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

930 Commits

Author SHA1 Message Date
buxue 82f59644cf develop hswish and hswish grad gpu operators 2021-05-17 09:26:10 +08:00
zuochuanyong de63ee4690 add some gpu ops after removing akg 2021-05-15 14:30:10 +08:00
zuochuanyong 7864914515 support MaxPool3D(CPU/GPU), AvgPool3D(CPU/GPU) and Conv3D(CPU) 2021-05-14 19:30:58 +08:00
TFBunny 593c68e110 add gpu ApplyGradientDescent 2021-05-13 13:48:12 -04:00
mindspore-ci-bot b596894d07 !16199 Support multiple types in GPU Print 
From: @TFbunny
Reviewed-by: @liangchenghui,@tom__chen
Signed-off-by: @tom__chen
 2021-05-11 20:53:57 +08:00
mindspore-ci-bot d567ea5fb2 !16030 Add atan2 op for gpu 
From: @xcnick
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-05-11 10:38:04 +08:00
TFBunny 33255dbf60 support multiple types in print 2021-05-10 11:41:10 -04:00
mindspore-ci-bot 88e1bf54b1 !16031 fix round op typos 
From: @xcnick
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-05-10 14:02:16 +08:00
mindspore-ci-bot 68c99f3ff7 !15591 Add sign op for gpu 
From: @xcnick
Reviewed-by: 
Signed-off-by:
 2021-05-10 11:02:43 +08:00
mindspore-ci-bot 1dc0efbab5 !16022 GPU Conv3d grad op support 
From: @tom__chen
Reviewed-by: @robingrosman,@mikef
Signed-off-by:
 2021-05-08 07:02:03 +08:00
tom__chen 94ff2fd30f conv3d grad gpu op 2021-05-07 15:05:00 -04:00
xcnick 112f4422cb Add sign op kernel for gpu 2021-05-07 09:25:34 +08:00
mindspore-ci-bot c3897f867d !15788 20210427 Add AdaptiveAvgPool2D ops 
From: @ZhengQihao3f3f3f
Reviewed-by: 
Signed-off-by:
 2021-05-07 09:23:13 +08:00
mindspore-ci-bot 3426f91cf0 !16006 SortOp gpu kernel 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-05-07 02:51:41 +08:00
xcnick 0e61cabb68 fix round op typos 2021-05-06 22:44:21 +08:00
xcnick 3f6c54a557 Add atan2 op for gpu 2021-05-06 22:38:06 +08:00
mindspore-ci-bot c92d4f36aa !15662 Add round op for cpu and gpu 
From: @xcnick
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-05-06 15:40:25 +08:00
Peilin Wang 91242dcf53 gpu sort op initial commit 
fix ci

