maekawatoshiki commented on PR #14536: URL: https://github.com/apache/tvm/pull/14536#issuecomment-1504925657
I appreciate your review! I found a quantized softmax implementation in tensorflow lite: (https://github.com/tensorflow/tensorflow/blob/305fec9fddc3bdb5bb574a134b955bf4b07fd795/tensorflow/lite/kernels/internal/reference/softmax.h#L60), so I'm going to try it and compare the accuracy with my current implementation. Besides, from https://github.com/apache/tvm/pull/14536#discussion_r1162144248 and https://github.com/apache/tvm/pull/14536#discussion_r1162443317, the current unit tests seem the need to be improved, I acknowledged. -- 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]
