Sure that sounds good. Since params are referenced by its numeric node id in Torch IR and we line-by-line translate, we still need association of numeric ID -> state_dict key name.
state_dict key name is available here as "full_attr" so you can use this name when creating Var. https://github.com/apache/incubator-tvm/blob/master/python/tvm/relay/frontend/pytorch.py#L2278 `full_attr_node_name` is the numeric ID corresponding to `full_attr`. You need to add this mapping in `outputs` variable. --- [Visit Topic](https://discuss.tvm.ai/t/pytorch-frontend-graph-input-names-can-change-using-loaded-torchscript/6055/22) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.ai/email/unsubscribe/5373062900dd24d5a06fed52783b2380cfec542d8a73cec83893e44bfd06437c).