fix ci

fix ci

fix ci

fix ci
 2021-05-06 01:23:51 -04:00
ZhengQihao3f3f3f e6a41b1938 Add ops test PR 1 2021-05-06 09:23:18 +08:00
mindspore-ci-bot 19158780b5 !15978 Add GPU BCEWithLogitsLoss 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-05-06 03:20:56 +08:00
tom__chen 2c98b7ea92 conv3d gpu op 2021-05-04 15:10:16 -04:00
TFBunny 9eae68efaa add gpu BCEWithLogitsLoss kernel 2021-04-30 16:46:08 -04:00
xcnick 9f62227f99 Add round op for cpu and gpu 2021-04-30 23:17:15 +08:00
mindspore-ci-bot a835d265ca !15858 Fix HSigmoidGrad bug in GPU 
From: @TFbunny
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui,@wuxuejian
 2021-04-30 11:35:58 +08:00
TFBunny 309fb476bf add fix to hsigmoid grad 2021-04-28 22:16:50 -04:00
TFBunny bc5434090c addn int64 support 2021-04-27 16:55:14 -04:00
mindspore-ci-bot 94ed3b89a3 !15647 Add rint op for cpu and gpu 
From: @xcnick
Reviewed-by: @liangchenghui,@tom__chen
Signed-off-by: @liangchenghui
 2021-04-26 23:22:24 +08:00
mindspore-ci-bot ef535c360a !15607 bugfix-issue:DepthToSpace SyncHostToDevice failed and the result is incorrect. 
From: @kanghui0204
Reviewed-by: @liangchenghui,@tom__chen
Signed-off-by: @liangchenghui
 2021-04-26 23:20:33 +08:00
xcnick a90713b194 Add rint op kernel for cpu and gpu 2021-04-25 17:28:25 +08:00
mindspore-ci-bot a0ab73cc8e !15554 Add floormod op for cpu and gpu 
From: @xcnick
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-04-25 14:09:29 +08:00
kanghui d9a1ee3429 fix depthtospace and spacetodepth ops bugs 
Signed-off-by: kanghui <405194527@qq.com>
 2021-04-25 05:59:18 +00:00
xcnick 181844a3d9 Add floormod op for cpu and gpu 2021-04-23 13:50:16 +08:00
TFBunny e8794ce0d7 add gpu kernel HSigmoid and HSigmoidGrad 2021-04-22 16:59:23 -04:00
mindspore-ci-bot 6611d79366 !14669 Add mod kernel implementation for gpu 
From: @xcnick
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-04-22 14:56:23 +08:00
mindspore-ci-bot 5fe72ea838 !15464 fix bugs in np.convolve and np.diff 
From: @yanglf1121
Reviewed-by: @liangchenghui,@kingxian
Signed-off-by: @liangchenghui,@kingxian
 2021-04-22 09:45:51 +08:00
tom__chen 7ea4bd0593 batchnorm1d gpu op 2021-04-21 11:48:46 -04:00
yanglf1121 43ebd837b9 fix diff, convolve 2021-04-21 15:19:58 +08:00
tom__chen 7e086b26a1 resize_bilinear gpu op 2021-04-20 17:22:27 -04:00
xcnick 6279ff4bbb add mod op kernel for gpu 2021-04-20 11:47:58 +08:00
mindspore-ci-bot 4631facee9 !15140 Add GPU ops：depthtospace and spacetodepth 
From: @kanghui0204
Reviewed-by: 
Signed-off-by:
 2021-04-19 15:20:45 +08:00
kanghui 91cd3490e8 Add GPU ops:depthtospace and spacetodepth 
Signed-off-by: kanghui <405194527@qq.com>
 2021-04-19 01:56:44 +00:00
mindspore-ci-bot 4cc75df1ac !15221 Support PReLU for GPU platform 
From: @xuguoyang5566
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-04-16 11:45:35 +08:00
xuguoyang 7d1a35bedb support PReLU for GPU platform 2021-04-15 16:29:38 +08:00
TFBunny b61e963b9f add bool support to gpu select 2021-04-14 11:49:01 -04:00
mindspore-ci-bot d09844a601 !15127 Add type support for GPU TensorScatterUpdate 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-04-14 05:37:22 +08:00
TFBunny f6c9e90ad0 add bool support to gpu gather 2021-04-13 15:12:07 -04:00
TFBunny e3820ad2cb add tensor scatter update support different type inputs 2021-04-13 14:35:47 -04:00
TFBunny 4de6b25d23 add float64 support to SigmoidCrossEntropyWithLogits and Grad 2021-03-31 11:42:25 -04:00
zhuyuxiao a11287c332 adagrad: support ouput on gpu 2021-03-23 18:11:43 +08:00
mindspore-ci-bot 5504116718 !13647 BroadcastTo add general -1 dim behavior 
From: @peilin-wang
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-03-20 15:05:22 +08:00
Peilin Wang 6cead43bdf add general -1 dim behavior for BroadcastTo op 2021-03-20 01:42:40 -04:00
TFBunny b780e5737c add float64 to Addn gpu 2021-03-19 15:46:27 -04:00
dingpeifei 87e41aaeee IR operators of GPU and CPU are unified as batchnorm 2021-03-18 19:02:28 +08:00
mindspore-ci-bot b61aa9b4cf !13342 Throw exception when tensor with 0 shape is constructed 
From: @liangzhibo
Reviewed-by: 
Signed-off-by:
 2021-03-17 09:18:27 +08:00
mindspore-ci-bot 0fdf5c54e3 !13069 Add dynamic shape testcases for Sub 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-03-16 21:21:33 +08:00
l00591931 bd777e0710 throw exception when tensor has zero in shape 2021-03-16 10:39:48 +08:00
TFBunny 4d35303265 support string in GPU print 2021-03-12 14:12:19 -05:00
TFBunny 3f397503c0 add dynamic shape testcases for Sub 2021-03-09 13:47:51 -05:00
mindspore-ci-bot 802e756c9b !12897 Add float64 support to reducemax grad gpu op 
From: @peilin-wang
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2021-03-08 19:41:35 +08:00
Peilin Wang dd72f44b27 tensor_scatter_update new op quick initial commit 
fix ci

fix ci

fix ci

fix ci
 2021-03-08 00:39:44 -05:00
mindspore-ci-bot 9ed9d950e2 !11446 fix argmax op for cpu and gpu 
From: @xcnick
Reviewed-by: 
Signed-off-by:
 2021-03-08 10:24:19 +08:00
mindspore-ci-bot df98fa0233 !12842 Add grad op for gpu dynamic shape testing op 
From: @peilin-wang
Reviewed-by: 
Signed-off-by:
 2021-03-05 23:15:07 +08:00
Peilin Wang 783c57c209 add float64 support to reducemax grad 
fix ci
 2021-03-04 17:58:36 -05:00
tom__chen 56e8aa9f7e change index_add op input_x to type Parameter 2021-03-04 07:30:59 -05:00
xcnick d65a5affba fix cpu/gpu argmax op 2021-03-04 16:42:41 +08:00
Peilin Wang 347575a38f add grad for GpuDynamicShape testing op 
add tests

