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

Add Docs glossary links (#16448)

Browse source 
Signed-off-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher 2024-09-23 23:48:46 +02:00 • committed by GitHub
parent 8b8c25f216
commit 443fbce194
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
193 changed files with 1124 additions and 1124 deletions
Download patch file Download diff file Expand all files Collapse all files

72
docs/en/integrations/openvino.md
View file

@ -10,7 +10,7 @@ keywords: YOLOv8, OpenVINO, model export, Intel, AI inference, CPU speedup, GPU
In this guide, we cover exporting YOLOv8 models to the [OpenVINO](https://docs.openvino.ai/) format, which can provide up to 3x [CPU](https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/cpu-device.html) speedup, as well as accelerating YOLO inference on Intel [GPU](https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/gpu-device.html) and [NPU](https://docs.openvino.ai/2024/openvino-workflow/running-inference/inference-devices-and-modes/npu-device.html) hardware.
OpenVINO, short for Open Visual Inference & Neural Network Optimization toolkit, is a comprehensive toolkit for optimizing and deploying AI inference models. Even though the name contains Visual, OpenVINO also supports various additional tasks including language, audio, time series, etc.
OpenVINO, short for Open Visual Inference & [Neural Network](https://www.ultralytics.com/glossary/neural-network-nn) Optimization toolkit, is a comprehensive toolkit for optimizing and deploying AI inference models. Even though the name contains Visual, OpenVINO also supports various additional tasks including language, audio, time series, etc.
<p align="center">
<br>
@ -59,20 +59,20 @@ Export a YOLOv8n model to OpenVINO format and run inference with the exported mo
## Arguments
| Key | Value | Description |
| --------- | ------------ | ---------------------------------------------------- |
| `format` | `'openvino'` | format to export to |
| `imgsz` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) |
| `half` | `False` | FP16 quantization |
| `int8` | `False` | INT8 quantization |
| `batch` | `1` | batch size for inference |
| `dynamic` | `False` | allows dynamic input sizes |
| Key | Value | Description |
| --------- | ------------ | --------------------------------------------------------------------------- |
| `format` | `'openvino'` | format to export to |
| `imgsz` | `640` | image size as scalar or (h, w) list, i.e. (640, 480) |
| `half` | `False` | FP16 quantization |
| `int8` | `False` | INT8 quantization |
| `batch` | `1` | [batch size](https://www.ultralytics.com/glossary/batch-size) for inference |
| `dynamic` | `False` | allows dynamic input sizes |
## Benefits of OpenVINO
1. **Performance**: OpenVINO delivers high-performance inference by utilizing the power of Intel CPUs, integrated and discrete GPUs, and FPGAs.
2. **Support for Heterogeneous Execution**: OpenVINO provides an API to write once and deploy on any supported Intel hardware (CPU, GPU, FPGA, VPU, etc.).
3. **Model Optimizer**: OpenVINO provides a Model Optimizer that imports, converts, and optimizes models from popular deep learning frameworks such as PyTorch, TensorFlow, TensorFlow Lite, Keras, ONNX, PaddlePaddle, and Caffe.
3. **Model Optimizer**: OpenVINO provides a Model Optimizer that imports, converts, and optimizes models from popular [deep learning](https://www.ultralytics.com/glossary/deep-learning-dl) frameworks such as PyTorch, [TensorFlow](https://www.ultralytics.com/glossary/tensorflow), TensorFlow Lite, Keras, ONNX, PaddlePaddle, and Caffe.
4. **Ease of Use**: The toolkit comes with more than [80 tutorial notebooks](https://github.com/openvinotoolkit/openvino_notebooks) (including [YOLOv8 optimization](https://github.com/openvinotoolkit/openvino_notebooks/tree/latest/notebooks/yolov8-optimization)) teaching different aspects of the toolkit.
## OpenVINO Export Structure
@ -103,7 +103,7 @@ For more detailed steps and code snippets, refer to the [OpenVINO documentation]
## OpenVINO YOLOv8 Benchmarks
YOLOv8 benchmarks below were run by the Ultralytics team on 4 different model formats measuring speed and accuracy: PyTorch, TorchScript, ONNX and OpenVINO. Benchmarks were run on Intel Flex and Arc GPUs, and on Intel Xeon CPUs at FP32 precision (with the `half=False` argument).
