Intel® Distribution of OpenVINO™ Toolkit
Community support and discussions about the Intel® Distribution of OpenVINO™ toolkit, OpenCV, and all things computer vision-related on Intel® platforms.
5959 Discussions

OpenVINO Model optimizer doesn't convert all output layers

Reinberger__Thomas
184 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

0 Kudos
0 Replies
Reply