- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello ,
I am also using CNN-AlextNet with model optimizer . I was build the model and convert the caffe model to openvx was able to run floating point precision variants but faced with an error while runtime for Q78
VXLOG: vxGetKernelByName: Failed to find kernel com.intel.cnn_helpers.scalemddata
(sts=VX_ERROR_INVALID_PARAMETERS)
The detailed error is in the attached file. Do I need install some additional setup or a custom version of the OpenVx.
Please kindly reply to this query.
Thanks and Regards,
Rishab Goel
Link Copied
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Goel,
Thank you for your question.
The reason you are getting this error is that Q78 is purposed to run on a specific platform.
for regular use we would recommend using just the precision variants as you successfully did so far.
We will remove the Q78 option when not compatible to the customer system- thanks for helping us improve the product!
Regards,
Stav
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hello Stav,
May I know the specific platform on which Q78 will run !!
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi,
We will update in the future.
Stay tuned to the forum! :)
Regards,
Stav

- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page