Bureaucrats, dave_user, Administrators
4,650
edits
Changes
Created page with "{{InfoBoxTop}} {{AppliesToMachineLearning}} {{AppliesTo Machine Learning TN}} {{InfoBoxBottom}} __FORCETOC__ == History == {| class="wikitable" border="1" !Version !Date !Not..."
{{InfoBoxTop}}
{{AppliesToMachineLearning}}
{{AppliesTo Machine Learning TN}}
{{InfoBoxBottom}}
__FORCETOC__
== History ==
{| class="wikitable" border="1"
!Version
!Date
!Notes
|-
|1.0.0
|October 2021
|First public release
|}
==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:
* 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==
TBD
==Results==
TBD
{{AppliesToMachineLearning}}
{{AppliesTo Machine Learning TN}}
{{InfoBoxBottom}}
__FORCETOC__
== History ==
{| class="wikitable" border="1"
!Version
!Date
!Notes
|-
|1.0.0
|October 2021
|First public release
|}
==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:
* 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==
TBD
==Results==
TBD
