- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi, I tried converting this facenet model (from the david sandberg repo) with the model optimizer and then running it but I get different errors with all the plugins and none work.
On the CPU:
File "ie_api.pyx", line 240, in inference_engine.ie_api.IEPlugin.load
File "ie_api.pyx", line 252, in inference_engine.ie_api.IEPlugin.load
RuntimeError: Unsupported primitive of type: Switch name: InceptionResnetV1/Block8/Branch_1/Conv2d_0b_1x3/BatchNorm/cond/Switch_2/Switch
/teamcity/work/scoring_engine_build/master/ie_bridges/python/inference_engine/ie_api_impl.cpp:202
On the iGPU:
File "ie_api.pyx", line 240, in inference_engine.ie_api.IEPlugin.load
File "ie_api.pyx", line 252, in inference_engine.ie_api.IEPlugin.load
RuntimeError: Invalid constant blob dimensions
/teamcity/work/scoring_engine_build/master/ie_bridges/python/inference_engine/ie_api_impl.cpp:202
On myriad (Movidius NCS):
File "ie_api.pyx", line 240, in inference_engine.ie_api.IEPlugin.load
File "ie_api.pyx", line 252, in inference_engine.ie_api.IEPlugin.load
RuntimeError: [VPU] Unsupported dimensions
/teamcity/work/scoring_engine_build/master/ie_bridges/python/inference_engine/ie_api_impl.cpp:202
They all throw errors while trying to do an IEPLuging.load(), can you help me out?
I am using the Python (3.5) api on Ubuntu 16.04.
Thanks
EDIT: never mind, I just needed to re-export the model with the model optimizer
Link Copied
1 Reply
- Mark as New
- Bookmark
- Subscribe
- Mute
- Subscribe to RSS Feed
- Permalink
- Report Inappropriate Content
Hi Luca,
I see that you edited your original post. Does your issue still need investigation or have you resolved it?
Kind Regards,
Monique Jones
Reply
Topic Options
- Subscribe to RSS Feed
- Mark Topic as New
- Mark Topic as Read
- Float this Topic for Current User
- Bookmark
- Subscribe
- Printer Friendly Page