Forums - Does SNPE provided the ability to set the input size at runtime at network initialization?

4 posts / 0 new
or Register
Last post
Does SNPE provided the ability to set the input size at runtime at network initialization?
32437506
Join Date: 5 Dec 17
Posts: 6
Posted: Tue, 2018-01-09 00:42
Top

When I use caffe, I will reshape the model use "net.blobs['data'].reshape" when the input is not equal to (22,22). So I can use any size of input data.

But  when I use snpe with dlc file, I can only use input of size(22,22), I didn't find a method to reshape the model.  and a variety of networks (e.g. fully convolutional ones) should be able to easily support variable input sizes regardless of the size used at model creation/conversion。

 

*/

If SNPE provided the ability to set the input size at runtime at network initialization (regardless of what size you used in model creation/conversion), I need to vary the input size at each inference .

  • Up0
  • Down0
Re: Does SNPE provided the ability to set the input size at...
davids0
Join Date: 9 Jan 18
Posts: 3
Posted: Wed, 2018-01-17 07:07
Top

I am also keen to find a solution to this problem.

  • Up0
  • Down0
Re: Does SNPE provided the ability to set the input size at...
congguohua0
Join Date: 21 Jan 18
Posts: 2
Posted: Sun, 2018-01-21 19:29
Top

I have same question, it seems like snpe can not support Non-Fixed-Size input, i think this is a bug, because tensorflow graph_transform is support this input type.

  • Up0
  • Down0
Re: Does SNPE provided the ability to set the input size at...
ashishku
Join Date: 27 Sep 17
Posts: 4
Posted: Sun, 2018-01-28 22:30
Top

Especially for the object detection model I needed variable input shape [1,?,?,3]. how to generate dlc from such tensor shape?

  • 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.