Nigel
/
mindspore
forked from mindspore-Ecosystem/mindspore
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity
46,627 Commits 24 Branches 0 Tags 3.9 GiB
Commit Graph

9968 Commits

Author SHA1 Message Date
liuchuting 38797fd535 perator CUDA operator performance data. 2022-06-14 14:20:27 +08:00
i-robot 091ef501d5
!35856 Add TensorData::has_sub_data() method 
Merge pull request !35856 from hewei/flatten_weights
 2022-06-14 06:12:49 +00:00
i-robot d7dab84181
!34704 [ASCEND/GPU] Dynamic data queue to support data sink with dynamic-shape data but without min/max shape 
Merge pull request !34704 from wYann/dynamic_queue
 2022-06-14 05:48:16 +00:00
i-robot 69fc09be50
!35866 rename Tensor.tensor_scatter_* to Tensor.scatter_* 
Merge pull request !35866 from yuchaojie/op_dev
 2022-06-14 05:46:05 +00:00
andy_wangrui 20dd3e333c remove case test_adam_apply_one_with_decay_dyn to level1 2022-06-14 13:13:44 +08:00
Lan-Ling 16aad8be1b update aicpu operator sspaddmm 2022-06-14 12:52:25 +08:00
i-robot 7f56bf8e60
!35750 DeformableOffsetsGrad cpu kernel implements 
Merge pull request !35750 from chenfei_mindspore/deformable-grad-cpu-impl
 2022-06-14 03:16:07 +00:00
ling b04d92fb0b soft shrink bug 2022-06-14 11:06:28 +08:00
i-robot cbd4720e14
!34307 support ResizeBilinear and ResizeBilinearGrad op 
Merge pull request !34307 from hanhuifeng/resize_bilinear
 2022-06-14 02:50:34 +00:00
i-robot 067212500a
!35863 Modify the channel from 8 to 64 in deformable offset grad test 
Merge pull request !35863 from guoqi/deformable_offsets_grad
 2022-06-14 02:47:07 +00:00
i-robot 411c1282ee
!33298 [assistant][ops] Add UnravelIndex 
Merge pull request !33298 from rnzhang/UnravelIndex
 2022-06-14 02:06:57 +00:00
i-robot a521bfa82a
!34385 [assistant][IdentityN] add new operator IdentityN 
Merge pull request !34385 from 李文轼/IdentityN
 2022-06-14 01:54:34 +00:00
looop5 1f2c7bc4ce remove Pad tensor interface 2022-06-14 09:21:22 +08:00
i-robot 6325e170c2
!35662 aicpu support priority replay buffer destroy 
Merge pull request !35662 from chenweifeng/aicpu-priority-replay-buffer-destroy
 2022-06-14 01:14:42 +00:00
i-robot 04dcc3c8f6
!35673 Unify the process of ms_function and bprop 
Merge pull request !35673 from caifubi/master-pynative-unified-ms-function-bprop
 2022-06-14 01:05:19 +00:00
i-robot f6672f05f4
!35812 Add MatrixSolve GPU Kernel 
Merge pull request !35812 from zhujingxuan/MatrixSolve
 2022-06-14 01:04:41 +00:00
i-robot aca9b62e76
!35819 add the test case of multi actor fusion 
Merge pull request !35819 from limingqi107/new_actor_runtime
 2022-06-14 00:55:32 +00:00
David 99680d0339 Added docs to ut cpp part 2 2022-06-13 14:45:48 -04:00
hanhuifeng2020 af70cc3b2c support ResizeBilinear and ResizeBilinearGrad op 2022-06-14 00:38:47 +08:00
fan-jibin 0168650200 add avgpool grad vmap 2022-06-13 20:48:41 +08:00
yuchaojie d65187f1ba rename Tensor.tensor_scatter_* to Tensor.scatter_* 2022-06-13 20:45:16 +08:00
Zichun Ye 2a893d828c add zichun_ye to akg related files' owner 
update akg related files' owner
 2022-06-13 20:33:28 +08:00
i-robot 309c01d800
!35502 [MD] Adding docstrings for minddata UT Cpp Part 1 
Merge pull request !35502 from davidanugraha/add_cpp_test_comment
 2022-06-13 12:16:02 +00:00
chenfei f294fba823 add kernel file 2022-06-13 20:12:11 +08:00
wilfChen 5f4d17f621 aicpu priority replay buffer destory 2022-06-13 19:59:06 +08:00
i-robot dbec13ca4a
!35650 支持SPMM算子 
Merge pull request !35650 from 黄晓/spmm_hxp_0609
 2022-06-13 11:49:01 +00:00
zhujingxuan fc84c41945 Add MatrixSolve GPU 2022-06-13 19:37:36 +08:00
jonyguo b451122bf3 del mindspore:: LogLevel 2022-06-13 19:11:30 +08:00
guoqi e67d508414 Modify the channel from 8 to 64 in deformable offset grad test case to get rid of a bug in run package. 2022-06-13 19:10:23 +08:00
He Wei 2c24157ccb Add TensorData::has_sub_data() method 2022-06-13 17:31:05 +08:00
xiongkun 1dfaa4c3c1 add data_format_dim_map vmap 
flip
 2022-06-13 17:17:59 +08:00
i-robot 2aa9519313
!35681 Extend export/load with customized encryption functions for MindIR 
Merge pull request !35681 from 张澍坤/master
 2022-06-13 08:43:41 +00:00
caifubi 6beb57eeec Unify the process of ms_function and bprop 
1. Support ms_function with control-flow.
2. Support ms_function with heterogenous.
3. Support ms_function with dynamic shape.
4. Fix bugs of testcases:
  4.1. The second output (argmax) of AdaptiveMaxPool2d is invalid on
  Ascend device target. Remove the assertion of argmax.
