Forum Discussion
New Contributoryolov3_tiny_tf run_inference_stream problem
I have solved the error ([CPU] Could not deserialize by device xml header) by modifying the model xml file.
Run the dla_compiler and then get the unsupported layers name. Delete the unsupported layers from xml file and compile again to obtain IR data. Error would disappear.
New ContributorActually, i did not any change on the run_image_stream.sh or stream.sh.
I used the below wic file from example project.
$COREDLA_ROOT/demo/ed4/a10_soc_s2m/sd-card/coredla-image-arria10.wic
https://www.intel.com/content/www/us/en/docs/programmable/848957/2025-1/writing-the-sd-card-image-wic-to-an-sd-card.html
Regular ContributorHi,
Have you performed some emulation to confirm if the model you are using is able to be run in FPGA? The reason is that the example provided is to have the model fully run in FPGA.
But based on the log file provided, some of the layer is not able to performed in FPGA and it need to revert to CPU but the Application code does not support it.
It is recommended you try to compile graph and check the output if it is fully supported or not. https://www.intel.com/content/www/us/en/docs/programmable/863373/2025-3/compiling-a-graph.html.
- fpga_guyx
If the run_image_stream and/or image_streaming_app code are modified according to unsupported layers, then the yolo-v3-tiny model will run successfully, what you are trying to tell me as i got it.
Thank you.
- JohnT_Altera
Hi,
I am glad that you understand it. Please let me know if you have any other queries.
- fpga_guyx
I could not understand what I exactly should change the run_image_stream and/or image_streaming_app (c++ codes) to run the hetero models with supported and unsupported layers? Is there any guide or something to clarify? I expect to run the model with supported layer and then it gives me outputs for supported layers, later execute the cpu codes for unsupported layer.
