sahooora commented on pull request #8070: URL: https://github.com/apache/tvm/pull/8070#issuecomment-844345929
> The parameter needs to be renamed in the `params` dictionary as well. Print out the dictionary and you should see the dense_kernel param under the old name. > […](#) > On Wed, May 19, 2021, 10:24 AM sahooora ***@***.***> wrote: %dense_kernel:0: can you also delete the :0? The problem here is that there are extra characters showing up in the variable names. If you get errors like these, try just renaming the variables to "normal looking" names. (Relay follows pretty standard rules for naming variables and declaring types, e.g. <variable name>: <type> where the variable name can be [A-Za-z0-9_]). Thanks. I tried dense_kernel and the error has gone. but I got the following error when I wanted to execute the model: result_myfloat = ex.evaluate()(input_st, **params) File "/home/sara/.local/lib/python3.6/site-packages/tvm-0.8.dev591+g4dfa7dfb4-py3.6-linux-x86_64.egg/tvm/relay/build_module.py", line 385, in _graph_wrapper args = self._convert_args(self.mod["main"], args, kwargs) File "/home/sara/.local/lib/python3.6/site-packages/tvm-0.8.dev591+g4dfa7dfb4-py3.6-linux-x86_64.egg/tvm/relay/backend/interpreter.py", line 120, in _convert_args cargs.appen d(kwargs[name]) KeyError: 'dense_kernel' — You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub <[#8070 (comment)](https://github.com/apache/tvm/pull/8070#issuecomment-844312017)>, or unsubscribe <https://github.com/notifications/unsubscribe-auth/AAJFZANER3NDKDIDH2BTIQ3TOPX5NANCNFSM45DBBYRQ> . Thanks. It works -- 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: [email protected]
