Error 5 - Cast and Dequantize Op not supported

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.

Error 5 - Cast and Dequantize Op not supported

718 Views

I got these two error when i was trying to

convert tensorflow objection detection zoo model (SSD-mobilenet or Faster-RCNN model) to graph

quantize pb file then convert it to graph

I know there are lots of ops are not supported, but Is there an official list of supported / unsupported tensorflow ops?

so at least i can avoid those model structure which are impossible to be converted at the beginning.

p.s. haven't tried it on ncsdk v2. but i didn't notice anything about new supported ops was mentioned in the release note.

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.