chengxianbin
|
4a76059f2b
|
fix quant export bug
|
5 years ago |
simson
|
7cc48a9af8
|
Third round of enhancement of API comment & README_CN
|
5 years ago |
chengxianbin
|
b97ed00c89
|
modify quant code
|
5 years ago |
mindspore-ci-bot
|
bc702459bc
|
!4319 upload yolov3-darknet quant net codes
Merge pull request !4319 from chengxb7532/master
|
5 years ago |
chengxianbin
|
759392571f
|
upload yolov3-darknet53 quant code
|
5 years ago |
mindspore-ci-bot
|
6d557a9892
|
!4199 [MS][QUANT] mindspore model zoo example for hand make quant graph
Merge pull request !4199 from chenzhongming/quant
|
5 years ago |
chenzomi
|
94fd9dd8cf
|
[MS][QUANT] mindspore model zoo example for hand make quant graph
|
5 years ago |
simson
|
dec2e4a819
|
Third round of the enhancement of API comments
|
5 years ago |
chenzomi
|
26b1242bc4
|
mobilenetV2 change for gpu
|
5 years ago |
chenzomi
|
315c6a5742
|
quant aware training add without bn fold and bn fold
|
5 years ago |
chenzomi
|
ed2e84d4ed
|
add LeakReLUQuant OP for bug fix.
|
5 years ago |
chenzomi
|
b8686fc5bf
|
bug fix for quant.py in train/ and nn/
|
5 years ago |
Wei Luning
|
7d5c9d52bc
|
fix geir export bugs
|
5 years ago |
Wei Luning
|
28d1d37085
|
End at validate when export.
|
5 years ago |
buxue
|
6d5c580a61
|
change shape and dtype of tensor from interface to attr
|
5 years ago |
mindspore-ci-bot
|
d3ec05d716
|
!2943 [quant]export bug fix
Merge pull request !2943 from vlne-v1/quant_export_bugfix
|
5 years ago |
Wei Luning
|
b522368161
|
fix bug of quant export without input fakequant.
|
5 years ago |
chenzomi
|
2ff29f0198
|
fix hswishquant and hsigmoidquant validation false bug
|
5 years ago |
chenzomi
|
3446940142
|
bug fix in quantization aware training auto create graph
|
5 years ago |
chenzomi
|
d383ade6f9
|
add mobilenetV2 quant export
|
5 years ago |
chenzomi
|
9b7a426c6b
|
bug fix in auto create quant graph in master
|
5 years ago |
chenzomi
|
1089c908a9
|
cherry-pick r0.5 to master for quantizaiton aware training
|
5 years ago |
wangdongxu
|
02584fe2c7
|
fix perchannel num_channels not set bug and adjust quant.py params order
|
5 years ago |
chenzomi
|
a834a6308e
|
change some comment name in the whole project
|
5 years ago |
chenzomi
|
c268c88220
|
aware quantization training auto create graph
|
5 years ago |
mindspore-ci-bot
|
9958bc479a
|
!2161 [qat]Export network from quantization aware network to deploy
Merge pull request !2161 from vlne-v1/I1IZV3-quant-infer
|
5 years ago |
Wei Luning
|
1d77bf86a9
|
Exports MindSpore quant predict model to deploy with GEIR
|
5 years ago |
chenzomi
|
bbce6faff9
|
remove _quant_ops.py from __init__.py
|
5 years ago |
王东旭
|
4e09ae83eb
|
fix FakeQuantPerLayer/FakeQuantPerLayerGrad symmetric bug
|
5 years ago |
chenzomi
|
4878616e43
|
change combined to nn
|
5 years ago |
buxue
|
66bbdb4a31
|
change tensor dtype and shape from function to attr
|
5 years ago |
chenzomi
|
185d80930b
|
fake quant debug
|
5 years ago |
chenzomi
|
d7a4ae2e34
|
bug fix in fake quant training in r0.3
|
5 years ago |
chenzomi
|
4da1e21f45
|
bug fix in fake quant
|
5 years ago |
zhaozhenlong
|
1f342fb926
|
add op BroadcastTo
|
5 years ago |
chenzomi
|
b7db3e9a4b
|
add fake quant per channel and bug fix
|
5 years ago |
wandongdong
|
1c3e579687
|
fix bug in quant and correction_mul_grad
|
6 years ago |
wangdongxu6
|
9eee157c58
|
fix some quant op bug
|
6 years ago |
王东旭
|
881d0f6a9b
|
format code
|
6 years ago |
王东旭
|
02e7237a91
|
fix some quant op bug
|
6 years ago |
wandongdong
|
d35c41e737
|
add custom tbe ops for quant aware training
|
6 years ago |
mindspore-ci-bot
|
75a26fded1
|
!1223 Add examples for the mindspore.ops.operations and minspore.nn package operator
Merge pull request !1223 from zhouneng/add_examples_for_ops
|
6 years ago |
zhouneng
|
3cc750fdce
|
为mindspore.ops.operations包和mindspore.nn包添加Examples
|
6 years ago |
chenzomi
|
9e7099d9ab
|
fix bug in nn quant
|
6 years ago |
shijianning
|
f2230fb070
|
fix pylint warnings
|
6 years ago |
chenzomi
|
1239cd6135
|
Merge branch 'master' into 04quant
|
6 years ago |
chenzomi
|
1397326c46
|
add quant.py and change the format of __init__
|
6 years ago |