X-LINUX-AI application samples zoo

Revision as of 17:39, 25 June 2024 by Registered User
Applicable for STM32MP13x lines, STM32MP15x lines, STM32MP25x lines

X-LINUX-AI Machine code.png
X-LINUX-AI TFLite.png
X-LINUX-AI Onnx.png
X-LINUX-AI coral.png
Execution engine NPU/GPU 1 CPU CPU EdgeTPU
Image classification logo.png Yes Yes Yes Yes
Object detection logo.png Yes Yes Yes Yes
Face recognition logo.png No Yes No No
Pose estimation logo.png Yes No No No
Semantic segmentation logo.png Yes No No No


Warning DB.png Important
1 NPU/GPU execution engine is available only for STM32MP2x boards

1. Performance Comparison[edit source]


Model STM32MP25
NPU
STM32MP15x
CPU
Image classification logo.png MobilenetV1_0.5 128x128

515 FPS

22 FPS

MobilenetV2_1.0 224x224

72 FPS

XXX FPS

Object detection logo.png SSD_MobilenetV1_1.0 300x300

40 FPS

2 FPS

SSD_MobilenetV2_FPNLite 224x224 36 FPS XXX FPS
Face recognition logo.png STModel_FaceReco

15 FPS

5 FPS

Pose estimation logo.png Movenet_SinglePose_Lightning_int8_4.tflite

14 FPS
(executed on GPU only)

1.8 FPS

Semantic segmentation logo.png DeepLabV3

16 FPS

1 FPS