  4.2. Cannot define temporary operator with trainable_params in
  forward_hook.
  4.3. The network structure is not equivalent after adding hooks with
  the CompareNet.
 2022-06-13 16:16:09 +08:00
i-robot fce24fd8f5
!32515 [feat] [assistant] [I4CRJK] Add new aicpu operator Expand 
Merge pull request !32515 from 路雄博/Expand
 2022-06-13 07:20:05 +00:00
zhangqi bcd7d8b70a fix gamma ops bug 2022-06-13 15:10:06 +08:00
muxiyin 27e96dd46d support spmm 2022-06-13 15:08:09 +08:00
i-robot 010c288667
!35815 takedown test_3d_dense_to_csr to ensure gate stability 
Merge pull request !35815 from LLLRT/master
 2022-06-13 06:47:46 +00:00
i-robot 982df86e42
!35816 Fix bug of SpaseSegmentMean in GPU implementation. 
Merge pull request !35816 from hezhenhao1/add_sparse
 2022-06-13 06:22:35 +00:00
limingqi107 63609bc82d add the test case of multi actor fusion 2022-06-13 14:13:29 +08:00
i-robot 7a4af063b8
!35734 Add testcase. 
Merge pull request !35734 from gaoyong10/dynamic_shape_01
 2022-06-13 04:37:37 +00:00
hezhenhao1 04876fd5be Fix bug of SpaseSegmentMean in GPU implementation. 2022-06-13 11:52:47 +08:00
i-robot 0e11cf9633
!35253 [op]Add CPU op Argmin and support Ascend dynamic shape 
Merge pull request !35253 from chenzhuo/Argmin_cpu
 2022-06-13 03:23:56 +00:00
liuruotao bebe986df3 downgraded testcase test_sparse_dense_to_csr_op.py::test_3d_dense_to_csr 2022-06-13 11:22:36 +08:00
i-robot 71c7e5760c
!35759 Add grad definition for DropoutGrad operation. 
Merge pull request !35759 from huangbingjian/grad_dropoutgrad
 2022-06-13 03:17:55 +00:00
i-robot 247da9fbf3
!32810 [assistant][ops] Add new Baddbmm 
Merge pull request !32810 from wxy220/Baddbmm
 2022-06-13 02:52:27 +00:00
i-robot cbea10add6
!35467 add cpu operation of StandardLaplace and its functional interface 
Merge pull request !35467 from panshaowu/master
 2022-06-13 02:32:36 +00:00
wYann 92a7c6e1bc dynamic data queue 2022-06-13 10:04:52 +08:00
i-robot 0f160775c5
!35618 Update ms_kernel custom op 
Merge pull request !35618 from zichun_ye/custom_op_update
 2022-06-13 02:00:54 +00:00
i-robot ea7c9daac3
!35743 [MS][CPU]resize linear 1d grad cppu kernel 
Merge pull request !35743 from mengyuanli/resize_linear_1d_grad_cpu
 2022-06-13 01:54:57 +00:00
i-robot 70d447d8d7
!35677 [Fallback][Control_flow] Fix the problem that the interpret node is not set interpret flag when it first appears as a phi node. 