YOLOv8 benchmarks below were run by the Ultralytics team on 4 different model formats measuring speed and accuracy: PyTorch, TorchScript, ONNX and OpenVINO. Benchmarks were run on Intel Flex and Arc GPUs, and on Intel Xeon CPUs at FP32 [precision](https://www.ultralytics.com/glossary/precision) (with the `half=False` argument).
!!! note
@ -121,28 +121,28 @@ Benchmarks below run on Intel® Data Center GPU Flex 170 at FP32 precision.
<img width="800" src="https://github.com/ultralytics/docs/releases/download/0/flex-gpu-benchmarks.avif" alt="Flex GPU benchmarks">
</div>
| Model | Format | Status | Size (MB) | mAP50-95(B) | Inference time (ms/im) |
| ------- | ----------- | ------ | --------- | ----------- | ---------------------- |
| YOLOv8n | PyTorch | ✅ | 6.2 | 0.3709 | 21.79 |
| YOLOv8n | TorchScript | ✅ | 12.4 | 0.3704 | 23.24 |
| YOLOv8n | ONNX | ✅ | 12.2 | 0.3704 | 37.22 |
| YOLOv8n | OpenVINO | ✅ | 12.3 | 0.3703 | 3.29 |
| YOLOv8s | PyTorch | ✅ | 21.5 | 0.4471 | 31.89 |
| YOLOv8s | TorchScript | ✅ | 42.9 | 0.4472 | 32.71 |
| YOLOv8s | ONNX | ✅ | 42.8 | 0.4472 | 43.42 |
| YOLOv8s | OpenVINO | ✅ | 42.9 | 0.4470 | 3.92 |
| YOLOv8m | PyTorch | ✅ | 49.7 | 0.5013 | 50.75 |
| YOLOv8m | TorchScript | ✅ | 99.2 | 0.4999 | 47.90 |
| YOLOv8m | ONNX | ✅ | 99.0 | 0.4999 | 63.16 |
| YOLOv8m | OpenVINO | ✅ | 49.8 | 0.4997 | 7.11 |
| YOLOv8l | PyTorch | ✅ | 83.7 | 0.5293 | 77.45 |
| YOLOv8l | TorchScript | ✅ | 167.2 | 0.5268 | 85.71 |
| YOLOv8l | ONNX | ✅ | 166.8 | 0.5268 | 88.94 |
| YOLOv8l | OpenVINO | ✅ | 167.0 | 0.5264 | 9.37 |
| YOLOv8x | PyTorch | ✅ | 130.5 | 0.5404 | 100.09 |
| YOLOv8x | TorchScript | ✅ | 260.7 | 0.5371 | 114.64 |
| YOLOv8x | ONNX | ✅ | 260.4 | 0.5371 | 110.32 |
| YOLOv8x | OpenVINO | ✅ | 260.6 | 0.5367 | 15.02 |
| Model | Format | Status | Size (MB) | mAP50-95(B) | Inference time (ms/im) |
| ------- | ------------------------------------------------------- | ------ | --------- | ----------- | ---------------------- |
| YOLOv8n | [PyTorch](https://www.ultralytics.com/glossary/pytorch) | ✅ | 6.2 | 0.3709 | 21.79 |
| YOLOv8n | TorchScript | ✅ | 12.4 | 0.3704 | 23.24 |
| YOLOv8n | ONNX | ✅ | 12.2 | 0.3704 | 37.22 |
| YOLOv8n | OpenVINO | ✅ | 12.3 | 0.3703 | 3.29 |
| YOLOv8s | PyTorch | ✅ | 21.5 | 0.4471 | 31.89 |
| YOLOv8s | TorchScript | ✅ | 42.9 | 0.4472 | 32.71 |
| YOLOv8s | ONNX | ✅ | 42.8 | 0.4472 | 43.42 |
| YOLOv8s | OpenVINO | ✅ | 42.9 | 0.4470 | 3.92 |
| YOLOv8m | PyTorch | ✅ | 49.7 | 0.5013 | 50.75 |
| YOLOv8m | TorchScript | ✅ | 99.2 | 0.4999 | 47.90 |
| YOLOv8m | ONNX | ✅ | 99.0 | 0.4999 | 63.16 |
| YOLOv8m | OpenVINO | ✅ | 49.8 | 0.4997 | 7.11 |
| YOLOv8l | PyTorch | ✅ | 83.7 | 0.5293 | 77.45 |
| YOLOv8l | TorchScript | ✅ | 167.2 | 0.5268 | 85.71 |
| YOLOv8l | ONNX | ✅ | 166.8 | 0.5268 | 88.94 |
| YOLOv8l | OpenVINO | ✅ | 167.0 | 0.5264 | 9.37 |
| YOLOv8x | PyTorch | ✅ | 130.5 | 0.5404 | 100.09 |
| YOLOv8x | TorchScript | ✅ | 260.7 | 0.5371 | 114.64 |
| YOLOv8x | ONNX | ✅ | 260.4 | 0.5371 | 110.32 |
| YOLOv8x | OpenVINO | ✅ | 260.6 | 0.5367 | 15.02 |
This table represents the benchmark results for five different models (YOLOv8n, YOLOv8s, YOLOv8m, YOLOv8l, YOLOv8x) across four different formats (PyTorch, TorchScript, ONNX, OpenVINO), giving us the status, size, mAP50-95(B) metric, and inference time for each combination.
