I tried to script a model using torch.jit.trace() but I always have this error:
TracerWarning: Output nr 1. of the traced function does not match the corresponding output of the Python function. Detailed error: Tensor-likes are not close!
I used model.eval() like suggested in other similar problems but the problem persists.
I am using :
- torch 2.0.0+cu117
- Python 3.10.6