Merge pull request !35677 from Margaret_wangrui/numpy_phi
 2022-06-13 01:49:51 +00:00
i-robot 09479b3e96
!35687 Change the logic of adding local param into interpret node and add checking to the input of interpret node 
Merge pull request !35687 from LiangZhibo/ast
 2022-06-13 01:47:32 +00:00
i-robot 38bb98530f
!35580 Add CPU OP ApplyAdaMax 
Merge pull request !35580 from liuyang/cpu_apply_ada_max
 2022-06-12 17:23:36 +00:00
danansheng 7250649f79 [feat][assistant][I4XJFX] add new Baddbmm 2022-06-13 00:26:59 +08:00
huangbingjian beff12d4e2 Add grad definition for DropoutGrad operation. 2022-06-12 23:28:00 +08:00
i-robot aa7e67d1d6
!35633 Error message structure optimization, hierarchical printing 
Merge pull request !35633 from wangjunbao/master
 2022-06-12 07:54:28 +00:00
liyuanshuo123@yeah.net a458c03619 [feat] [assistant][I48O75] add new math operator [IdentityN] 2022-06-12 13:09:05 +08:00
panshaowu fa32247b6f add cpu operation of StandardLaplace and its functional interface 2022-06-11 18:25:58 +08:00
chenzhuo 2529bd3c2c add cpu ops Argmin add support Ascend dynamic ArgminV2 2022-06-11 17:20:47 +08:00
i-robot bf41f2b534
!35758 update InstanceNormGrad GPU kernel 
Merge pull request !35758 from zhujingxuan/InstanceNormGrad
 2022-06-11 08:05:44 +00:00
Shukun Zhang 52024260ad Expand LoadMindIR with Encryption 2022-06-11 15:48:37 +08:00
i-robot d6bbef46ee
!35448 add deformable offsets grad op for Ascend 
Merge pull request !35448 from guoqi/deformable_offsets_grad
 2022-06-11 07:39:42 +00:00
i-robot 2c9fe2bc6b
!34869 support tensor to sparse tensor conversion 
Merge pull request !34869 from 杨林枫/dense_to_csr_gpu
 2022-06-11 07:03:19 +00:00
王超 10e29a904e [feat] [assistant] [I4CRJK] Add new aicpu operator Expand 2022-06-11 12:53:10 +08:00
zhujingxuan d9dc842c4a update InstanceNormGrad GPU kernel 2022-06-11 11:28:48 +08:00
i-robot f50df36ab7
!35738 fix gpu KLDivLoss st 
Merge pull request !35738 from baihuawei/ci
 2022-06-11 02:42:26 +00:00
i-robot 3dbb3708cd
!35515 Memoffload reuse continuous memory 
Merge pull request !35515 from tanghuikang/mem_offload_kernel_runtime_v3
 2022-06-11 02:42:17 +00:00
i-robot 090c400eee
!35730 fix test for funtion api 
Merge pull request !35730 from zhangyinxia/master
 2022-06-11 02:06:44 +00:00
David 54d2858d78 Added docs to ut cpp part 1 2022-06-10 17:13:09 -04:00
i-robot eb932c543c
!35746 add the test case of runtime optimize 
Merge pull request !35746 from limingqi107/new_actor_runtime
 2022-06-10 13:08:50 +00:00
i-robot e7a32b1f53
!35654 Add testcases for ScatterUpdateof and SetItem on dynamic shape tensors 
Merge pull request !35654 from zhengzuohe/shrink_axis_mask
 2022-06-10 11:39:00 +00:00
i-robot b40c8385b9
!35685 update InstanceNorm GPU kernel 
Merge pull request !35685 from zhujingxuan/InstanceNorm
 2022-06-10 10:16:47 +00:00
hu-xinyu-1216 4491e56178 [feat][assisant][I48OET] add aicpu operator addv2 2022-06-10 17:40:26 +08:00
i-robot 0a7e9ac87b
!35395 Add functional and tensor interface for `GatherD` 
Merge pull request !35395 from TronZhang/gatherd_interface
 2022-06-10 09:22:38 +00:00
jiaorui ed237f96c5 fix ci error 2022-06-10 17:22:23 +08:00
liangzhibo 3400487a51 Fallback warning for interpret node 2022-06-10 17:21:42 +08:00
limingqi107 ab5a7e0a99 add the test case of runtime optimize 2022-06-10 17:15:33 +08:00
i-robot 0ea5714762
!34615 fuse csr ops 
Merge pull request !34615 from huangmengxi/fuse_gnn
 2022-06-10 09:09:06 +00:00
mengyuanli cec4234497 add resize_linear_1D_grad_cpu kernel 2022-06-10 16:57:58 +08:00
i-robot c79d9cb6d6
!35210 修复 ST probabilistic failure in daily version 
Merge pull request !35210 from 王程浩/master
 2022-06-10 08:36:31 +00:00
i-robot 58efca88db
!35394 add get_mindir_input api 
Merge pull request !35394 from changzherui/add_get_mindir_input
 2022-06-10 08:28:35 +00:00
i-robot 402431e754
!35667 [kernel]add celu vmap 
Merge pull request !35667 from 张学同/celu
 2022-06-10 08:21:43 +00:00
i-robot 16884a6b9e
!35337 ApplyadagradDAD CPU operator supported 
Merge pull request !35337 from 冯一航/ApplyAdagradDAD_operator_cpu_support
 2022-06-10 08:12:30 +00:00
ZRN 0098788622 add operator UnravelIndex 2022-06-10 16:08:58 +08:00
Zichun Ye 8de24b4d2f update ms_kernel related files 
fix import problem

update code check

update test case

update test case

rename file
 2022-06-10 15:41:38 +08:00
i-robot 2aa818f6b1
!34264 [feat] [assistant] [I4XJI1] add math operator Gcd 
Merge pull request !34264 from Seeker98/op_gcd
 2022-06-10 07:19:11 +00:00
guoqi b68e7d5045 add deformable offset grad operator for Ascend 2022-06-10 15:14:17 +08:00
baihuawei 7cdbd3999e fix gpu KLDivLoss st 2022-06-10 15:10:21 +08:00
i-robot 7659a6ff14
!35303 modify generate strategy for matmul parallel operators 
Merge pull request !35303 from yangzhenzhang/modify-gen-strategy-for-matmul-op
 2022-06-10 07:07:12 +00:00
gaoyong10 bb0bcd3bb2 Add testcase. 2022-06-10 14:59:14 +08:00
i-robot 5b57829f11
!35595 per_batch_map input column optimization 
Merge pull request !35595 from 刘勇琪/master-decrypt-column
 2022-06-10 06:57:41 +00:00
zhujingxuan 2bf0a95a25 update InstanceNorm GPU kernel 2022-06-10 14:45:10 +08:00
i-robot 187b902cf3
!35737 takedown scatter_nd_update and sparse_segment_mean testcases 
Merge pull request !35737 from yanghaoran/takedown_testcases
 2022-06-10 06:44:02 +00:00
yanghaoran 42fee70ce0 takedown scatter_nd_update and sparse_segment_mean testcases 2022-06-10 14:32:26 +08:00
i-robot 90b2a6884f
!35707 fix bug when reduce axis have duplicate elements 
Merge pull request !35707 from zhangbuxue/fix_bug_when_reduce_axis_have_duplicate_elements
 2022-06-10 06:18:54 +00:00
yanglf1121 dd7f6f91c0 support tensor to sparse tensor 2022-06-10 12:41:12 +08:00
liuyang_655 22a261e4b2 add cpu op ApplyAdaMax 2022-06-10 12:10:48 +08:00
i-robot 29a3c7f3ed
!34888 add Col2Im GPU impl 
Merge pull request !34888 from baihuawei/col2im
 2022-06-10 03:50:40 +00:00
andy_wangrui e54b2be09a update tests/st/networks/models/resnet50/test_resnet50_imagenet_and_thor.py. 
