i-robot
20f3a911f1
!34094 Remove the context option: 'enable_sparse'.
...
Merge pull request !34094 from 张清华/opt
2022-05-20 00:52:05 +00:00
Zhang Qinghua
d7762f1c8d
Add bprop_return_sparse flag for sparse bprop primitive and remove context option: 'enable_sparse'.
2022-05-19 17:31:57 +08:00
fujianzhao
7fcb75beaa
[feat] [assistant] [ops] [I51VS2] Add new operator nn.AdaptiveMaxPool1d
2022-05-18 15:50:44 +08:00
fujianzhao
cb56dd895d
[feat] [assistant] [ops] [I51VS1] Add new operator nn.AdaptiveAvgPool1d
2022-05-16 16:19:24 +08:00
i-robot
c07819796c
!34221 [feat] [assistant] [ops] [I51VSC] Add new operator nn.HuberLoss
...
Merge pull request !34221 from fujianzhao/huberloss
2022-05-13 02:57:19 +00:00
i-robot
bfd377ca3c
!34125 add nn.ConstantPad1d nn.ConstantPad2d nn.ConstantPad3d and nn.ZeroPad2d
...
Merge pull request !34125 from ZhidanLiu/master
2022-05-13 01:53:23 +00:00
ZhidanLiu
fdd6f7c759
add nn.ConstantPad1d nn.ConstantPad2d nn.ConstantPad3d and nn.ZeroPad2d
2022-05-12 10:34:52 +08:00
fujianzhao
4fd3433d23
[feat] [assistant] [ops] [I51VSC] Add new operator nn.HuberLoss
2022-05-11 15:39:02 +08:00
fujianzhao
5bb57674da
[feat] [assistant] [ops] [I51VSB] Add new operator nn.Hardtanh
2022-05-11 14:23:11 +08:00
liqiliang
0fabbc4ccb
Add a nn cell for softsign.
2022-05-10 17:09:33 +08:00
He Wei
8b0d4e7751
Refactor optimizers to support flatten parameters
2022-04-20 20:23:31 +08:00
He Wei
0d12199928
Enable flatten_gradients for Adam optimizer
2022-04-15 19:49:57 +08:00
He Wei
723543eb5d
Modify Optimizer to support flatten parameters
...
1. Provide method to create Parameter from Tensor without copy;
2. Adapt optimizer.py to support flattened parameters;
3. Add unit test cases for parameter and optimizer.
2022-04-07 14:11:32 +08:00
xiao_yao1994
94df0869ad
uni_backend: add ut ge test
2022-03-10 16:08:36 +08:00
Margaret_wangrui
462c38813d
[ME] Add parameter name check.
2022-02-14 10:07:43 +08:00
liuyang_655
15a153a40d
Modify error info
2022-01-06 01:28:53 -05:00
wanyiming
ab65f4ac98
addut
2021-11-26 09:48:34 +08:00
chenzhuo
d07f24462c
add examples of grad, jvp and vjp
2021-11-16 14:15:26 +08:00
chenzhuo
f36edec3ff
add function jvp
2021-11-12 08:44:41 +08:00
Zhang Qinghua
b43693be23
Fix fallback and cell kwargs issues.
2021-10-27 14:06:02 +08:00
Bingya Weng
be20f00299
modify ut of probability
2021-10-14 19:33:34 +08:00
huanghui
ba66c0d491
add security isolate for save_graphs
2021-09-14 10:24:12 +08:00
i-robot
76fac95591
!23069 Modify error content
...
Merge pull request !23069 from huchunmei/master
2021-09-11 03:50:52 +00:00
huchunmei
c75773cf37
Modify error content
2021-09-10 15:21:33 +08:00
yanghaoran
0ced8775c4
upgrade Ascend software package 09 Sep 21
2021-09-09 20:30:22 +08:00
huangxinjing
6cea07f749
Add args check
2021-09-08 09:12:35 +08:00
yao_yf
82889ec56b
fixed sparse attention
2021-08-31 16:11:56 +08:00
i-robot
ff2e34b9f9
!22509 Add ut and st for Jvp, Vjp and Grad
...
Merge pull request !22509 from LiangZhibo/fix
2021-08-30 08:21:54 +00:00
Zhang Qinghua
a137fa1d0b
Optimize the Executors routines.
...
- Fix the key generating.
- Distinguish the executors.
2021-08-28 17:36:12 +08:00
l00591931
98fad9f08e
Add st and ut for jvp vjp and grad
2021-08-28 17:34:23 +08:00
zhihenghu
ce12c02343
Add Sparse Attention
...
adjut the file structure and name
Deleted extra information
Do some formatting work
Add test case and fix some document
fix imports
2021-08-28 11:50:58 +08:00
huangxinjing
62496d75f3
less the interface exposed
2021-08-25 21:22:40 +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
huangxinjing
d777742904
1. Move the class to mindspore.parallel, support activation sharding
2021-08-20 14:34:10 +08:00
huangxinjing
18044aff0f
1. Add docstring, elimitate attention mask, tuple append the deocoder return layer past
...
split attention inputs from two into three
Add input check and modify test case
Fix check error and add check to transformer inputs
add input check to the transformers
2021-08-16 21:08:48 +08:00
i-robot
2650aae9ba
!21351 complex support
...
Merge pull request !21351 from zhouyaqiang0/complex_support
2021-08-12 09:39:15 +00:00
zhouyaqiang
b81ba100b7
add complex number support
2021-08-12 10:36:43 +08:00
jiangzhenguang
a3bb780ce4
optimize run memory
2021-08-10 20:45:25 +08:00
huangxinjing
615d1a179d
Add transformer layer
2021-07-29 11:10:43 +08:00
huangbingjian
ad8f73f32b
set default context mode to GRAPH_MODE
2021-06-09 14:40:49 +08:00
huanghui
29f632613f
optimize log
2021-06-04 12:32:44 +08:00
huanghui
5acf3c8ade
[dfx]optimize exception info print
2021-05-31 14:57:29 +08:00
wangnan39@huawei.com
2761776699
add check for optimizer parameters
2021-05-17 22:23:03 +08:00
jiaqi
cdb7330818
diceloss bug
2021-03-09 16:23:45 +08:00
Zhang Qinghua
df866f7248
Add TopoSort Rhs First attribute for special CNode, such as Depend CNode with isolated nodes.
2021-03-06 12:39:36 +08:00
Zhang Qinghua
8b8c59f01e
Optimize the compile performance in Parser, FG, Manager and Renormalize:
...
---
Remove the routine of handling isolated nodes in Renormalize.
Add isolated nodes from Parser&Resolver.
Modify isolated nodes handling in FG&Manager.
Optimize the renormalize routines.
Other optimizations.
2021-03-04 16:01:54 +08:00
Jiaqi
112b8488c5
add rmse loss
2021-02-25 17:03:07 +08:00
Jiaqi
fd1a4726b7
add focal loss
2021-02-22 19:33:26 +08:00
Jiaqi
952e245000
add multclass diceloss
2021-02-19 15:43:30 +08:00