MLonMCU: TinyML Benchmarking with Fast Retargeting
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916311066476544 |
|---|---|
| author | van Kempen, Philipp Stahl, Rafael Mueller-Gritschneder, Daniel Schlichtmann, Ulf |
| author_facet | van Kempen, Philipp Stahl, Rafael Mueller-Gritschneder, Daniel Schlichtmann, Ulf |
| contents | While there exist many ways to deploy machine learning models on microcontrollers, it is non-trivial to choose the optimal combination of frameworks and targets for a given application. Thus, automating the end-to-end benchmarking flow is of high relevance nowadays. A tool called MLonMCU is proposed in this paper and demonstrated by benchmarking the state-of-the-art TinyML frameworks TFLite for Microcontrollers and TVM effortlessly with a large number of configurations in a low amount of time. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_08951 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | MLonMCU: TinyML Benchmarking with Fast Retargeting van Kempen, Philipp Stahl, Rafael Mueller-Gritschneder, Daniel Schlichtmann, Ulf Machine Learning While there exist many ways to deploy machine learning models on microcontrollers, it is non-trivial to choose the optimal combination of frameworks and targets for a given application. Thus, automating the end-to-end benchmarking flow is of high relevance nowadays. A tool called MLonMCU is proposed in this paper and demonstrated by benchmarking the state-of-the-art TinyML frameworks TFLite for Microcontrollers and TVM effortlessly with a large number of configurations in a low amount of time. |
| title | MLonMCU: TinyML Benchmarking with Fast Retargeting |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2306.08951 |