-
Notifications
You must be signed in to change notification settings - Fork 31
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Help running inference using yolov5, 6 & 8 #107
Comments
Most likely the models that you are using use operators that are not implemented. Note that this project is not currently actively maintained. |
Thank you for the quick response! |
Would suggest adding some prints. Or well, you can also explore the onnx model and search in this repo wether its implemented or not. |
@alrevuelta |
Hi,
Thanks for this amazing package!
I'm having troubles running inference using different yolo versions, whenever I'm running tiny_yolov2 test the inference seems to succeed.
Whenever I try any of the other version it fails with segmentation fault - exported to onnx, tried different opsets (including 12) and increase MAX_NUMBER_OF_NODES since yolov8 has 259 nodes.
More observations:
Running
resolve
function from inferece.c outputs segmentation fault. When I copy the content of resolve function toconnx.c
it seems to be running (after commenting the part preparing the operators since the opset is already 12).Doing the same with
inference
function did not work as it seems thatall_context[nodeIdx].executer
isNULL
.Can anyone assist please?
The text was updated successfully, but these errors were encountered: