Lara Haidar 45024e7a35 Support Exporting Bitshift to ONNX (#28210) ... Summary: Support exporting left/right bitshifts to ONNX for all opset versions. ONNX has a bitshift operator in opset 11, but it only supports unsigned ints, so it can't be used in PyTorch (since only uint8 is the only uint type). Pull Request resolved: https://github.com/pytorch/pytorch/pull/28210 Reviewed By: hl475 Differential Revision: D18575512 Pulled By: houseroad fbshipit-source-id: 74161db67f599996a0614981edcc171af6780d21		2019-11-19 09:25:50 -08:00
..
__init__.py	Disabling ONNX IR v4 sematics for opset 8 or lower. (#28990)	2019-11-06 21:57:21 -08:00
operators.py	Move torch.onnx.operators functions into ATen (#12803)	2018-10-18 16:04:34 -07:00
symbolic_caffe2.py	Add support for quantized operator conversion from PT to C2 via ONNX (#29694)	2019-11-18 12:12:40 -08:00
symbolic_helper.py	Add support for quantized operator conversion from PT to C2 via ONNX (#29694)	2019-11-18 12:12:40 -08:00
symbolic_opset7.py	Export Meshgrid (#26037)	2019-10-25 16:59:22 -07:00
symbolic_opset8.py	Fix jit outplace tracing and reapply changes to *_like operators. (#28839)	2019-10-31 13:23:08 -07:00
symbolic_opset9.py	Support Exporting Bitshift to ONNX (#28210)	2019-11-19 09:25:50 -08:00
symbolic_opset10.py	Opset 11 updates (#28225)	2019-11-04 12:16:12 -08:00
symbolic_opset11.py	Support Exporting Bitshift to ONNX (#28210)	2019-11-19 09:25:50 -08:00
symbolic_registry.py	PyTorch export to ONNX Opset 7 and 8 - Cont (#22421)	2019-07-12 14:52:48 -07:00
utils.py	Add support for quantized operator conversion from PT to C2 via ONNX (#29694)	2019-11-18 12:12:40 -08:00