restore test_resnet50_imagenet_and_thor.py:test_resnet_imagenet_and_thor_4p as thor_cost < 30
 2022-06-10 11:39:20 +08:00
i-robot 93eaf5512e
!35676 fix testcase failer 
Merge pull request !35676 from zhujingxuan/master
 2022-06-10 03:35:35 +00:00
wangjunbao d8e7f7aad1 Error message structure optimization, hierarchical printing 2022-06-10 11:20:37 +08:00
fengyihang 458495035f ApplyAdagradDAD_operator_cpu_support 2022-06-10 11:12:10 +08:00
zhengzuohe 5b62f41523 add nested vmap testcases for ScatterUpdate 
add testcases of SetItem for dynamic shape tensors
 2022-06-10 11:07:54 +08:00
Seeker 4f711cfb70 Add math op Gcd 2022-06-10 10:14:20 +08:00
i-robot 81ba610b7f
!33341 [assistant][ops][I40FK0] Add Cholesky 
Merge pull request !33341 from 李定维/Cholesky
 2022-06-10 01:59:35 +00:00
i-robot 55cb76fe98
!35644 修复Bessel i0/k0/k0e精度问题，修复Bessel算子st 
Merge pull request !35644 from xutianyu/bessel
 2022-06-10 01:51:31 +00:00
Margaret_wangrui 2040c60ca6 [Fallback][Control_flow] Fix the problem that the interpret node is not set interpret flag when it first appears as a phi node. 2022-06-10 09:49:57 +08:00
i-robot 260f2bda0f
!35490 add functional, tensor interface and vmap for ops.Pad 
Merge pull request !35490 from looop5/op_pad_commit
 2022-06-10 01:29:10 +00:00
i-robot d124bc732e
!35518 Fix print all eval by fallback 
Merge pull request !35518 from huanghui/fallback-st
 2022-06-10 01:21:57 +00:00
臧庆香 35c521d607 fox new run package not exist aicpu file 2022-06-10 09:18:25 +08:00
zhangxuetong 86dc05b979 support functional tensor vmap for celu 2022-06-10 09:12:39 +08:00
tanghuikang 7522bb2c9b Memoffload reuse continuous memory 2022-06-10 09:01:54 +08:00
i-robot 764656a010
!35363 Add testcase for eliminate nopnode. 
Merge pull request !35363 from gaoyong10/dynamic_shape_01
 2022-06-09 22:09:10 +00:00
i-robot 01642da438
!35426 Refactor Python Multiprocessing code of Map 
Merge pull request !35426 from h.farahat/new_work
 2022-06-09 19:27:27 +00:00
王程浩 1561337f1e 修复 ST probabilistic failure in daily version 2022-06-09 23:25:08 +08:00
changzherui 9649556315 add get_mindir_input api 2022-06-09 22:18:16 +08:00
buxue 45c5b4801f fix bug when reduce axis have duplicate elements 2022-06-09 21:15:59 +08:00
huangmengxi 0be019329f fuse csr ops && add csr atomic clean 2022-06-09 20:28:50 +08:00
baihuawei 404816a5f4 add gpu Col2Im impl and tensor & function op 2022-06-09 20:10:00 +08:00
yangzhenzhang e5b62b2714 modify gen strategy for matmul op 2022-06-09 19:50:31 +08:00
gaoyong10 8299f3ca05 Add testcase for eliminate nopnode. 2022-06-09 19:12:06 +08:00
tronzhang 9a2fc5785d add functional and tensor interface for gatherd 2022-06-09 18:00:08 +08:00
hezhenhao1 17653575c5 Add random seed for SparseSegmentMean test case. 2022-06-09 17:43:37 +08:00
i-robot 2d43f55bd6
!35181 [feat] [assistant] [I4XJI2] add math operator Lcm 
Merge pull request !35181 from Seeker98/op_lcm
 2022-06-09 09:13:58 +00:00
i-robot 94a1973ec6
!35625 add ut test case for parallel if 
Merge pull request !35625 from xychow/add-ut-test-case-for-parallel-if
 2022-06-09 08:58:21 +00:00
Xiaoda Zhang 4f791ab931 adjust for scalar input; add API annotations 2022-06-09 16:54:23 +08:00
zhujingxuan e9c267d268 reduce testcase size 2022-06-09 15:53:52 +08:00
zhousiyi 6afda60609 add ut test cases for parallel-if by check isomorphic funcgraphs 2022-06-09 07:45:42 +00:00
gyuer b606723dcf [feat][assistant][I4ZZSG] add new gpu operator Sinh 2022-06-09 15:38:09 +08:00
i-robot 8a90d74860
!35639 modify ckpt file chmod 
Merge pull request !35639 from changzherui/mod_chmod_file
 2022-06-09 07:37:52 +00:00
i-robot a6275d3726
!35032 ascend support AllToAll kernel by kernel 
Merge pull request !35032 from baihuawei/alltoall
 2022-06-09 06:43:50 +00:00
i-robot d87f0bea2d
!35623 Import the error for syntax "for x in xs" 
Merge pull request !35623 from LiangZhibo/syntax
 2022-06-09 06:30:17 +00:00
looop5 4c5de144ce add functional, tensor interface and vmap for ops.Pad 2022-06-09 14:26:36 +08:00
i-robot eafd35217a
!33569 add hswish operator 
Merge pull request !33569 from jjfeing/add_hswish_operator
 2022-06-09 06:19:38 +00:00
i-robot 598caa37ca
!35568 Extend the MatrixBandPart kernel to support batch. 