removed some unused imports

fix ci
 2021-03-03 16:01:55 -05:00
huangmengxi 3a319a97e9 move matmul from numpy to ops 2021-03-01 17:21:05 +08:00
mindspore-ci-bot d8433e9f5c !12605 Fix GPU ReduceMax/Sum float64 type failure 
From: @TFbunny
Reviewed-by: @tom__chen
Signed-off-by:
 2021-02-27 04:48:28 +08:00
mindspore-ci-bot f269f3fc8d !12231 Support ad for scalar inputs 
From: @ginfung
Reviewed-by: 
Signed-off-by:
 2021-02-26 15:50:32 +08:00
TFBunny ec644a5291 add fix to float64 support in reduce ops 2021-02-25 15:30:58 -05:00
tom__chen 03b1aeecdb FusedBatchNormEx dynamic shape support 2021-02-25 09:03:40 -05:00
yujianfeng 41189781f3 support scalar input for cell 2021-02-25 09:56:15 +08:00
mindspore-ci-bot 50bf5033f2 !12400 Add float64 support to ZerosLike, remove duplicate ZerosLike gpu kernel 
From: @peilin-wang
Reviewed-by: 
Signed-off-by:
 2021-02-24 06:12:49 +08:00
mindspore-ci-bot 9f48ab87c0 !12524 Add DType dynamic shape testcases for GPU 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-02-24 06:11:59 +08:00
mindspore-ci-bot 57f6c17933 !12438 Add backward op for IndexAdd GPU 
From: @TFbunny
Reviewed-by: @robingrosman
Signed-off-by: @robingrosman
 2021-02-23 09:05:36 +08:00
TFBunny cbc75810a9 add testcases to DType dynamic shape 2021-02-22 17:19:11 -05:00
Peilin Wang ba9ae8097f removed zeroslike from math/unary_op_gpu_kernel and added float64 support 
fix ci

fix ci
 2021-02-22 16:15:23 -05:00
TFBunny e1462c8684 add indexaddgrad ops support and testcases 2021-02-22 12:03:12 -05:00
mindspore-ci-bot cada22e7bf !12354 Add float64 support to ReduceMax and ReduceSum GPU 
From: @TFbunny
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-02-23 00:17:03 +08:00
mindspore-ci-bot 52eae8d4ad !12329 GPU index_add forward op 
From: @tom__chen
Reviewed-by: @liangchenghui,@robingrosman
Signed-off-by: @liangchenghui
 2021-02-20 09:07:21 +08:00
tom__chen b94bba1def index_add gpu op 2021-02-19 09:49:06 -05:00
mindspore-ci-bot feb07198e7 !12399 Add type support to Squeeze gpu op 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-02-19 21:33:20 +08:00
mindspore-ci-bot 7d97d1300e !12370 Add type support to CumSum gpu op 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-02-19 21:33:02 +08:00
mindspore-ci-bot 191b3f0c8c !12368 Add type support to Split gpu op 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-02-19 04:16:29 +08:00
Peilin Wang 4821caa143 add uint16, uint32, int8, int64, float64 type support to gpu Squeeze op 
change to test in graph mode
 2021-02-18 14:11:59 -05:00
mindspore-ci-bot 7443ea4b5b !12369 Add type support to tile op 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-02-18 23:42:54 +08:00
mindspore-ci-bot f021af8096 !12367 Add float64 support to MatMul ops in GPU 
From: @TFbunny
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-02-18 23:41:45 +08:00
mindspore-ci-bot 4b27c3206d !12362 Add float64 support to Abs, Neg, Sqrt, Sin, Cos 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2021-02-18 23:39:38 +08:00
mindspore-ci-bot 048eba4460 !12359 add float64 support to assign GPU 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-02-18 10:10:56 +08:00
Peilin Wang 5f7fc5a0b1 initial commit 
fix ci
 2021-02-17 17:39:18 -05:00
Peilin Wang 1655a88b64 initial commit 2021-02-17 16:08:39 -05:00
Peilin Wang 2252e440a5 initial commit 
fix ci
 2021-02-17 15:32:48 -05:00
Peilin Wang 073fc6fa93 initial commit 
fix ci
 2021-02-17 13:36:30 -05:00
TFBunny 4c18e0894e add float64 support to matmul ops 2021-02-17 12:35:55 -05:00
Peilin Wang ce26d2e987 intitial commit 
fix ci

