[Relax][Frontend][TFLite] Add segment operator mappings

[Aharrypotter]

Summary

This PR adds Relax TFLite frontend support for the following segment operators from #19412:

• SEGMENT_SUM
• UNSORTED_SEGMENT_MIN
• UNSORTED_SEGMENT_PROD

These operators are lowered through relax.op.scatter_nd with the corresponding reduction modes.

Changes

TFLite Frontend

1. Add TFLite converter mappings for segment operators:

   • SEGMENT_SUM -> scatter_nd(..., reduction="add")
   • UNSORTED_SEGMENT_MIN -> scatter_nd(..., reduction="min")
   • UNSORTED_SEGMENT_PROD -> scatter_nd(..., reduction="mul")

2. Add shared segment lowering logic:

   • Convert segment_ids into scatter indices via expand_dims.
   • Build the output shape from num_segments or constant segment_ids.
   • Initialize the scatter base tensor with the correct reduction identity.

Tests

Add TFLite frontend tests for:

• test_segment_sum
• test_unsorted_segment_min
• test_unsorted_segment_prod

Each test verifies the imported Relax IR lowers to R.scatter_nd with the expected reduction mode and base tensor initialization.

Testing

All targeted tests pass:

python -m pytest  \
  tests/python/relax/test_frontend_tflite.py::test_scatter_nd \
  tests/python/relax/test_frontend_tflite.py::test_segment_sum \
  tests/python/relax/test_frontend_tflite.py::test_unsorted_segment_min \
  tests/python/relax/test_frontend_tflite.py::test_unsorted_segment_prod \
  -q

References

• Issue [Tracking Issue][TFlite] Expand Missing / Partial Operator Coverage #19412: TFLite Relax frontend operator support tracking
• Related PR [Relax][Frontend][TFLite] Add SCATTER_ND operator for Relax TFLite #19490: Adds SCATTER_ND support

[gemini-code-assist]

Code Review

This pull request adds support for SEGMENT_SUM, UNSORTED_SEGMENT_MIN, and UNSORTED_SEGMENT_PROD operators in the TFLite frontend by lowering them to relax.op.scatter_nd. The implementation includes helper functions for identity base tensor creation and segment count calculation, along with corresponding unit tests. A syntax error was identified in the SEGMENT_SUM error handling logic where a closing parenthesis is incorrectly placed, which would lead to a failure during execution.

[tlopex]

Could you resolve the conflict so that we can merge it in?

[Aharrypotter]

I'll resolve the conflicts and update the PR shortly.

[Aharrypotter]

Please take a look @tlopex. Fixed alphabetical ordering of operator mappings.