Merge pull request !35568 from liqiliang/vmap_and_dynamic_and_tests
 2022-06-09 06:14:48 +00:00
liu-yongqi-63 0dfd42153f per_batch_map input column optimization 2022-06-09 13:17:02 +08:00
liruoxuan 830cca9c53 [assistant][ops][I40FK0] add Cholesky operator 2022-06-09 12:39:36 +08:00
i-robot fd50ac5dbf
!35380 add EarlyStopping and ReduceLROnPleatu callbacks 
Merge pull request !35380 from liutongtong9/add_cbs
 2022-06-09 03:42:37 +00:00
i-robot 490e502d01
!35557 add mish lrn lrn_grad vmap_rule and some test case 
Merge pull request !35557 from zhuzhongrui/pub_master2
 2022-06-09 03:29:02 +00:00
i-robot 4f07986eae
!35440 Add testcases for ScatterUpdate and unify the testing codes of ScatterMin/Max/Update 
Merge pull request !35440 from zhengzuohe/test_scatterupdate
 2022-06-09 03:20:59 +00:00
i-robot 5b6806ae36
!35641 Bugfix for gathering hostname under muti-node setting 
Merge pull request !35641 from chengang/fix_gather_hostname_order
 2022-06-09 03:06:44 +00:00
jjfeing 5f8af95bb6 add hardswish & hardswishgrad 2022-06-09 10:51:38 +08:00
Seeker c908ac8cc3 Add aicpu op Lcm 2022-06-09 10:43:08 +08:00
i-robot 3e11eded32
!33594 [assistant][Resample] 
Merge pull request !33594 from chenchen/Resample
 2022-06-09 02:08:54 +00:00
i-robot 508f3d7b5f
!35647 takedown yolov3_darknet53 due to constant failures 
Merge pull request !35647 from yanghaoran/takedown_testcases
 2022-06-09 02:02:40 +00:00
i-robot 1e6af66b5a
!35354 soft shrink 
Merge pull request !35354 from ling/sr
 2022-06-09 02:02:16 +00:00
huanghui f9c502d4ca fix print all to fallback 2022-06-09 09:54:56 +08:00
i-robot 008953c4c0
!35466 tan support complex 
Merge pull request !35466 from ling/bug
 2022-06-09 01:39:27 +00:00
yanghaoran ff7c7c9b02 takedown yolov3_darknet53 due to constant failures 2022-06-09 09:39:17 +08:00
i-robot ef555956f2
!35454 Change the logic of inherit local python parameter between block. 
