JDAI-CV/dabnn

onn2bnn:terminate called after throwing an instance of 'std::out_of_range' what(): _Map_base::at Aborted (core dumped)

wayy13 opened this issue · 4 comments

wayy13 commented

terminate called after throwing an instance of 'std::out_of_range'
what(): _Map_base::at
Aborted (core dumped)

xvyaward commented

hi, did you solve your problem?
I am facing the same issue.

hebangwen commented

Hi, sorry to bother you, but I'd like to ask if you have solved this problem. I'm also facing the same problem but don't know where to start. It would be very appreciated if you can give me some suggestions.

hebangwen commented

Hi, all. I've checked the pretrained models from README.md and found three attributes in the model properties: format-ONNXv3, producer-pytorch0.3, and imports-ai.onnxv6. Thus, the easiest way to use DABNN without this error is to downgrade your PyTorch version to 0.3. Or else, you need to fix the version incompatible bug between DABNN and ONNX.

travisdriver commented

@BangwenHe This fixed it for me, thank you! Specifically, I used pytorch 0.4.1 and python 3.7.