gemini-code-assist[bot] commented on code in PR #19547:
URL: https://github.com/apache/tvm/pull/19547#discussion_r3224773616


##########
python/tvm/relax/frontend/onnx/onnx_frontend.py:
##########
@@ -4757,9 +4757,9 @@ def _impl_v10(cls, bb, inputs, attr, params):
                 _, param_value = params[1][var_name]
                 max_output_boxes_per_class = int(param_value.numpy().item())
             else:
-                max_output_boxes_per_class = 100  # Default value
+                max_output_boxes_per_class = 0  # Default value
         else:
-            max_output_boxes_per_class = 100  # Default value
+            max_output_boxes_per_class = 0  # Default value

Review Comment:
   ![medium](https://www.gstatic.com/codereviewagent/medium-priority.svg)
   
   The default value for `max_output_boxes_per_class` is updated to 0 here to 
align with the ONNX specification. However, `AllClassNMS._impl_v1` (lines 4849 
and 4851) still uses 100 as the default value. To maintain consistency across 
the ONNX frontend, `AllClassNMS` should also be updated to use 0 as the default 
value.



-- 
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]


---------------------------------------------------------------------
To unsubscribe, e-mail: [email protected]
For additional commands, e-mail: [email protected]

Reply via email to