X-LINUX-AI v5.1.0

Signed-off-by: Maxence GUILHIN <[email protected]>

Author: mguSTM

README.md

@@ -1,9 +1,8 @@
-
 <p align="center">
     <img width="720" src="https://raw.githubusercontent.com/STMicroelectronics/meta-st-stm32mpu-ai/master/x-linux-ai-logo.png">
 </p>
 
-X-LINUX-AI version: v5.0.0
+X-LINUX-AI version: v5.1.0
 
 X-LINUX-AI is a free of charge open-source software package dedicated to AI.
 It is a complete ecosystem that allow developers working with OpenSTLinux to create AI-based application very easily.
@@ -20,8 +19,8 @@ X-LINUX-AI OpenEmbedded meta layer to be integrated into OpenSTLinux distributio
 It contains recipes for AI frameworks, tools and application examples for STM32MPx series
 
 ## Compatibility
-The X-LINUX-AI OpenSTLinux Expansion Package v5.0.0 is compatible with the Yocto Project™ build system Mickledore.
-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
+The X-LINUX-AI OpenSTLinux Expansion Package v5.1.0 is compatible with the Yocto Project™ build system Mickledore.
+It is validated over the OpenSTLinux Distribution v5.1.0 on STM32MP25x and STM32MP1x series.
 
 ## Versioning
 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.
@@ -31,27 +30,38 @@ The X-LINUX-AI generic versioning v**x**.**y**.**z** is built as follows:
 * **z**: patch version to introduce bug fixes. A patch version is implemented in a backward compatible manner.
 
 ## Available frameworks and tools within the meta-layer
-[X-LINUX-AI v5.0.0 expansion package](https://wiki.st.com/stm32mpu/wiki/Category:X-LINUX-AI_expansion_package):
-* XNNPACK support for TensorFlow™ Lite and ONNX Runtime, with about 20% to 30% performance gain for quantized networks on a 32-bit system
-* TensorFlow™ Lite 2.11.0 with XNNPACK delegate activated
-* ONNX Runtime 1.14.0 with XNNPACK execution engine activated
-* OpenCV 4.7.x
-* Python™ 3.10.x (enabling Pillow module)
-* Coral Edge TPU™ accelerator native support
-  * libedgetpu 2.0.0 (Gouper) aligned with TensorFlow™ Lite 2.11.0
-  * libcoral 2.0.0 (Gouper) aligned with TensorFlow™ Lite 2.11.0
-  * PyCoral 2.0.0 (Gouper) aligned with TensorFlow™ Lite 2.11.0
-* Support for the OpenSTLinux AI package repository allowing the installation of a prebuilt package using apt-* utilities
-* Application samples
-  * C++ / Python™ image classification example using TensorFlow™ Lite based on the MobileNet v1 quantized model
-  * C++ / Python™ object detection example using TensorFlow™ Lite based on the COCO SSD MobileNet v1 quantized model
-  * C++ / Python™ image classification example using Coral Edge TPU™ based on the MobileNet v1 quantized model and compiled for the Edge TPU™
-  * C++ / Python™ object detection example using Coral Edge TPU™ based on the COCO SSD MobileNet v1 quantized model and compiled for the Edge TPU™
-  * 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]
-  * Python™ image classification example using ONNX Runtime based on the MobileNet v1 quantized model
-  * C++ / Python™ object detection example using ONNX Runtime based on the COCO SSD MobileNet v1 quantized model
-* Application support for the 720p, 480p, and 272p display configurations
-* 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
+[X-LINUX-AI v5.1.0 expansion package](https://wiki.st.com/stm32mpu/wiki/Category:X-LINUX-AI_expansion_package):
+* AI Frameworks:
+  * STAI_MPU Unified API based on OpenVX™(STM32MP25x only), TensorFlow™ Lite, Coral Edge TPU™ and ONNX Runtime™ compatible with all STM32MPU series
+  * TIM-VX™ 1.1.57 (STM32MP25x only)
+  * TensorFlow™ Lite 2.11.0 (CPU only) with XNNPACK delegate activated
+  * ONNX Runtime™ 1.14.0 (CPU only) with XNNPACK execution engine activated
+  * Coral Edge TPU™ accelerator native support
+    * libedgetpu 2.0.0 (Grouper) aligned with TensorFlow™ Lite 2.11.0
+    * libcoral 2.0.0 (Grouper) aligned with TensorFlow™ Lite 2.11.0
+    * PyCoral 2.0.0 (Grouper) aligned with TensorFlow™ Lite 2.11.0
+
+* Out of the box applications:
+  * Image classification :
+    * C++ / Python™ example using STAI_MPU Unified API]] based on the MobileNet v1 and v2 quantized models
+  * Object detection :
+    * C++ / Python™ example using STAI_MPU Unified API]] based on the SSD MobileNet v1 and v2 quantized models
+    * Python™ example using STAI_MPU Unified API]] based on YoloV8n pose quantized model
+  * Semantic segmentation :
+    * Python™ example using STAI_MPU Unified API]] based on DeepLabV3 quantized model
+  * Face recognition:
+    * C++ example 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]
+  * Note: applications are based on Gstreamer 1.22.x, GTK 3.x, OpenCV 4.7.x, Pillow, Python 3
+
+* Utilities:
+  * X-LINUX-AI tool suite provides tools for software information, AI packages management and Neural Network models benchmarking.
+  * Support wide range of image sensors for ST MPU including IMX335 (5MP) for MP2 with use of internal ISP, GC2145 and OV5640 for STM32MP13x
+  * Support for the OpenSTLinux AI package repository allowing the installation of a prebuilt package using apt-*
+
+* Host tools:
+  * ST Edge AI tool for NBG generation
+  * 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 supports all the above frameworks. It is available from the X-LINUX-AI product page
 
