Application Acceleration With FPGAs
Programmable Acceleration Cards (PACs), DCP, DLA, Software Stack, and Reference Designs
Announcements
Intel Support hours are Monday-Fridays, 8am-5pm PST, except Holidays. Thanks to our community members who provide support during our down time or before we get to your questions. We appreciate you!

Need Forum Guidance? Click here
Search our FPGA Knowledge Articles here.
407 Discussions

OpenVINO - "Error: Failure due to generic standard exception" when running inference on FPGA

CJian1
Beginner
1,042 Views

Hello, I have got an error when running inference on "HETERO:FPGA,CPU" with OpenVINO. Below are the full error log:

[ INFO ] InferenceEngine: API version ............ 1.0 Build .................. 9911 [ INFO ] Parsing input parameters [ INFO ] Loading plugin   API version ............ 1.0 Build .................. heteroPlugin Description ....... heteroPlugin [ INFO ] Loading network files: [ INFO ] Preparing input blobs [ INFO ] Batch size is 1 [ INFO ] Preparing output blobs [ INFO ] Loading model to the plugin Graph Error Code: 78 Graph Error Description: Error: Incorrect layout type of the output primitive. Sequence: 1 Subgraph: 1 Primitive: 9 Type: Output File: api/src/dla_graph_assembler.cpp Function: compute_output_primitive_params Line #: 1122 [ ERROR ] Error: Failure due to generic standard exception

The FPGA I used is Arria 10 on a PAC card and the neural network model is just a simple AlexNet-like binary classifier. The inference engine runs successfully when it only uses the CPU plugin.

 

Have anyone experienced the same problem before? I appreciate any insights you guys might have.

 

Thanks.

0 Kudos
0 Replies
Reply