[BugFix][Relax][ONNX] Honor auto_pad in ConvTranspose converter

[swjng]

Motivation

The ConvTranspose ONNX → Relax converter silently drops the auto_pad attribute. Conv has dedicated handling (onnx_frontend.py lines 1383-1404), but ConvTranspose passes pads straight through, defaulting to 0 when the attribute is absent. Models that rely on auto_pad=SAME_UPPER/SAME_LOWER/VALID therefore produce the wrong output shape after import.

Minimal repro (against onnxruntime):

node = helper.make_node(
    "ConvTranspose", ["X", "W"], ["Y"],
    strides=[2, 2], auto_pad="SAME_UPPER",
)
# input  X: [1, 1, 4, 4], W: [1, 1, 3, 3]
# ORT  -> Y.shape = (1, 1, 8, 8)   # input * stride
# TVM  -> Y.shape = (1, 1, 9, 9)   # auto_pad ignored, pads=0

Fix

Compute pads from the ONNX spec equation before delegating to the Relax conv-transpose op:

total_pad[i] = stride[i] * (in[i] - 1)
             + output_padding[i]
             + (kernel[i] - 1) * dilation[i] + 1
             - in[i] * stride[i]

then split begin/end by SAME_UPPER vs SAME_LOWER. VALID becomes pads=0; NOTSET keeps the user-supplied pads. We deliberately do not reuse Conv's autopad() helper because it pads the input data, whereas ConvTranspose subtracts pads from the output.

The output_shape attribute (which, when set, also overrides pads per spec) remains unsupported; leaving that as a follow-up.

Test plan

• `pytest tests/python/relax/test_frontend_onnx.py::test_conv_transpose_auto_pad` — 6 new cases (3 modes × 2 strides) for 1D/2D/3D pass.
• `pytest tests/python/relax/test_frontend_onnx.py::test_conv_transpose` — existing 8 parameterizations still pass.

[gemini-code-assist]

Code Review

This pull request introduces support for the auto_pad attribute in the ConvTranspose operator within the ONNX frontend, covering SAME_UPPER, SAME_LOWER, and VALID modes, and includes new test cases. Feedback suggests simplifying the padding calculation to avoid dependencies on input spatial dimensions, which prevents potential TypeErrors when handling symbolic shapes in Relax.

[tlopex]

LGTM