[GitHub] [incubator-tvm] t-vi edited a comment on pull request #5779: Improve separation of PyTorch dtypes and TVM dtypes in relay PyTorch frontend

[GitBox <gi...@apache.org>]

t-vi edited a comment on pull request #5779:
URL: https://github.com/apache/incubator-tvm/pull/5779#issuecomment-643420736


   Note that I don't remove the possibility to pass in names. As the thread suggests, people will find that useful. I'm not sure why you would have to insist on passing them if the user is fine with the TorchScript provided ones. I'm not taking away passing input names, I just soften the mandates.
   
   Passing the shapes should be needed very little, and I am surprised that you would need the user to do that. Ignoring the dtypes in of the inputs is actively terrible.
   
   How about doing the following:
   - Allow passing nothing.
   - Allow passing names only. (A list of strings.)
   - Allow passing names and shapes (for backward compat).
   - Allow passing names and shapes and dtypes (as a list of triples).
   


----------------------------------------------------------------
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.

For queries about this service, please contact Infrastructure at:
users@infra.apache.org