projects / platform / upstream / pytorch.git / commit
? search:
summary | shortlog | log | commit | commitdiff | tree
(parent: 4371cb5) | patch
Add empty_quantized (#18960)
authorJerry Zhang <jerryzh@fb.com>
Wed, 17 Apr 2019 23:10:05 +0000 (16:10 -0700)
committerFacebook Github Bot <facebook-github-bot@users.noreply.github.com>
Wed, 17 Apr 2019 23:17:40 +0000 (16:17 -0700)
commitad8f34fcca6aadbe0711227e43f87ae47cf417eb
tree2708643a6bab2bea35cf632ac6ace61e7bb2c59etree | snapshot
parent4371cb5e0193d2eaa8d23673eb153874113eab4ecommit | diff
Add empty_quantized (#18960)

Summary:
Pull Request resolved: https://github.com/pytorch/pytorch/pull/18960

empty_affine_quantized creates an empty affine quantized Tensor from scratch.
We might need this when we implement quantized operators.

Differential Revision: D14810261

fbshipit-source-id: f07d8bf89822d02a202ee81c78a17aa4b3e571cc
aten/src/ATen/native/native_functions.yaml diff | blob | history
aten/src/ATen/native/quantized/TensorFactories.cpp [new file with mode: 0644] blob
aten/src/ATen/quantized/Quantizer.cpp diff | blob | history
aten/src/ATen/quantized/Quantizer.h diff | blob | history
aten/src/ATen/test/quantized_test.cpp diff | blob | history
c10/core/QScheme.h diff | blob | history
test/test_torch.py diff | blob | history
Domain: Machine Learning / ML Framework;