0

I have explored edge computation for AI and I came across multiple library or framework which can help to convert model into lite format which is suitable for edge devices.

`Tensorflow Lite`

will help us to convert `Tensorflow`

Model into Tensorflow lite.
Or `Intel OpenVino`

will optimise the model for edge devices.

Questions

- If we have library to optimise the model for edge devices, after conversion will
**it cause any accuracy issue**. performance will get increase but accuracy of that model will get decrease. - If we have such technology to optimise model performance and wont get accuracy decrease then why people wont prefer
`tensorflow Lite model`

over`tensorflow model`

.

Please read my question carefully. – Maheshwar Ligade – 2019-12-19T05:27:27.573

can you be more specific about your comment or rephase your question please I might be able to reformulate my answer – pascal sautot – 2019-12-19T09:26:11.247

I have two questions which are interrelated point 1 and point 2. – Maheshwar Ligade – 2019-12-19T10:47:11.567

By any chance could you check if that answered your question. – pascal sautot – 2020-01-31T14:05:12.870

I upvoted for your answer. Thank you for giving me a brief overview. – Maheshwar Ligade – 2020-02-03T05:21:48.517