Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
0
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
45,876 Commits 24 Branches 0 Tags 3.9 GiB
Commit Graph

45876 Commits

Author SHA1 Message Date
jianghui58 ba796f95de modify train api 2022-05-20 17:37:00 +08:00
wuweikang e689d57fe2 resnet50_cifar10 test for ge process 2022-05-20 17:31:07 +08:00
He Wei 2d7c4334ec Support fusion_size argument for flatten_weights 2022-05-20 17:11:48 +08:00
ling 16c573e1ea softshrink softshrinkgrad 2022-05-20 17:09:07 +08:00
i-robot df9c0d2ff5
!34060 Enable dynamic shape for ms_function decorated inner cell 
Merge pull request !34060 from JoyLvliang/enable_ms_function_dynamic_shape_for_non_top_cell
 2022-05-20 09:07:44 +00:00
fanjibin 482f5efeb0 support vmap for masked_fill 2022-05-20 16:54:19 +08:00
wangchangheng ab78aa86ee optimize lamb 2022-05-20 16:50:45 +08:00
i-robot 23a3cc7c4e
!34693 Refactor the UnaryGradOpGpuKernelMod by new interfaces. 
Merge pull request !34693 from liqiliang/unarygrad-gpu
 2022-05-20 08:48:27 +00:00
huanghui 8137dfa0a9 add st for fallback constant control flow with 320 321 322 2022-05-20 16:40:43 +08:00
i-robot 6ceac21fa6
!34661 [MS]{Lite][Task] apply lite code permission 
Merge pull request !34661 from 刘力力/master
 2022-05-20 08:29:36 +00:00
i-robot 7c6c9f51ee
!34612 [MS][Lite][Task] add extendrt and opt cmake 
Merge pull request !34612 from 刘力力/feature_cloud_infer_runtime_develop_tmp_merge
 2022-05-20 08:27:36 +00:00
i-robot fabdc43d3b
!34677 Fix out-of-bounds in user defined sampler 
Merge pull request !34677 from xiaotianci/fix_udf_sampler
 2022-05-20 08:26:28 +00:00
i-robot 725875010e
!34391 refactor scatter_nd_arithmetic_cpu_kernel 
Merge pull request !34391 from zhuzhongrui/pub_master2
 2022-05-20 08:21:00 +00:00
zhangyinxia 86895a1514 add deformable offsets pass 2022-05-20 16:18:03 +08:00
i-robot 7359855538
!34644 change aicpu memcpy extinfo for profiling 
Merge pull request !34644 from TuDouNi/pass_support_dynamic
 2022-05-20 08:14:06 +00:00
i-robot c6b79f4f57
!34699 Update space to batch nd doc 
Merge pull request !34699 from zichun_ye/code_docs_space_to_batch_nd
 2022-05-20 08:02:26 +00:00
i-robot b4178ff210
!34709 fix scatter_nd_add && scatter_nd_sub doc api 
Merge pull request !34709 from zhuzhongrui/code_docs_scipy
 2022-05-20 07:58:50 +00:00
zhangzhaoju 53cf9dd2c5 Add Wl,--no-as-needed to make sure train.so been linked 2022-05-20 15:48:14 +08:00
z00512249 7ec5d95d9d fix scatter_nd_add && scatter_nd_sub doc api 2022-05-20 15:35:12 +08:00
zhuyuxiao ce16351d16 add CPU support for KLDivLoss op 2022-05-20 15:34:31 +08:00
zhixinaa d30d43b70d [feat] [assistant] [ops] [I4ZZUR] New GPU operator implementation, include RightShift 2022-05-20 15:33:37 +08:00
shaojunsong 17564d6749 fixed example in export function from seralization.py 2022-05-20 15:18:57 +08:00
i-robot 294b9101d1
!34708 Fix the indent of mutable docs 
Merge pull request !34708 from YuJianfeng/code_docs
 2022-05-20 07:07:15 +00:00
limingqi107 817e60a308 add tensor/functional interface for diag op 2022-05-20 15:05:11 +08:00
zhangxuetong c089794e62 fix review comments 2022-05-20 14:53:26 +08:00
i-robot e0530f8ff6
!34598 Fix optimizer compile performance 
Merge pull request !34598 from ZPaC/fix-optimizer-compile-issue
 2022-05-20 06:50:07 +00:00
jonyguo 0718a283c8 filter dumplicate log from python operation 2022-05-20 14:46:46 +08:00
张勇贤 a0f6e58790 [MSLITE] Support TensorRT Unstack Op 2022-05-20 14:46:12 +08:00
i-robot 462055aee1
!34588 解决dictionary-list 子图消除error. 
Merge pull request !34588 from lanzhineng/issue
 2022-05-20 06:44:35 +00:00
yujianfeng 9dd11c6c6d Fix the indent of mutable docs 2022-05-20 14:41:03 +08:00
Arielxyx 44543ad95c [feat][assistant][I4XJG1] add new function LogAddExp 2022-05-20 14:37:32 +08:00
Parallels cdbbd315d8 Support reconnect to meta server if heartbeat connection broken 2022-05-20 14:26:53 +08:00
Zichun Ye 54c1a18da5 update space_to_batch_nd functional api doc 
update space_to_batch_nd functional api doc

