p47068915
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

!7987 add type check for ActQuant's activation param 

Merge pull request !7987 from yuchaojie/quant3
This commit is contained in:
mindspore-ci-bot 2020-10-30 15:43:02 +08:00 committed by Gitee
parent f1a410e237 cfd270ea66
commit b77cb32c37
1 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

3
mindspore/nn/layer/quant.py
View File

@ -1057,7 +1057,7 @@ class ActQuant(_QuantActivation):
Please check `FakeQuantWithMinMaxObserver` or other observer for more details.
Args:
activation (Cell): Activation cell class.
activation (Cell): Activation cell.
ema_decay (float): Exponential Moving Average algorithm parameter. Default: 0.999.
quant_config (QuantConfig): Configs the oberser types and quant configs of weight and activation. Default:
both set to default FakeQuantWithMinMaxObserver.
@ -1084,6 +1084,7 @@ class ActQuant(_QuantActivation):
quant_config=quant_config_default,
quant_dtype=QuantDtype.INT8):
super(ActQuant, self).__init__()
self.act = Validator.check_isinstance("activation", activation, Cell)
self.fake_quant_act = quant_config.activation(min_init=-6,
max_init=6,
ema=False,