mirror of https://github.com/llvm/torch-mlir
02327af998
Adds onnx ConvTranspose support for autopadding (https://github.com/nod-ai/SHARK-ModelDev/issues/839). - Adds support for attribute auto_pad="SAME_UPPER" or "SAME_LOWER" which will automatically calculate padding of input based on output shape. - Adds support, during auto-padding, for output_shape=[H,W] which overrides the default output shape of input_shape[i]*stride[i] (for spatial dimensions only). - Adds lit test for auto-padding. - Tests are added by https://github.com/nod-ai/SHARK-TestSuite/pull/370 NOTE: ConvTranspose still doesn't support asymmetric padding, therefore multiple original onnx tests still won't pass. |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| DefaultDomainAtoF.cpp | ||
| DefaultDomainGtoP.cpp | ||
| DefaultDomainQtoZ.cpp | ||
| OnnxRecurrentLayerOpExpanders.cpp | ||
| PassDetail.h | ||
| Passes.cpp | ||
| Patterns.cpp | ||
| TorchOnnxToTorch.cpp | ||
| Utils.cpp | ||