Merge pull request !35454 from LiangZhibo/master
 2022-06-09 01:34:52 +00:00
baihuawei 8b80248a50 alltoall for kernel by kernel 2022-06-09 09:30:33 +08:00
i-robot 2a0bcb581e
!35599 Fix several bugs of Pad 
Merge pull request !35599 from xiaotianci/fix_pad
 2022-06-09 01:26:03 +00:00
i-robot 06cfba0683
!35615 Add ut for side effect order enforce 
Merge pull request !35615 from chenfei_mindspore/add-ut-for-abstract-ref
 2022-06-09 01:22:32 +00:00
liangzhibo 59df5656b3 Improve the error for fallback control flow 2022-06-09 09:08:52 +08:00
Parallels af2cab6fa5 bugfix for order of gather hostnames 2022-06-08 23:56:23 +08:00
Tianyu Xu e5ecd64a76 修复Bessel i0/k0/k0e精度问题，修复Bessel算子st 2022-06-08 23:36:38 +08:00
changzherui 9de853b393 modify file chmod 2022-06-08 23:26:15 +08:00
hesham 13ce3b6fd4 python MP new 2022-06-08 10:52:44 -04:00
liutongtong 7605d6470d add earlystop and reducelrpleatu 2022-06-08 22:10:43 +08:00
i-robot 7fa2215252
!31463 Add ArgMax(Min)WithValue to Expander 
Merge pull request !31463 from jiaoy1224/argmaxwithvalue
 2022-06-08 13:02:12 +00:00
liqiliang e0369d0d54 Extend the MatrixBandPart kernel to support batch. 2022-06-08 20:45:19 +08:00
i-robot 8c823836a6
!35383 Add cpu kernel for deformable_offsets 
Merge pull request !35383 from YuJianfeng/deformable_conv
 2022-06-08 11:13:30 +00:00
i-robot aacf006016
!34766 add gpu deformable offset grad 
Merge pull request !34766 from kisnwang/add-gpu-deformable-offset-grad
 2022-06-08 09:35:03 +00:00
i-robot 0f27520ddb
!35560 Move ClipByNorm to inner interface 
Merge pull request !35560 from JoyLvliang/move_clipbynorm_to_inner_interface
 2022-06-08 09:27:05 +00:00
i-robot 37561dc40d
!35326 Extend export/load with customized encryption functions 
Merge pull request !35326 from 张澍坤/master
 2022-06-08 09:04:59 +00:00
z00512249 c85cb977db add mish lrn lrn_grad vmap_rule and some test case 2022-06-08 16:43:02 +08:00
i-robot 33e737e07f
!35511 Change spelling to American English 
Merge pull request !35511 from xiaotianci/fix_spelling
 2022-06-08 08:41:06 +00:00
i-robot ddeaad24fd
!35386 add gpu dataformatdimmap 
Merge pull request !35386 from KXiong/branch_gpu_dataformatdimmap
 2022-06-08 08:35:11 +00:00
Xiao Tianci 2df7c5a193 fix bugs of Pad 2022-06-08 15:57:28 +08:00
chenfei bcd6ad95a3 add test ut 2022-06-08 15:56:40 +08:00
i-robot 1ae90cbaea
!35439 AdamApplyOneWithDecay support dynamic shape 
Merge pull request !35439 from Yanzhi_YI/adam_with_decay
 2022-06-08 07:54:15 +00:00
i-robot dc6bee390e
!33385 UpsampleNearest3D GPU operator 
Merge pull request !33385 from tom_chen/upsample
 2022-06-08 07:52:04 +00:00
i-robot ff6a2a1c8d
!35477 add flatten weight adam weight decay st 
Merge pull request !35477 from kisnwang/add-adam-weight-decay-flatten-weight-st
 2022-06-08 07:17:41 +00:00
i-robot 4ae05706e5
!35381 Add MatrixSolve Op CPU Kernel 
Merge pull request !35381 from zhujingxuan/MatrixSolve
 2022-06-08 06:24:06 +00:00
ling 60e7d1f947 tan support complex 2022-06-08 14:14:01 +08:00
i-robot e5d57a316e
!35534 fixed bug in st cases of reflectionpad 
Merge pull request !35534 from shaojunsong/fix/st_reflectionpad
 2022-06-08 06:12:07 +00:00
i-robot 539be854ba
!35371 fix rewrite bug 
Merge pull request !35371 from 于振华/rewrite_r1.8_fix
 2022-06-08 04:54:59 +00:00
liangzhibo 458a3d65a3 Change fallback control flow local param logic 2022-06-08 11:55:19 +08:00
yujianfeng 2d283c96df Add the implement of cpu kernel for deformable_offsets 2022-06-08 11:53:52 +08:00
zhengzuohe 9cda5eac64 add testcases for ScatterUpdate and unify the testing codes of ScatterMin/Max/Update 2022-06-08 11:50:30 +08:00
i-robot 624565f6fb
!35531 difference branches the same type 
Merge pull request !35531 from lanzhineng/issue
 2022-06-08 03:48:46 +00:00
chenx2ovo 6e62ed181e [feat][assistant[I3CEG6] add op resample 2022-06-08 11:46:12 +08:00
i-robot 59b9adefa2
!35499 Reduce the execution time of distributed ut cases 
Merge pull request !35499 from chengang/reduce_ut_time
 2022-06-08 03:38:21 +00:00
i-robot 53397921b3
!35507 [MS][LITE]add resize linear cpu kernel 
Merge pull request !35507 from mengyuanli/resize_linear_1d_cpu
 2022-06-08 03:31:12 +00:00
ling 313274ae66 soft shrink 
unsorted segment prod num_segments type check
 2022-06-08 11:22:34 +08:00
Shukun Zhang 8d92f989ab Add Customized Export With Encryption 2022-06-08 10:50:42 +08:00
i-robot 77489c3d3e
!34387 [assistant][ListDiff] add new operator ListDiff 
Merge pull request !34387 from 李文轼/ListDiff
 2022-06-08 02:43:58 +00:00
yiyanzhi_akane 1e18fe3574 AdamApplyOneWithDecay support dynamic shape 2022-06-08 09:53:01 +08:00
i-robot 275ee3c637
!35459 Fix GradOperation descripition and support tuple/list for 'get_by_list'. 