 ## Further information on how to install and how to use X-LINUX-AI Starter package
 <https://wiki.st.com/stm32mpu/wiki/X-LINUX-AI_Starter_package>

recipes-devtools/x-linux-ai/files/x-linux-ai-tool/x-linux-ai-tool.cc

@@ -206,15 +206,15 @@ std::string exec_command(const char* cmd) {
 int main(int argc, char *argv[])
 {
     process_args(argc, argv);
-    std::string command = "ls /var/lib/apt/lists/*_AI_*_main_*";
-    std::string ostl_pkg_path = "/var/lib/dpkg/status";
-    std::string x_pkg_path = exec_command(command.c_str());
-
-    if (!x_pkg_path.empty() && x_pkg_path.back() == '\n') {
-        x_pkg_path.pop_back();
-    }
 
     if (list) {
+        std::string command = "ls /var/lib/apt/lists/*_AI_*_main_*";
+        std::string ostl_pkg_path = "/var/lib/dpkg/status";
+        std::string x_pkg_path = exec_command(command.c_str());
+
+        if (!x_pkg_path.empty() && x_pkg_path.back() == '\n') {
+            x_pkg_path.pop_back();
+        }
         print_pkgs(ostl_pkg_path, x_pkg_path);
     }
     else if (to_install && argc == 3) {
@@ -224,12 +224,12 @@ int main(int argc, char *argv[])
         manage_pkgs(argc, argv,false);
     }
     else if (version) {
-        std::cout << "\nX-LINUX-AI version: " << README_VERSION << std::endl;
+        std::cout << "\nX-LINUX-AI version: " << README_VERSION << "\n" << std::endl;
     }
     else if (features) {
         std::cout << "\nFeatures:\n " << README_FEATURES << std::endl;
         std::cout << "\nFind more information on the wiki page: https://wiki.st.com/stm32mpu/wiki/X-LINUX-AI_OpenSTLinux_Expansion_Package" << std::endl;
-        std::cout << "\nApplications:\n " << README_APPLI << std::endl;
+        std::cout << "\nApplications:\n " << README_APPLI << "\n" << std::endl;
     }
     else{
         print_help(argc, argv);

recipes-devtools/x-linux-ai/x-linux-ai-tool_5.1.0.bb

@@ -29,10 +29,10 @@ do_configure() {
     xpkg_ver=$(sed -n 's/^.*X-LINUX-AI version: //p' README_sym)
 
     # Get features
-    xpkg_fea=$(sed -n '/^*.TensorFlow/,${p;/^*.Application.samples/q}' README_sym | sed '$d' | sed '1s/^//;$!s/$/ \\n \\/;$s/$//')
+    xpkg_fea=$(sed -n '/^* AI Frameworks:/,/^* Out of the box applications:/{/^* Out of the box applications:/!p}' README_sym | sed '$d' | sed '1d; $!s/$/ \\n \\/')
 
     # Get applications
-    xpkg_app=$(sed -n '/^*.Application.samples/,${p;/^*.Application.support/q}' README_sym | sed '1d;$d' | sed '1s/^//;$!s/$/ \\n \\/;$s/$//' | sed 's/^\ *//g' )
+    xpkg_app=$(sed -n '/^* Out of the box applications:/,/^* Utilities:/{/^* Utilities:/!p}' README_sym | sed '$d' | sed '1d; $!s/$/ \\n \\/')
 
     # Get wiki link
     xpkg_link=$(grep -o 'https://wiki.st.com/stm32mp.*Starter_package>' README_sym | sed 's/>$//')