torch-mlir/test/Conversion/TorchOnnxToTorch
Angel Zhang 52be4bdc18
[ONNX] Fix bugs for the `onnx.OneHot` operator (#3334)
This commit fixes the bugs for the `onnx.OneHot` operator by:

1) Converting negative indices to non-negative indices
2) Handling both `int` and `float` types for `off` and `on` values
3) Using the correct result type

It also includes a new unit test.
2024-05-22 08:32:00 -04:00
..
ops Support onnx.If (#2825) 2024-04-30 18:36:40 +00:00
simple_ops_a_to_f.mlir Add attributes support for onnx cumsum op (#3241) 2024-05-11 02:09:01 +08:00
simple_ops_g_to_p.mlir [ONNX] Fix bugs for the `onnx.OneHot` operator (#3334) 2024-05-22 08:32:00 -04:00
simple_ops_q_to_z.mlir [ONNX] Implement Softsign op (#3373) 2024-05-21 12:10:26 -07:00
unsupported_fb_opt_ops.mlir Add attributes support for onnx cumsum op (#3241) 2024-05-11 02:09:01 +08:00