fix ci
 2021-02-12 17:17:57 -05:00
TFBunny e1ed3b9c15 add float64 support to assign GPU 2021-02-12 16:17:16 -05:00
TFBunny c6baca71e5 add float64 support to ReduceMax and ReduceSum 2021-02-12 12:51:03 -05:00
mindspore-ci-bot 8d936a6589 !12352 Add float64 support to Gather GPU 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-02-13 00:03:14 +08:00
mindspore-ci-bot 0ee8ef736d !12351 Add float64 support to GatherNd GPU 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-02-13 00:02:17 +08:00
mindspore-ci-bot 8fabb26412 !12350 add float64 support to concat GPU 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-02-12 23:25:50 +08:00
TFBunny 6f9cfb809e add float64 support to GatherNd 2021-02-11 13:43:03 -05:00
TFBunny 6fad165e43 add float64 support to gather gpu 2021-02-11 12:01:04 -05:00
TFBunny ebb7f2e771 add float64 support to concat GPU 2021-02-11 11:03:10 -05:00
mindspore-ci-bot d249ededf6 !12347 add float64 support to slice ops in GPU 
From: @TFbunny
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2021-02-11 04:02:59 +08:00
mindspore-ci-bot ed5f9cb1f2 !11802 Optimize GPU kernels for fasterrcnn 
From: @robingrosman
Reviewed-by: 
Signed-off-by:
 2021-02-11 02:53:05 +08:00
TFBunny 799e51cff0 Add float64 support to slice ops 2021-02-10 11:51:38 -05:00
RobinGrosman 5d5225f2ee optimize fasterrcnn on gpu. fix randomchoicewithmask, topk kernels 2021-02-09 13:57:00 -08:00
mindspore-ci-bot adf934c567 !12152 Rewrite sequence_mask as a composite op 
From: @TFbunny
Reviewed-by: @robingrosman
Signed-off-by:
 2021-02-09 20:40:10 +08:00
mindspore-ci-bot 96cea98864 !11731 Add dynamic shape support to ReLU6 GPU 
From: @TFbunny
Reviewed-by: 
Signed-off-by:
 2021-02-09 06:40:52 +08:00
mindspore-ci-bot 6ed6d57076 !11560 Add dynamic shape support and testcases to GPU Dropout 
From: @TFbunny
Reviewed-by: 
Signed-off-by:
 2021-02-09 06:32:51 +08:00
mindspore-ci-bot 4d9551e129 !12046 modify Gelu、FastGelu to GeLU and FastGeLU 
From: @jinyaohui
Reviewed-by: 
Signed-off-by:
 2021-02-06 09:57:48 +08:00
TFBunny ad3d737d29 Rewrite sequence_mask as a composite op 2021-02-05 18:01:08 -05:00
mindspore-ci-bot 5a2f472790 !12153 Add type support to StridedSlice GPU 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-02-05 22:47:03 +08:00
jinyaohui 30a27b2adb modify Gelu、FastGelu to GeLU and FastGeLU 2021-02-05 17:19:52 +08:00
TFBunny b45a9f56c8 add all types support to StridedSlice GPU 2021-02-04 16:46:27 -05:00
mindspore-ci-bot 9af166990c !12074 gpu RangeOp precision fix 
From: @peilin-wang
Reviewed-by: 
Signed-off-by:
 2021-02-05 05:32:27 +08:00
Peilin Wang 44bb9cb216 added validation 
fix ci

