Revision as of 09:29, 26 June 2024 by Registered User
| Applicable for | STM32MP13x lines, STM32MP15x lines, STM32MP25x lines |
 |
 |
 |
 | |
|---|---|---|---|---|
| Execution engine | NPU/GPU | CPU | CPU | EdgeTPU |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
 Important
|
| 1 NPU/GPU acceleration based on OpenVX backend using network binary graph (NBG) is available only for STM32MP2x boards |
1. Performance Comparison[edit source]
| Model | STM32MP25 NPU |
STM32MP15x CPU | |
|---|---|---|---|
|
MobilenetV1_0.5 128x128 |
515 FPS |
22 FPS |
| MobilenetV2_1.0 224x224 |
72 FPS |
XXX FPS | |
|
SSD_MobilenetV1_1.0 300x300 |
40 FPS |
2 FPS |
| SSD_MobilenetV2_FPNLite 224x224 | 36 FPS | XXX FPS | |
|
STModel_FaceReco |
15 FPS |
5 FPS |
|
YoloV8n 256x256 |
59 FPS |
1.3 FPS |
|
DeepLabV3 257x257 |
17 FPS |
1 FPS |
Neural processing unit - NEW
Graphics processing units
Central processing unit
Frames per second