Commit Graph

55 Commits

Author SHA1 Message Date
Zhang Qinghua a137fa1d0b Optimize the Executors routines.
- Fix the key generating.
- Distinguish the executors.
2021-08-28 17:36:12 +08:00
ms_yan 36a8886ca2 Revert "[feat] [assistant] [I3T96T] add new Dataset operator CMUARCTICDataset"
This reverts commit b077aa1cab.

Revert "[feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset"

This reverts commit 4e6f7dc97d.

delete pass_registry_test.cc

comment  hiai_nlu_model_multi.pb related  line
2021-08-23 01:46:38 +08:00
djc 4e6f7dc97d [feat] [assistant] [I3T96X] add new Dataset operator LibriSpeechDataset 2021-08-22 13:39:37 +08:00
i-robot 962c3f4ae3 !21632 add post training quant of unet,maskrcnn,crnn,deeplabv3
Merge pull request !21632 from chenzhuo/quant
2021-08-14 11:27:33 +00:00
chenzhuo 3d0b6839c1 add post training quant of unet,maskrcnn,crnn,deeplabv3 2021-08-13 09:42:31 +08:00
zhang__sss 5fed27b32d api modify 2021-08-09 16:03:39 +08:00
zhang__sss da2db8780e add all for api 2021-07-20 17:12:35 +08:00
zhang__sss b4a9dcc59b code clean 2021-07-15 14:55:13 +08:00
i-robot 5cde059ef3 !19854 clearing the untrusted code of quantization
Merge pull request !19854 from Erpim/master
2021-07-12 11:24:10 +00:00
Erpim 300456a2d7 clearing the untrusted code of quantization 2021-07-10 11:24:28 +08:00
zhang__sss dd1f1c26d9 code clean 2021-07-10 07:57:13 +08:00
Erpim ce2c5d5fce modified the quant API document description 2021-06-29 09:54:13 +08:00
zhang__sss 40ef894029 modify weight offset for air 2021-06-17 19:40:38 +08:00
i-robot 6103989fcc !18003 finish q8bert task
Merge pull request !18003 from chenzhuo/q8bert
2021-06-10 08:49:24 +08:00
chenzhuo 9865ce6ed8 fix q8bert bugs 2021-06-09 22:57:25 +08:00
mindspore-ci-bot 82faa51cc9 !17756 quant cal zp error for 310
From: @zhang__sss
Reviewed-by: @zlq2020,@zhoufeng54
Signed-off-by: @zlq2020
2021-06-05 11:32:19 +08:00
mindspore-ci-bot 475386e338 !17569 Modified the ST of lenet_quant, and fix the neg_trunc bug for manual quantization
From: @erpim
Reviewed-by: @zhang__sss,@zlq2020,@zh_qh
Signed-off-by: @zlq2020
2021-06-04 14:38:27 +08:00
zhang__sss 15e2f2eb31 zp=0 2021-06-04 09:30:32 +08:00
Erpim 02228d342c Modified the ST of lenet_quant, and fix the neg_trunc bug for manual quantization 2021-06-03 09:29:53 +08:00
zhang__sss 43948d255a lsq end to end 2021-06-01 21:05:52 +08:00
mindspore-ci-bot 196156d4c2 !16721 modify api doc about quant
From: @zhang__sss
Reviewed-by: @zhoufeng54,@zh_qh
Signed-off-by: @zh_qh
2021-05-25 10:02:11 +08:00
zhang__sss 9626c3a1ae api_modify 2021-05-24 15:09:28 +08:00
Erpim 275f247946 fix quant model export mindir failed bug 2021-05-18 21:10:49 +08:00
mindspore-ci-bot f8f1f0f84d !16362 Quant end to end accuracy testing
From: @zhang__sss
Reviewed-by: @zh_qh,@zlq2020,@liangchenghui
Signed-off-by: @zh_qh
2021-05-17 17:13:07 +08:00
zhang__sss 79cfdd8692 quant_export_910 2021-05-13 19:22:32 +08:00
Erpim 2e9c9a6d4f fix lsq quant bugs 2021-05-10 21:38:41 +08:00
Erpim 5ece4a338c fix lenet quant testcase failed occasionally 2021-05-08 16:50:59 +08:00
Erpim 90d5d5dab3 add lsq quantization method 2021-04-27 20:48:04 +08:00
zhang__sss 518de99cde quant export 2021-04-26 21:12:34 +08:00
dinglinhe 865cf68243 All the descriptions of batch normal under the mindspore folder have been uniformly updated to 'Batch Normalization' 2021-04-19 16:37:51 +08:00
mindspore-ci-bot 24319a647b !15322 fix momentum parameter of batchnorm in quantization
From: @chenzhuo42
Reviewed-by: @zh_qh,@zhoufeng54
Signed-off-by: @zh_qh
2021-04-19 14:17:57 +08:00
zhangyi fa2eaafa51 fix some error format for api comments. 2021-04-19 09:21:23 +08:00
chenzhuo 20fc2ca240 fix momentum of batchnorm in quantization 2021-04-17 16:56:10 +08:00
mindspore-ci-bot f47767b361 !14330 Amend manual quant export and add resnet50_quant export.py
From: @zhang__sss
Reviewed-by: @zhoufeng54
Signed-off-by:
2021-03-30 19:14:12 +08:00
zhang__sss 4c45b76eed resnet50 quant export 2021-03-30 14:20:52 +08:00
chengxianbin b64d8c54b3 fix bug of quant function 2021-03-29 21:43:49 +08:00
mindspore-ci-bot 6cd1a0b484 !13760 fix bug of quant export
From: @chengxb7532
Reviewed-by: 
Signed-off-by:
2021-03-23 19:54:44 +08:00
chengxianbin 85b3389caa fix bug of quant export 2021-03-23 14:50:27 +08:00
zhangyi ef0acc815c fix api comment grammer errors and formatting error. 2021-03-22 16:18:45 +08:00
yingchen d582883c03 fix api bugs 2021-03-15 17:46:07 +08:00
yepei6 908b590d8e update comments 2021-03-08 14:45:55 +08:00
l00591931 9ec100d069 Change TensorAdd to Add, from r1.1 to master 2021-02-01 17:53:52 +08:00
yanghaoran 58bae307d6 fix bugs 2021-01-14 20:31:49 +08:00
xiaoyisd 10062603a0 fix python api bug 2020-12-10 16:04:16 +08:00
xiaoyisd 5f18742e5c add use one conv 2020-11-26 13:49:51 +08:00
yuchaojie 1c095221e6 fix QuantizationAwareTraining note typo error 2020-11-23 14:33:59 +08:00
yuchaojie 01303fa88e move Conv2dBnAct,DenseBnAct to combined.py 2020-11-03 21:37:59 +08:00
yuchaojie 2bbe733fd6 add bool typecheck for conv param 2020-10-31 13:53:18 +08:00
yuchaojie e030754f3e Unify LeakyReLUQuant,HSwishQuant,HSigmoidQuant to ActQuant 2020-10-30 15:46:28 +08:00
yuchaojie 69d9e76d65 rename create_quant_config && add notes 2020-10-27 19:10:43 +08:00