You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Copy file name to clipboardExpand all lines: README.md
+24-13Lines changed: 24 additions & 13 deletions
Display the source diff
Display the rich diff
Original file line number
Diff line number
Diff line change
@@ -12,20 +12,27 @@ It is a complete ecosystem that allow developers working with OpenSTLinux to cre
12
12
***C++ API** for embedded high-performance applications
13
13
* Optimized **open-source solutions** provided with source codes that allow extensive **code reuse** and **time savings**
14
14
15
-
16
-
# meta-st-stm32mpu-ai
15
+
# meta-st-x-linux-ai
17
16
X-LINUX-AI OpenEmbedded meta layer to be integrated into OpenSTLinux distribution.
18
17
It contains recipes for AI frameworks, tools and application examples for STM32MPx series
19
18
20
19
## Compatibility
21
-
The X-LINUX-AI OpenSTLinux Expansion Package v3.0.0 is compatible with the Yocto Project™ build systems Kirkston.
22
-
It is validated over the OpenSTLinux Distributions v4.1 on STM32MP157F-DK2 with a USB image sensor and on STM32MP157F-EV1 with its built-in camera module
20
+
The X-LINUX-AI OpenSTLinux Expansion Package v5.0.0 is compatible with the Yocto Project™ build system Mickledore.
21
+
It is validated over the OpenSTLinux Distribution v5.0 on STM32MP157F-DK2 with a USB image sensor, on STM32MP157F-EV1 with its built-in camera module, and on STM32MP135F-DK with its built-in camera module
22
+
23
+
## Versioning
24
+
Since its release v5.0.0, the major versioning of the X-LINUX-AI OpenSTLinux Expansion Package is aligned on the major versioning of the OpenSTLinux Distribution. This prevents painful backward compatibility attempts and makes dependencies straightforward.
25
+
The X-LINUX-AI generic versioning v**x**.**y**.**z** is built as follows:
26
+
***x**: major version matching the OpenSTLinux Distribution major version. Each new major version is incompatible with previous OpenSTLinux Distribution versions.
27
+
***y**: minor version, which is changed when new functionalities are added to the X-LINUX-AI OpenSTLinux Expansion Package in a backward compatible manner.
28
+
***z**: patch version to introduce bug fixes. A patch version is implemented in a backward compatible manner.
23
29
24
30
## Available frameworks and tools within the meta-layer
* XNNPACK support for TensorFlow™ Lite and ONNX Runtime, with about 20% to 30% performance gain for quantized networks on a 32-bit system
33
+
* TensorFlow™ Lite 2.11.0 with XNNPACK delegate activated
34
+
* ONNX Runtime 1.14.0 with XNNPACK execution engine activated
35
+
* OpenCV 4.7.x
29
36
* Python™ 3.10.x (enabling Pillow module)
30
37
* Coral Edge TPU™ accelerator native support
31
38
* libedgetpu 2.0.0 (Gouper) aligned with TensorFlow™ Lite 2.11.0
@@ -39,14 +46,18 @@ It is validated over the OpenSTLinux Distributions v4.1 on STM32MP157F-DK2 with
39
46
* C++ / Python™ object detection example using Coral Edge TPU™ based on the COCO SSD MobileNet v1 quantized model and compiled for the Edge TPU™
40
47
* C++ face recognition application using proprietary model capable of recognizing the face of a known (enrolled) user. Contact the local STMicroelectronics support for more information about this application or send a request to [email protected]
41
48
* Python™ image classification example using ONNX Runtime based on the MobileNet v1 quantized model
49
+
* C++ / Python™ object detection example using ONNX Runtime based on the COCO SSD MobileNet v1 quantized model
42
50
* Application support for the 720p, 480p, and 272p display configurations
43
51
* X-LINUX-AI SDK add-on extending the OpenSTLinux SDK with AI functionality to develop and build an AI application easily. The X-LINUX-AI SDK add-on provides support for all the above frameworks. It is available from the [X-LINUX-AI](https://www.st.com/en/embedded-software/x-linux-ai.html) product page
44
52
45
-
## Further information on how to install and how to use X-LINUX-AI
0 commit comments