czh978 commented on PR #12593: URL: https://github.com/apache/tvm/pull/12593#issuecomment-1230099126
> Thanks for the fix @czh978. > > Do you mind providing some context on why `force_supress` needs to be set this way? Can you give one example of something that wasn't working before this change, and works after the change? https://github.com/apache/tvm/blob/3d41ac3a9ab58ba5f7d3182e6afe915924568f8d/python/tvm/relay/frontend/tflite.py#L3278-L3284 The value of use_regular_nms is always Flase，becasue use_regular_nms=True is not yet supported in tvm。 https://github.com/tensorflow/tensorflow/blob/47c541330813f575057d7af90ef55985baca87eb/tensorflow/lite/kernels/detection_postprocess.cc#L882-L887 The result will suppress all detections regardless of class_id in tflite，when the value of use_regular_nms is always Flase. Therefore,the value of force_suppress should be true. [tflite_graph_with_postprocess.zip](https://github.com/apache/tvm/files/9443753/tflite_graph_with_postprocess.zip) There is a model，you can try adjust the code in test_forward.py of tflite,where is in https://github.com/apache/tvm/blob/3d41ac3a9ab58ba5f7d3182e6afe915924568f8d/tests/python/frontend/tflite/test_forward.py#L4309-L4336 there is my example:  It will get a Mismatched elements. -- 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]
