torch-mlir/lib/Conversion
zjgarvey 074098d20c
Modifies onnx resize lowering to fix numerical issues (#3381)
Updates:

- some unsupported modes are now going to report a match failure for
unsupported coordinate transformation modes.
- fixes a bug that was introduced in the last patch for resize (my
bad...)
- uses actual x and y coordinates for computing weights in bilinear
interpolation (rather than eps modified values)
- slightly simplifies the bilinear interpolation payload for readability
and performance
- passes coordinate transformation mode information from an onnx.Resize
op to the mode string for the aten._interpolate op. This allows us to
perform custom logic in the torch->linalg lowering to support
onnx.Resize options without losing the default behaviors of the
interpolate op.
2024-05-30 20:34:37 -04:00
..
TorchConversionToMLProgram [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
TorchOnnxToTorch Modifies onnx resize lowering to fix numerical issues (#3381) 2024-05-30 20:34:37 -04:00
TorchToArith [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
TorchToLinalg Modifies onnx resize lowering to fix numerical issues (#3381) 2024-05-30 20:34:37 -04:00
TorchToSCF [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
TorchToStablehlo [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
TorchToTMTensor [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
TorchToTensor [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
TorchToTosa [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
Utils [NFC] Remove unused header files (#3386) 2024-05-30 14:30:36 +08:00
CMakeLists.txt [torch] Improve shape inference for `torch-to-linalg` path for reshapes (#3055) 2024-03-26 12:41:40 -07:00
PassDetail.h Minor fixes for `ConvertTorchConversionToMLProgram`. (#1991) 2023-04-04 09:09:58 -07:00
Passes.cpp Clang format refresh (#2812) 2024-01-29 12:59:33 -05:00