History

Ramiro Leal-Cavazos 25a2c8bd85 Add notes on missing lazy tensor ops for ResNet18 and MaskRCNN		2021-09-30 16:38:12 -07:00
..
README.md	Add notes on missing lazy tensor ops for ResNet18 and MaskRCNN	2021-09-30 16:38:12 -07:00
builder.py	Implement the lazytensor package (#331 )	2021-09-28 17:25:06 -07:00

README.md

Future Work for Lazy Tensor Core

In the last part of the section Understand The Metrics Report, it is mentioned that after running the metrics report,

If you see aten:: ops other than nonzero and _local_scalar_dense, that usually means a missing lowering in the accelerator plugin.

Looking at the sample output and the sample output produced by running a ResNet18 model and a MaskRCNN model, respectively, on the Lazy Tensor Core using the TorchScript backend, the following operations are needed and not yet supported by the backend:

aten::convolution_overrideable
aten::max_pool2d_with_indices
aten::mean.out
aten::sort
aten::arange.start_out
aten::bitwise_and.Tensor_out
aten::clamp.out
aten::exp.out
aten::index.Tensor
aten::nonzero
aten::rsqrt.out
aten::sigmoid.out
aten::topk.values
aten::upsample_nearest2d.out

Note: This list is incomplete because currently the MaskRCNN example crashes halfway through when run on LTC. The output error can also be found in the MaskRCNN sample output.