torch-mlir/lib
Rob Suderman 306ed62edd
[onnx][torch] Fix `onnx.SoftmaxCrossEntropyLoss` for ignore index (#3585)
There were two issues related to `ignore_index` being set

(1) the onnx-to-linalg pass as not reading the value correctly (2) the
mean pass was not considering the `ignore_index` value

For (2) when taking the mean we need to know how many of the values were
considered in the sum and therefore we cannot divide by the total number
of elements. Adding a summation across the total number should correct
this issue.
2024-08-02 09:00:56 -07:00
..
CAPI [ONNX] add int16 quantization support (#3446) 2024-06-12 10:37:22 +05:30
Conversion [onnx][torch] Fix `onnx.SoftmaxCrossEntropyLoss` for ignore index (#3585) 2024-08-02 09:00:56 -07:00
Dialect [Torch] Add support for static uneven divisible AdaptiveAvgPool2d (#3566) 2024-08-01 11:37:53 +08:00
RefBackend [NFC] Change to *cast instead of .*cast variants (#3405) 2024-05-30 23:45:13 -07:00
CMakeLists.txt Link necessary op interface implementations (#3364) 2024-06-03 19:43:28 -05:00
InitAll.cpp [Stablehlo] legalize deprecated ops to stablehlo ops (#3543) 2024-07-17 00:05:11 +08:00