fix ci

fixed test cases and ci

fixed test cases and ci
 2021-02-04 16:19:07 -05:00
mindspore-ci-bot 74652eb942 !12044 modify pack to stack 
From: @jinyaohui
Reviewed-by: 
Signed-off-by:
 2021-02-04 21:02:09 +08:00
jinyaohui 8022f9a6ed modify pack to stack 2021-02-04 18:54:31 +08:00
mindspore-ci-bot 62d272f648 !12014 Fix GPU Print kernel 
From: @TFbunny
Reviewed-by: 
Signed-off-by:
 2021-02-03 22:45:44 +08:00
TFBunny 5a8c899789 Rework GPU print, supporting pynative mode and graph mode 2021-02-02 18:35:46 -05:00
l00591931 9ec100d069 Change TensorAdd to Add, from r1.1 to master 2021-02-01 17:53:52 +08:00
mindspore-ci-bot ce89cc5e8b !11761 Change GatherV2 to Gather (merge from r1.1 to master) 
From: @liangzhibo
Reviewed-by: 
Signed-off-by:
 2021-01-30 17:53:20 +08:00
mindspore-ci-bot 9fa0499fa0 Change GatherV2 to Gather r1.1 to master 2021-01-30 14:13:47 +08:00
Corleone 82de371987 update matmul implementation for GPU 2021-01-30 14:12:11 +08:00
mindspore-ci-bot 96f007ebb4 !11785 gpu RangeOp better error handling in kernel 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2021-01-29 21:06:52 +08:00
mindspore-ci-bot 76e9cc46fe !11688 Add GPU ReciprocalGrad Kernel 
From: @TFbunny
Reviewed-by: @tom__chen,@tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-01-29 11:59:08 +08:00
Peilin Wang 3bef4e9b75 range better error initial commit 2021-01-28 16:11:16 -05:00
wilfChen 2e7d7b1c5e gpu testcase fix 2021-01-28 20:08:39 +08:00
TFBunny 88b5458f78 add new GPU kernel ReciprocalGrad 2021-01-27 17:48:01 -05:00
TFBunny 2fc5ebd077 add dynamic shape support and testcases to GPU Dropout 2021-01-27 17:44:26 -05:00
TFBunny 0e05e3e8ec add dynamic shape support and testcases to ReLU6 2021-01-27 17:41:06 -05:00
TFBunny 6cd7dc42e9 add testcases and dynamic shape to reduce ops 2021-01-27 12:26:22 -05:00
Jonathan Yan 18f67c61c2 return minimal index for argmaxwithvalue 2021-01-25 08:47:32 -05:00
tom__chen f34934a317 fix conv2d NHWC filter shape and cyclomatics errors 2021-01-22 16:46:39 -05:00
mindspore-ci-bot f07bb3bd04 !11089 General reduction with hybrid mode 
From: @jonwe
Reviewed-by: @robingrosman,@tom__chen,@robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2021-01-21 20:24:50 +08:00
mindspore-ci-bot ddf84551ab !11328 OneHot int64 input support 
From: @peilin-wang
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-01-21 06:01:21 +08:00
mindspore-ci-bot 868f0e9361 !11247 Add dynamic shape support to GPU BiasAdd 
From: @TFbunny
Reviewed-by: @tom__chen
Signed-off-by:
 2021-01-20 23:59:22 +08:00
TFBunny 6a58479e42 add dynamic shape and testcases to GPU biasadd 2021-01-20 09:35:27 -05:00
Jonathan Yan 6c8f275bdd redcution v1 2021-01-19 18:53:52 -05:00
mindspore-ci-bot 60feffad20 !11332 update Pooling's attr kernel_size, pad_mode 
From: @yuchaojie
Reviewed-by: 
Signed-off-by:
 2021-01-19 16:17:45 +08:00
mindspore-ci-bot 45e03742d2 !11392 TileOp gpu int64 input support 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2021-01-19 05:46:56 +08:00
mindspore-ci-bot 6d0c0157aa !11213 Add dynamic shape support to GPU ReduceMean 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-01-19 03:16:34 +08:00
Peilin Wang 945ef9ff89 initial commit 
forgot some test cases
 2021-01-18 11:16:47 -05:00
Peilin Wang 386b219ffc initial commit 
ci fix

fix ci
 2021-01-18 00:03:39 -05:00
yuchaojie b51b3a6764 update Pool's attr kernel_size, pad_mode 2021-01-18 12:10:20 +08:00
mindspore-ci-bot 8008843562 !11327 Dynamic shape support for Conv2d Op 
From: @tom__chen
Reviewed-by: 
Signed-off-by:
 2021-01-17 22:46:18 +08:00
tom__chen 2ff5f9f1bc dynamic shape support for conv2d op 2021-01-16 00:39:30 -05:00
mindspore-ci-bot be14046b0e !11290 Add dynamic shape support & testcases to MatMul, BatchMatMul gpu 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-01-16 07:01:37 +08:00
TFBunny c994eab732 add dynamic shape and testcases to MatMul & BatchMatMul 2021-01-14 18:56:15 -05:00
TFBunny 07de432deb add dynamic shape testcase to tensoradd 2021-01-14 12:24:26 -05:00
mindspore-ci-bot 59551879a0 !11021 Add new nn layer InstanceNorm2d 
From: @yuan_shen_zhou
Reviewed-by: 
Signed-off-by:
 2021-01-14 17:43:11 +08:00
zhouyuanshen 26f6daa850 add new op instancenorm2d 2021-01-14 15:38:56 +08:00
mindspore-ci-bot e5afc028f6 !11168 Add a testcase for P.mul dynamic shape 
From: @TFbunny
Reviewed-by: 
Signed-off-by:
 2021-01-13 22:53:22 +08:00
TFbunny d0b2f17445 add dynamic shape to GPU ReduceMean with testcases 2021-01-12 16:19:01 -05:00
TFbunny 503c38ca1a add testcase for dynamic shape GPU P.Mul 2021-01-11 16:19:17 -05:00
linqingke b9467e5340 fix matrix inverse ops st. 2021-01-11 10:38:49 +08:00
mindspore-ci-bot 6d6ed86a9d !10427 RangeOp new gpu kernel 
From: @peilin-wang
Reviewed-by: 
Signed-off-by:
 2021-01-07 23:14:40 +08:00
mindspore-ci-bot cdeacdf5c7 !9809 Add int8 uint8 type support to GPU ScatterAdd 
From: @TFbunny
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2021-01-07 05:48:15 +08:00
Peilin Wang 507cc4ab15 range past segfault addressed comments 
changed default max_output_length to 1000000

