[GitHub] [incubator-tvm] cam145 commented on a change in pull request #5992: Add support for tflite arg_min and arg_max

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

cam145 commented on a change in pull request #5992:
URL: https://github.com/apache/incubator-tvm/pull/5992#discussion_r452216449



##########
File path: python/tvm/relay/frontend/tflite.py
##########
@@ -1634,6 +1636,56 @@ def convert_reduce_sum(self, op):
     def convert_reduce_any(self, op):
         return self._convert_reduce(_op.reduce.any, op)
 
+    def _convert_arg_min_max(self, relay_op, op):
+        """Generic method to convert TFLite arg_min_max"""
+        try:
+            from tflite.Operator import Operator

Review comment:
       @d-smirnov 
   
   is something like this?
   
       def convert_arg_max(self, op):
           """Convert TFLite ABS"""
           if self.is_quantized(op):
               raise tvm.error.OpNotImplemented(
                   'TFlite quantized ARG_MAX operator is not supported yet.')
           return self._convert_unary_elemwise(_op.arg_max, op)
   




----------------------------------------------------------------
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