@ -185,7 +185,7 @@ Benchmarks below run on Intel® Arc 770 GPU at FP32 precision.
### Intel Xeon CPU
The Intel® Xeon® CPU is a high-performance, server-grade processor designed for complex and demanding workloads. From high-end cloud computing and virtualization to artificial intelligence and machine learning applications, Xeon® CPUs provide the power, reliability, and flexibility required for today's data centers.
The Intel® Xeon® CPU is a high-performance, server-grade processor designed for complex and demanding workloads. From high-end [cloud computing](https://www.ultralytics.com/glossary/cloud-computing) and virtualization to [artificial intelligence](https://www.ultralytics.com/glossary/artificial-intelligence-ai) and machine learning applications, Xeon® CPUs provide the power, reliability, and flexibility required for today's data centers.
Notably, Xeon® CPUs deliver high compute density and scalability, making them ideal for both small businesses and large enterprises. By choosing Intel® Xeon® CPUs, organizations can confidently handle their most demanding computing tasks and foster innovation while maintaining cost-effectiveness and operational efficiency.
@ -255,7 +255,7 @@ Benchmarks below run on 13th Gen Intel® Core® i7-13700H CPU at FP32 precision.
The Intel® Ultra™ 7 155H represents a new benchmark in high-performance computing, designed to cater to the most demanding users, from gamers to content creators. The Ultra™ 7 155H is not just a CPU; it integrates a powerful GPU and an advanced NPU (Neural Processing Unit) within a single chip, offering a comprehensive solution for diverse computing needs.
This hybrid architecture allows the Ultra™ 7 155H to excel in both traditional CPU tasks and GPU-accelerated workloads, while the NPU enhances AI-driven processes, enabling faster and more efficient machine learning operations. This makes the Ultra™ 7 155H a versatile choice for applications requiring high-performance graphics, complex computations, and AI inference.
This hybrid architecture allows the Ultra™ 7 155H to excel in both traditional CPU tasks and GPU-accelerated workloads, while the NPU enhances AI-driven processes, enabling faster and more efficient [machine learning](https://www.ultralytics.com/glossary/machine-learning-ml) operations. This makes the Ultra™ 7 155H a versatile choice for applications requiring high-performance graphics, complex computations, and AI inference.
The Ultra™ 7 series includes multiple models, each offering different levels of performance, with the 'H' designation indicating a high-power variant suitable for laptops and compact devices. Early benchmarks have highlighted the exceptional performance of the Ultra™ 7 155H, particularly in multitasking environments, where the combined power of the CPU, GPU, and NPU leads to remarkable efficiency and speed.
@ -465,7 +465,7 @@ Yes, you can benchmark YOLOv8 models in various formats including PyTorch, Torch
# Load a YOLOv8n PyTorch model
model = YOLO("yolov8n.pt")
# Benchmark YOLOv8n speed and accuracy on the COCO8 dataset for all export formats
# Benchmark YOLOv8n speed and [accuracy](https://www.ultralytics.com/glossary/accuracy) on the COCO8 dataset for all export formats
results = model.benchmarks(data="coco8.yaml")
```