OpenVINO Model optimizer doesn't convert all output layers

Intel® Distribution of OpenVINO™ Toolkit

Community assistance about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all aspects of computer vision-related on Intel® platforms.

OpenVINO Model optimizer doesn't convert all output layers

348 Views

Hi,

I tried to convert the posenet model (https://github.com/tensorflow/tfjs-models/tree/master/posenet) using https://github.com/oveddan/posenet-for-installations which converts the Tensorflow js model back to Tensorflow and then to a CoreML model.

The CoreML model contains four output layers: heatmap,offset_2,displacement_fwd_2,displacement_bwd_2

When I create the IR using the OpenVINO model optimizer, there seems to be only one output layer: heatmap, even if I use the specify the output layers using

--output heatmap,offset_2,displacement_fwd_2,displacement_bwd_2

, although I don't get any error message during conversion (which I get if I specify some bogus output layer names).

I should mention that I'm new to ML and Computer Vision.

Any idea what I'm doing wrong?

Cheers

Thomas

Link Copied

0 Replies

Community support is provided during standard business hours (Monday to Friday 7AM - 5PM PST). Other contact methods are available here.

Intel does not verify all solutions, including but not limited to any file transfers that may appear in this community. Accordingly, Intel disclaims all express and implied warranties, including without limitation, the implied warranties of merchantability, fitness for a particular purpose, and non-infringement, as well as any warranty arising from course of performance, course of dealing, or usage in trade.

For more complete information about compiler optimizations, see our Optimization Notice.