change docstring

fix ci

change max_output_length to maxlen
 2021-01-06 13:39:28 -05:00
mindspore-ci-bot 5a70853392 !10332 add grad definitions for the following operations: ReluGrad, SqrtGrad, AtanGrad, TanhGrad, AsinhGrad, AcoshGrad. 
From: @david-he91
Reviewed-by: @liangchenghui
Signed-off-by: @liangchenghui
 2021-01-06 15:59:17 +08:00
mindspore-ci-bot 9f44599abd !9806 equal op gpu kernel support int64/uint8 
From: @jonwe
Reviewed-by: @robingrosman,@tom__chen,@robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2021-01-06 04:45:27 +08:00
mindspore-ci-bot 666ab8f105 !10850 Conversion weights type when compute weights loss 
From: @xuguoyang5566
Reviewed-by: @wuxuejian
Signed-off-by: @wuxuejian
 2021-01-04 18:53:12 +08:00
xuguoyang 7dcc3d89c3 Conversion weights type when compute weights loss 2021-01-04 15:30:20 +08:00
mindspore-ci-bot 1bb9342aa0 !8100 New add matrix inverse ops. 
From: @linqingke
Reviewed-by: 
Signed-off-by:
 2020-12-30 15:45:50 +08:00
hedongdong b783070467 add grad definitions for the following operations: ReluGrad, SqrtGrad, AtanGrad, TanhGrad, AsinhGrad, AcoshGrad. 
A minor change in sigmoidGradGrad operation (non-functional change).
 2020-12-30 14:57:26 +08:00
mindspore-ci-bot f80b28313f !10619 add timedistributed 
From: @d00562747
Reviewed-by: 
Signed-off-by:
 2020-12-30 09:33:27 +08:00
TFbunny 83e06bbba0 add return to sparseapplyftrl gpu 2020-12-29 16:18:43 -05:00
dinglongwei 5a6caa7b0a add timedistributed and bugfix cpu ops assign and maximum 2020-12-29 17:40:21 +08:00
mindspore-ci-bot ee07285420 !10580 Add new GPU operators: Asinh, AsinhGrad, Acosh, AcoshGrad, Atan and AtanGrad 
From: @david-he91
Reviewed-by: @linqingke,@liangchenghui,@liangchenghui
Signed-off-by: @liangchenghui,@liangchenghui
 2020-12-29 16:40:14 +08:00
linqingke 96183f8b12 new add matrix inverse. 2020-12-29 16:34:21 +08:00
mindspore-ci-bot b381d4f7a0 !10603 add grad definition for AsinGrad and ACosGrad. 
From: @wangshuide2020
Reviewed-by: @liangchenghui,@linqingke
Signed-off-by: @liangchenghui
 2020-12-29 15:19:11 +08:00
mindspore-ci-bot 2dc275be06 !9842 Add SquaredDifference kernel for GPU 
From: @he-botao
Reviewed-by: @c_34
Signed-off-by:
 2020-12-29 09:41:45 +08:00
hebotao f4ae9cdbc4 Add SquareDifference kernel for GPU 
添加测试用例