update space_to_batch_nd functional api doc
 2022-05-20 14:19:31 +08:00
zengzitao 816a6ea81c add ResetResource func to support gather_nd dynamic shape on GPU 2022-05-20 14:14:32 +08:00
i-robot 0829f10565
!34666 Fix tensor copy constructor 
Merge pull request !34666 from zjun/fix_bug4
 2022-05-20 06:11:15 +00:00
i-robot 57216a7b80
!34683 Add epoch number for lenet train 
Merge pull request !34683 from ZPaC/fix-full-ps-lenet-acc
 2022-05-20 06:08:49 +00:00
i-robot c5d08781bb
!34629 Add tensor and functional interface for MatrixDiagV3 operator. 
Merge pull request !34629 from hezhenhao1/add_matrix_diag
 2022-05-20 06:04:28 +00:00
yanghaoran a10015c6fa fix code coverage, but this may lead to incorrect coverage results 2022-05-20 13:54:14 +08:00
张勇贤 64be94cfc6 [MSLITE] Fix bug for delegate graph input output 2022-05-20 12:55:30 +08:00
i-robot d68d64bb92
!34648 optimizes the documentation of chinese API of MSSSIM,ACos,Abs,etc 
Merge pull request !34648 from zhangfanghe/code_docs_master_11_519
 2022-05-20 04:03:16 +00:00
liu lili e0ecc973ff mindspore lite: add extendrt and opt cmake 2022-05-20 11:23:53 +08:00
liqiliang c2d3c75161 Refactor the UnaryGradOpGpuKernelMod by new interfaces. 2022-05-20 11:19:56 +08:00
i-robot 421cbf82f4
!31810 [assistant][ops] Add new LogAddExp2 
Merge pull request !31810 from wxy220/LogAddExp2
 2022-05-20 03:08:03 +00:00
i-robot f649965a12
!34653 Update nn.AdaptiveMaxPool1d and nn.AdaptiveAvgPool1d docs 
Merge pull request !34653 from fujianzhao/adaptive_avg_pool_1d_doc_fix
 2022-05-20 02:59:20 +00:00
i-robot 698ec02a9d
!34670 adapt vmap for scatter_min operator 
Merge pull request !34670 from hujiahui8/scatter_min
 2022-05-20 02:58:07 +00:00
z00512249 1612b9b506 refactor scatter_nd_arithmetic_cpu_kernel 2022-05-20 10:33:23 +08:00
i-robot 968672f98f
!34667 optimize scale grad code 
Merge pull request !34667 from chujinjin/fix_scale_grad_code
 2022-05-20 02:28:03 +00:00
i-robot 98badab6a7
!34672 Fix format for set_dump api introduce 
Merge pull request !34672 from maning202007/code_docs_dump_api
 2022-05-20 02:02:30 +00:00
i-robot 9b0d37c7e7
!34657 support const-test if 
Merge pull request !34657 from hangq/rewrite-pr
 2022-05-20 01:55:52 +00:00
dayschan 387b6baf2b add a pattern to process elemwise areas only 
1. Change the original `elemwise_depth` pattern to `elemwise_depth` and `broadcast_depth`.
   the new `elemwise_depth` only process the elemwise nodes, while the `broadcast_depth`
   process elemwise and explicit broadcast nodes.
2. `elemwise_width` does the same.
3. don't fuse the broadcast area in broadcast_tot when `Reshape` op exists.
4. move the `broadcast_tot` pattern before the `broadcast_depth` pattern.
 2022-05-20 09:51:51 +08:00