible and cost-effective option for various applications.
@ -51,7 +51,7 @@ Neural Magic's Deep Sparse technology is inspired by the human brain's efficienc
- **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.
<p align="center">
<img width="640" src="https://neuralmagic.com/wp-content/uploads/2021/03/Screen-Shot-2021-03-16-at-11.09.45-AM.png" alt="How Neural Magic's DeepSparse Technology Works ">
<img width="640" src="https://github.com/ultralytics/docs/releases/download/0/neural-magic-deepsparse-technology.avif" alt="How Neural Magic's DeepSparse Technology Works ">
</p>
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/).
@ -148,7 +148,7 @@ DeepSparse provides additional features for practical integration of YOLOv8 in a
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.
<p align="center">
<img width="640" src="https://user-images.githubusercontent.com/3195154/211942937-1d32193a-6dda-473d-a7ad-e2162bbb42e9.png" alt="Image Annotation Feature">
<img width="640" src="https://github.com/ultralytics/docs/releases/download/0/image-annotation-feature.avif" alt="Image Annotation Feature">
</p>
After running the eval command, you will receive detailed output metrics such as precision, 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 YOLOv8 models for specific use cases, ensuring high accuracy and efficiency.