添加测试用例

添加测试用例

添加测试用例
清除告警

添加测试用例

添加测试用例

清除告警
 2020-12-28 16:47:52 +08:00
mindspore-ci-bot aecd96cdb2 !10424 Compute weighted loss 
From: @xuguoyang5566
Reviewed-by: @wuxuejian
Signed-off-by:
 2020-12-28 10:00:10 +08:00
wangshuide2020 677127ef5e add grad definition for AsinGrad and ACosGrad 2020-12-26 16:03:01 +08:00
hedongdong 352a362878 Add new GPU operators: Asinh, AsinhGrad, Acosh, AcoshGrad, Atan and AtanGrad 2020-12-26 11:09:07 +08:00
xuguoyang 7fe25d6444 Add weights loss compute 2020-12-26 10:47:54 +08:00
mindspore-ci-bot 6e690ab725 !9949 add testcase and minor fix for SparseApplyProximalAdagrad/Ftrl 
From: @TFbunny
Reviewed-by: @liangchenghui,@linqingke
Signed-off-by: @liangchenghui
 2020-12-24 14:15:22 +08:00
mindspore-ci-bot f9dbebd958 !10410 add dtype supports[fp64/fp32/fp16/int8/int16/int32/int64/uint8] for relu/reluv2/relugradv2 
From: @yuan_shen_zhou
Reviewed-by: @wilfchen,@liangchenghui,@linqingke
Signed-off-by: @liangchenghui
 2020-12-24 10:00:55 +08:00
zhouyuanshen 2e2c01d6f0 add dtype supports for relu/reluv2/relugradv2 2020-12-23 22:04:35 +08:00
mindspore-ci-bot 44abd94b42 !9408 [ME][Pynative]Fix mem leak problem in pynative mode 
From: @chenfei52
Reviewed-by: 
Signed-off-by:
 2020-12-23 21:30:10 +08:00
chenfei 1f20e552ed handle mem leak in pynative mode 
use enter and leave construct
 2020-12-23 17:10:58 +08:00
mindspore-ci-bot b8b4ce7442 !10323 Rewrite gpu implementation for op maxpool_with_argmax/maxpool_with_argmax_grad 
From: @yuan_shen_zhou
Reviewed-by: @linqingke,@liangchenghui
Signed-off-by: @linqingke
 2020-12-22 19:56:52 +08:00
zhouyuanshen 09b68f9006 rewrite gpu implementation of op maxpool_with_argmax and maxpool_with_argmax_grad 2020-12-22 12:37:33 +08:00
mindspore-ci-bot 2b64b7f295 !10312 SequenceMask move API to composite 
From: @peilin-wang
Reviewed-by: @liangchenghui,@wuxuejian
Signed-off-by: @liangchenghui
 2020-12-22 09:24:46 +08:00
Peilin Wang 412665f707 wrap sequenceMask in composite 2020-12-21 16:27:00 -05:00
Peilin Wang 299509dbfc changed cast to round to zero if casting from float to integral 2020-12-21 13:54:42 -05:00
mindspore-ci-bot 4477b97465 !10167 BatchNormGrad infer gpu kernel 
From: @jonwe
Reviewed-by: @liangchenghui
Signed-off-by:
 2020-12-21 10:41:52 +08:00
mindspore-ci-bot 88155de042 !10159 momentum weight fusion 
From: @wilfchen
Reviewed-by: @cristoval,@limingqi107
Signed-off-by: @cristoval
 2020-12-19 17:05:38 +08:00
Jonathan Yan 335c3f7602 BatchNormGrad infer gpu kernel 2020-12-18 17:03:27 -05:00
mindspore-ci-bot 4b7e9975a0 !10090 [MS][GPU][CI Alarm] Fixed CI Alarm for Pad GPU kernel + code clean up 
From: @danishnxt
Reviewed-by: @robingrosman
Signed-off-by: @robingrosman
 2020-12-19 04:37:05 +08:00
mindspore-ci-bot 1c43115eef !9540 [MS][API] - Update BroadcastTo to be able to support dynamic -1 
From: @danishnxt
Reviewed-by: @robingrosman,@robingrosman
Signed-off-by: @robingrosman
 2020-12-19 02:03:07 +08:00
mindspore-ci-bot a83e058f42 !9858 [MS][GPU][API] UnsortedScatterND_int64_Support 
From: @danishnxt
Reviewed-by: @tom__chen,@robingrosman,@robingrosman
Signed-off-by:
 2020-12-19 00:21:40 +08:00
wilfChen 09e10e18bb momentum weightdecay fusion 2020-12-18 19:08:05 +08:00
jonwe 54e5025c1a equal op gpu kernel 2020-12-17 21:24:30 -05:00
mindspore-ci-bot eb22cf7e5a !10073 [MS][CompositeOp][API] TensorDot pr fix 
From: @danishnxt
Reviewed-by: @tom__chen
Signed-off-by:
 2020-12-18 03:58:09 +08:00
danishnxt ac109b601a pad_CI_Alarm fix 
typo fix

test addition for half - pad value checking
 2020-12-17 14:47:27 -05:00
mindspore-ci-bot 904f61b7fd !9857 [MS][GPU] SparseApplyFtrl_int64_Support 
From: @danishnxt
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2020-12-18 03:05:54 +08:00
danishnxt b0b768335e PR 10072 fix + new sts 
lintfix

doc fix + code cleaned

doc update 2
 2020-12-17 13:57:05 -05:00
mindspore-ci-bot b645f7959d !9749 [MS][API] UnsortedSegmentMax_Min added check for bug fix - num_segments 
From: @danishnxt
Reviewed-by: 
Signed-off-by:
 2020-12-17 04:33:38 +08:00
danishnxt d1fcfaf0f2 First commit - scatter_nd_int64_update 
lint fix - no lint required for previous code

fix int64 templates

removed extra files
 2020-12-16 15:19:13 -05:00
danishnxt bc84e9b4e7 range check - UortedSegmin/max num_seg tensors 
added in checks in PythonAPI to trigger Value errors in case of non dyn