Merge pull request !35459 from 张清华/opt
 2022-06-08 01:46:39 +00:00
xiongkun 7249a25ad7 add gpu dataformatdimmap 
tick

add dataformatdimmap

add dataformatdimmap

add dataformatdimmap

add dataformatdimmap

add dataformatdimmap
 2022-06-08 09:43:07 +08:00
i-robot 37422cd424
!35567 add deformable offsets test 
Merge pull request !35567 from zhangyinxia/master
 2022-06-08 01:20:17 +00:00
kswang 410402ba6b add gpu deformable offset grad 2022-06-08 09:09:05 +08:00
i-robot 4f97ed5fb0
!35550 Fix the mish_grad test case. 
Merge pull request !35550 from liqiliang/mishgrad-cpu
 2022-06-08 00:00:48 +00:00
i-robot 802cfc8950
!34611 Trunc Operator for CPU 
Merge pull request !34611 from Mina/master
 2022-06-07 23:01:00 +00:00
tom__chen b4c0635d53 upsample_nearest_3d GPU operator 2022-06-07 10:43:53 -04:00
i-robot e84b1b3197
!35351 add determinant data_type && add vmap rule 
Merge pull request !35351 from zhuzhongrui/pub_master
 2022-06-07 13:17:24 +00:00
7347157+joylvliang@user.noreply.gitee.com e8bc5e59e7 move_clipbynorm_to_inner_interface 2022-06-07 21:01:04 +08:00
i-robot 63fbca95a4
!35172 support S string input in GE mode/ocr ops/scope fusion attr 
Merge pull request !35172 from chenmai1102/cm_master
 2022-06-07 12:55:08 +00:00
zhangyinxia 28193d3c97 add test for deformable_conv 2022-06-07 20:49:48 +08:00
Yang Jiao ecf69c41af expand argmaxminwithvalue 2022-06-07 20:41:19 +08:00
i-robot c8d964aff6
!34619 AdaptiveMaxPool2D support ascend platform. 
Merge pull request !34619 from linqingke/adative_maxpool_2d_support_ascend
 2022-06-07 12:31:34 +00:00
i-robot ea4c18db2b
!35199 modify ssd_mobilenet_fpn testcase 
Merge pull request !35199 from anzhengqi/modify-modelzoo-testcase
 2022-06-07 12:26:09 +00:00
i-robot 6fe64a18c9
!34770 Add gpu DeformableOffsets 
Merge pull request !34770 from tanghuikang/gpu_deformable_offset
 2022-06-07 10:55:50 +00:00
i-robot 1617f280d3
!33752 Add the GPU version of GridSampler2D/GridSampler2DGrad and GridSampler3D/GridSampler3DGad operators 
Merge pull request !33752 from dessyang/grid_sampler_gpu_ops_dev
 2022-06-07 10:54:50 +00:00
i-robot 911b7b9950
!33331 gpu priority replay buffer implement 
Merge pull request !33331 from chenweifeng/priority-replay-buffer-gpu-kernel
 2022-06-07 10:39:57 +00:00
i-robot 8f51b50547
!35393 Add tensor and functional interface for ScatterNdMul and ScatterNdMax operator. 
Merge pull request !35393 from hezhenhao1/add_scatter_max
 2022-06-07 09:49:34 +00:00
i-robot b8a0522b56
!35297 [kernel]add the vmap of apply proximal adagrad 
Merge pull request !35297 from 张学同/applyproximaladagrad_gpu
 2022-06-07 09:40:56 +00:00
liqiliang 6409772e72 Fix the mish_grad test case. 2022-06-07 17:18:17 +08:00
zhou-yunfeier 516f8ffe27 [feat] [assistant] [ops] [I4ZZTT] New GPU operator Ger 2022-06-07 16:53:17 +08:00
wilfChen bea37279ff gpu priority replay buffer 2022-06-07 16:08:08 +08:00
yuzhenhua fa60ab7c84 fix rewrite bug 2022-06-07 15:45:16 +08:00
i-robot e5d53e4c02
!34942 [bug] fix jet and grad input check error in graph mode 
Merge pull request !34942 from chenzhuo/master
 2022-06-07 07:35:04 +00:00
shaojunsong 6f9e4ccedc fixed reflectionpad bug in st cases of acend and cpu 2022-06-07 15:34:33 +08:00
lanzhineng c864d6a55c difference branches the same type 2022-06-07 15:07:14 +08:00
i-robot d9ff3dd395
!35375 fix handle builtin func in loop body 
Merge pull request !35375 from huanghui/fix-fallback
 2022-06-07 07:06:27 +00:00
mengyuanli 4444ecc668 add resize linear 1d cpu 2022-06-07 15:00:29 +08:00
Zhang Qinghua ce39353421 Fix GradOperation descripition and support tuple/list for 'get_by_list'. 2022-06-07 14:21:58 +08:00
z00512249 cb1f8886e0 add determinant data_type && add vmap rule 2022-06-07 14:21:45 +08:00
i-robot 568278684d
!34540 UpsampleTrilinear3D GPU Kernel 
Merge pull request !34540 from danishfarid/UpsampleTrilinear3D
 2022-06-07 06:07:34 +00:00
i-robot ec65b96074
!34252 [CPU operator] Add ReNorm CPU operator 
Merge pull request !34252 from Xiaoda/127-add-renorm-op
 2022-06-07 05:47:46 +00:00
i-robot 87c21bdc5c
!35335 Add pass to convert unused tuple output parameter to make_tuple 
Merge pull request !35335 from YuJianfeng/mutable
 2022-06-07 04:18:42 +00:00
linqingke 632eb99304 AdativeMaxpool2D support ascend platform. 2022-06-07 12:13:08 +08:00
i-robot ae2c2c34f3
!35288 batchtospacend support tensor/func/vmap 
Merge pull request !35288 from r1chardf1d0/bts
 2022-06-07 03:59:47 +00:00
i-robot e6686ba1c9
!35194 Add dynamic and vmap support for NLLLossGrad in Ascend. 
