Vasiliy Kuznetsov 65df8b3886 hardswish: make it work in static quantization (#36545) ... Summary: Pull Request resolved: https://github.com/pytorch/pytorch/pull/36545 * adds a quantized nn.module for Hardswish so we can observe activation values * modifies the hardswish op to allow specifying scale + zero_point * makes hardswish model be properly swapped in static quantization Test Plan: added tests and they pass for: * the new _out flavor of hardswish * QNNPACK changes * static quant e2e Imported from OSS Differential Revision: D21045320 fbshipit-source-id: ab7e52f0f54a7d5923ab6f58197022cc28c12354		2020-04-15 18:02:35 -07:00
..
__init__.py	Ignore F401 in all __init__.py without putting noqa (#25823)	2019-10-23 15:28:13 -07:00
_numeric_suite.py	[PyTorch Numeric Suite] Add weight compare API (#36186)	2020-04-13 19:02:00 -07:00
_quantize_script.py	[quant][graph] Add quant fusion for dynamic quantization (#35586)	2020-03-30 23:34:56 -07:00
default_mappings.py	hardswish: make it work in static quantization (#36545)	2020-04-15 18:02:35 -07:00
fake_quantize.py	Per channel quantization performance improvement (#33772)	2020-02-26 10:19:25 -08:00
fuse_modules.py	[quant] Enable fusion for conv modules with bias (#36173)	2020-04-08 15:53:32 -07:00
observer.py	[quant][graphmode] Add new tensorlist observer for LSTM (#35893)	2020-04-03 10:41:28 -07:00
qconfig.py	[quant][graph] Add a new observer type for dynamic quantization (#35455)	2020-03-26 17:38:21 -07:00
quantize.py	Add the more fusion (conv3d and batchnorm)support in pytorch quantization flow (#33540)	2020-03-23 20:36:03 -07:00
stubs.py	Factored out the default mappings	2019-10-03 11:52:21 -07:00