new-TonyWang opened a new pull request #9850: URL: https://github.com/apache/tvm/pull/9850
I have encountered "list index out of range" when parsing the keras LSTM. Then I dived in to this problem. I found that when using keras LSTVM and set "use_bies=False", this would lead to the "list index out of range" exception, because at this time, the **weightList** only contains two tensors, and tvm will fall on fetching **weightList[2]**. So I made a little improvment by adding *if* statement and added some new test cases. -- 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. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
