Forums - what is the Tensorflow version used for custom ssd mobilenet v2

4 posts / 0 new
or Register
Last post
what is the Tensorflow version used for custom ssd mobilenet v2
ambikadolly96
Join Date: 26 Apr 20
Posts: 4
Posted: Wed, 2020-07-01 01:32
Top

I am trying to convert custom trained SSD Mobilenet V2 model.

Model trained on: Tensorflow 1.12 version

SNPE version for conversion: 1.39 version

Tensorflow version used for snpe conversion: Tensorflow 1.12 version

Python version for converting to snpe: Python 3.5 version

I am facing issues while converting the SSD Model. So wanted to know what is the exact Tensorflow version with which custom ssd model can be trained with and also exact tensorflow version used for snpe coonverison and also python version that can be used for snpe conversion.

  • Up0
  • Down0
Re: what is the Tensorflow version used for custom ssd...
gesqdn-forum
Join Date: 4 Nov 18
Posts: 184
Posted: Tue, 2020-07-07 06:55
Top

Hi ambikadolly96,

Kindly use below are Software version details so that SSD Mobilenet v2 model get converted to DLC successfully:
                 Tensorflow: 1.13.1
                 SNPE: 1.37
                 Python: 3.5
                 Please see https://developer.qualcomm.com/docs/snpe/convert_mobilenetssd.html for more information

  • Up0
  • Down0
Re: what is the Tensorflow version used for custom ssd...
WillieLogue23
Join Date: 9 Jul 20
Posts: 1
Posted: Thu, 2020-07-09 19:36
Top

Unfortunately, the above software details didn't help me. ANy alternative will be appreciated mybpcreditcard

  • Up0
  • Down0
Re: what is the Tensorflow version used for custom ssd...
gesqdn-forum
Join Date: 4 Nov 18
Posts: 184
Posted: Tue, 2020-07-14 03:05
Top

Hello WillieLogue23,

Kindly provide detailed information/logs on the issue faced by you.
Also, provide the software versions details.

  • Up0
  • Down0
or Register

Opinions expressed in the content posted here are the personal opinions of the original authors, and do not necessarily reflect those of Qualcomm Incorporated or its subsidiaries (“Qualcomm”). The content is provided for informational purposes only and is not meant to be an endorsement or representation by Qualcomm or any other party. This site may also provide links or references to non-Qualcomm sites and resources. Qualcomm makes no representations, warranties, or other commitments whatsoever about any non-Qualcomm sites or third-party resources that may be referenced, accessible from, or linked to this site.