ML-TN-001 - AI at the edge: comparison of different embedded platforms - Part 6
| HOME | SOMs | SBCs | ToloMEO Embedded Assistant |  GET A QUOTE
|
 ONLINE HELPDESK
|
| Roadmap | IoT Services | ML/AI services | Embedded Design Services |
HistoryEdit
| Version | Date | Notes |
|---|---|---|
| 1.0.0 | October 2021 | First public release |
IntroductionEdit
This Technical Note (TN for short) belongs to the series introduced here. The configuration here described is similar to the one used for this article of the same series. With respect to that TN, the main differences are:
- PyTorch framework was used instead of TensorFlow
- Vitis AI was upgraded to version 1.3.2.
Also, two significant improvements were implemented:
- Structural pruning of the model
- Model review resulting in the removal of the fully connected layer.
These changes allowed to increase performance as detailed in the rest of the document.
PyTorch-based development flowEdit
TBD
ResultsEdit
TBD