Difference between revisions of "ML-TN-001 - AI at the edge: comparison of different embedded platforms - Part 6"
(Created page with "{{InfoBoxTop}} {{AppliesToMachineLearning}} {{AppliesTo Machine Learning TN}} {{InfoBoxBottom}} __FORCETOC__ == History == {| class="wikitable" border="1" !Version !Date !Not...") |
|||
| Line 5: | Line 5: | ||
__FORCETOC__ | __FORCETOC__ | ||
| − | + | = History = | |
{| class="wikitable" border="1" | {| class="wikitable" border="1" | ||
!Version | !Version | ||
| Line 16: | Line 16: | ||
|} | |} | ||
| − | + | =Introduction= | |
This Technical Note (TN for short) belongs to the series introduced [[ML-TN-001_-_AI_at_the_edge:_comparison_of_different_embedded_platforms_-_Part_1|here]]. The configuration here described is similar to the one used for [[ML-TN-001 - AI at the edge: comparison of different embedded platforms - Part 3|this article]] of the same series. With respect to that TN, the main differences are: | This Technical Note (TN for short) belongs to the series introduced [[ML-TN-001_-_AI_at_the_edge:_comparison_of_different_embedded_platforms_-_Part_1|here]]. The configuration here described is similar to the one used for [[ML-TN-001 - AI at the edge: comparison of different embedded platforms - Part 3|this article]] of the same series. With respect to that TN, the main differences are: | ||
* PyTorch framework was used instead of TensorFlow | * PyTorch framework was used instead of TensorFlow | ||
| Line 26: | Line 26: | ||
These changes allowed to increase performance as detailed in the rest of the document. | These changes allowed to increase performance as detailed in the rest of the document. | ||
| − | + | =PyTorch-based development flow= | |
TBD | TBD | ||
| − | + | =Results= | |
TBD | TBD | ||
Latest revision as of 13:13, 24 September 2021
| HOME | SOMs | SBCs | ToloMEO Embedded Assistant |  GET A QUOTE
|
 ONLINE HELPDESK
|
| Roadmap | IoT Services | ML/AI services | Embedded Design Services |
Info Box
|
History[edit | edit source]
| Version | Date | Notes |
|---|---|---|
| 1.0.0 | October 2021 | First public release |
Introduction[edit | edit source]
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 flow[edit | edit source]
TBD
Results[edit | edit source]
TBD
