Open carsonswope opened 4 months ago
I can reproduce this issue. The error is actually coming when the second saved PyTorch model is being loaded. I suspect this issue is the result of some of the PyTorch graph lowering that we do during conversion.
πDescribing the bug
After running
ct.convert
on a torchscript model, the torchscript model appears to be corrupted and does not save correctly. The stack trace is coming from torch, but it only happens after the model has been processed using ct.convert.Stack Trace
To Reproduce
Python script:
System environment (please complete the following information):