Merge pull request !35194 from TronZhang/nlllossgrad
 2022-06-07 03:04:12 +00:00
i-robot d740fe74c2
!35231 Tensor getitem & setitem support dynamic shape on ascend platform 
Merge pull request !35231 from huoxinyou/0526tensorslice
 2022-06-07 02:58:15 +00:00
zhangxuetong 355edf2e55 support apply_proximal_adagrad vmap 2022-06-07 10:56:56 +08:00
i-robot 526b1ebedc
!35273 Op ScatterNd, rewrite infer function with c++, supports vmap, supports dynamic shape on Gpu and Ascend. 
Merge pull request !35273 from DeshiChen/0527_scatternd_dynshape
 2022-06-07 02:54:09 +00:00
zhujingxuan 513f28fadb Add MatrixSolve Op 2022-06-07 10:44:39 +08:00
Xiao Tianci fd9598dabc change spelling of some words 2022-06-07 10:30:59 +08:00
i-robot 8d84471f89
!35413 [MD] Transforms Unification - Phase 4: Add deprecation warning for c_transforms and py_transforms.py 
Merge pull request !35413 from cathwong/ckw_xtranuni_code5_depr_warn
 2022-06-07 02:17:09 +00:00
i-robot 7cb5f8a103
!35239 op tiling for KLDivLoss and adapt vmap st 
Merge pull request !35239 from xulei/kldiv
 2022-06-07 02:17:06 +00:00
i-robot 06824b4a2e
!35316 gpu_testcase_level_adjust 
Merge pull request !35316 from LLLRT/master
 2022-06-07 02:09:14 +00:00
chenzhuo 4f7c9ffc80 fix jet input check error in graph mode 2022-06-07 10:08:16 +08:00
kswang 5450fa2551 add flatten weight adam weight decay st 2022-06-07 10:03:25 +08:00
i-robot 7b5287ffc7
!35475 fix scatter max gpu kernel and code check 
Merge pull request !35475 from polyhedral/max
 2022-06-07 02:00:23 +00:00
i-robot c3bfbf2c3c
!35479 fix axis check range 
Merge pull request !35479 from looop5/vmap_axis
 2022-06-07 01:57:38 +00:00
i-robot 74b9ef095e
!35322 Adapt MatrixDiagPartV3 GPU to new API 
Merge pull request !35322 from zhujingxuan/MatrixDiagPart
 2022-06-07 01:49:49 +00:00
huanghui b0daae6137 fix handle builtin func in while body 2022-06-07 09:14:15 +08:00
Cathy Wong 780da6e141 [MD] Transform Unification - Phase 4: Add deprecation warning for 
c_transforms.py and py_transforms.py
 2022-06-06 13:54:13 -04:00
Parallels e93769eb62 reduce the execution time of distributed ut 2022-06-06 23:24:44 +08:00
dessyang 801763172a Add GPU version of GridSampler2D/GridSampler3D and GridSampler2DGrad/GridSampler3DGrad operators 
adapt to new NativeGpuKernelMod interface
 2022-06-06 09:54:16 -04:00
i-robot 17d2e1e1dd
!32411 [assistant][ops] Add BlackmanWindow 
Merge pull request !32411 from 张渝/blankman_window
 2022-06-06 13:33:06 +00:00
hezhenhao1 bf6340504d Add functional doc and interface for ScatterNdMul and ScatterNdMax operator. 2022-06-06 20:39:02 +08:00
looop5 6c24a18dff fix axis check range 2022-06-06 19:38:46 +08:00
tanghuikang 3e0b3a2ce0 Add gpu DeformableOffsets 2022-06-06 19:17:04 +08:00
polyhedral bd7278de51 fix scatter max gpu kernel and code check 2022-06-06 18:58:38 +08:00
i-robot 621b48760b
!35347 flatten support functional and tensor interface, dynamic shape and vmap 
Merge pull request !35347 from polyhedral/flatten
 2022-06-06 09:50:51 +00:00
zhujingxuan 40899613ca adapt MatrixDiagPartV3 GPU to new API 2022-06-06 17:33:18 +08:00
i-robot dfd7daabd4
!31638 [assistant][ops] Add new Ldexp 
Merge pull request !31638 from wxy220/Ldexp
 2022-06-06 08:39:22 +00:00
tronzhang dadcbe124f add dynamic and vmap support for nlllossgrad 2022-06-06 15:49:46 +08:00
i-robot 8026412d84
!35305 Fix some remaining problems of Pad 
Merge pull request !35305 from xiaotianci/fix_pad
 2022-06-06 07:28:21 +00:00