added required check for python API

ST update + op check update

revert segSum change

updated gatherV2 and SplitOp check

added shape -1 sanity check - splitOp

slight refactor in unseg-Min/Max

lintfix

lint fix
 2020-12-16 13:12:04 -05:00
mindspore-ci-bot a3d4dded12 !9979 BUGFIX: Correct the calculation of the output 'd_x' of the operator LayernormGradGrad 
From: @david-he91
Reviewed-by: @liangchenghui,@linqingke
Signed-off-by: @liangchenghui
 2020-12-16 21:12:16 +08:00
hedongdong 6cc9d2c087 BUGFIX: Correct the calculation of the output 'd_x' of the operator LayernormGradGrad 2020-12-16 16:30:42 +08:00
mindspore-ci-bot b401a5fb07 !9750 add int64 support to UniformCandidateSampler GPU 
From: @TFbunny
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2020-12-16 04:16:30 +08:00
danishnxt 67c528386e update BroadcastTo 
typo in API

added init type check + fix doc

fixes

lint

added prim_attr setter in python API

revert back one

changed self.shape / add prim attr

fix
 2020-12-14 17:24:45 -05:00
TFbunny 01903eb770 add int64 support to transpose GPU 2020-12-14 15:49:00 -05:00
TFbunny d5a08f1956 add testcase for input update in adagrad and move resetresource 2020-12-14 15:18:23 -05:00
danishnxt 55c455df9e first commit - updated op + STs 
lint fix
 2020-12-11 13:54:31 -05:00
mindspore-ci-bot d68708960e !9620 [MS][GPU] UnsortedSegmentMax_int64_Support 
From: @danishnxt
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by:
 2020-12-12 00:26:43 +08:00
mindspore-ci-bot e20be19548 !9476 Change Tensor shape from int to size_t for GPU Argmax 
From: @TFbunny
Reviewed-by: 
Signed-off-by:
 2020-12-12 00:10:03 +08:00
TFbunny 43755a71e7 add additional type support to ScatterAdd 2020-12-10 17:17:48 -05:00
jonwe d982fec2ff ReLU/ReLUGrad int8/32/64 support 2020-12-10 14:33:47 -05:00
TFbunny 5263588b2c add int64 support to UniformCandidateSampler GPU 2020-12-10 11:08:33 -05:00
mindspore-ci-bot bb241214f8 !9747 add int64 support for indices of GPU gatherNd 
From: @TFbunny
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2020-12-10 21:05:02 +08:00
mindspore-ci-bot 0c2856c632 !9617 Add new operator layer_norm_grad_grad 
From: @david-he91
Reviewed-by: 
Signed-off-by:
 2020-12-10 15:15:46 +08:00
hedongdong 8bfeadf26e Add new operator layer_norm_grad_grad 2020-12-10 14:10:24 +08:00
mindspore-ci-bot be4e91339f !9661 gpu relu optimize 
From: @wilfchen
Reviewed-by: @cristoval,@limingqi107
Signed-off-by: @limingqi107
 2020-12-10 11:32:22 +08:00
danishnxt 0be02c4756 UnsortedSegMax_Int64_support 
lint fix

style fix

style fix 2
 2020-12-09 17:52:11 -05:00
TFbunny d274f425c7 change tensor shape from int to size_t for GPU Argmax 2020-12-09 17:45:10 -05:00
TFbunny f54bd166a6 add int64 support for indices of GatherND gpu 2020-12-09 14:45:32 -05:00
mindspore-ci-bot 0aa7197ef8 !9694 ZerosLike dynamic shape support 
From: @peilin-wang
Reviewed-by: @liangchenghui
Signed-off-by: @liangchenghui
 2020-12-09 16:54:07 +08:00
wilfChen c1d3bd2160 relu optimize 2020-12-09 14:31:45 +08:00
Peilin Wang d9fb28b9fc zeroslike dynamic shape no opt 
fix ci

fix ci

fix ci

fix ci
 2020-12-08 22:31:58 -05:00
zhouyuanshen e9aca01620 add support to reduceAny and reduceAll on gpu 2020-12-09 10:21:04 +08:00
mindspore-ci-bot dbc592acce !9537 [MS][GPU] GatherV2_int64_Support 
From: @danishnxt
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2020-12-07 21:05:17 +08:00
mindspore-ci-bot ec025a1c4c !9288 Add Adagrad for GPU kernel 
From: @zyx5256
Reviewed-by: 
Signed-off-by:
 2020-12-07 19:01:59 +08:00
mindspore-ci-bot 9d1e6ca59f !9492 Fix implement bug in pack and unpack 
From: @yuan_shen_zhou
Reviewed-by: @liangchenghui,@linqingke
Signed-off-by: @liangchenghui
 2020-12-07 14:58:44 +08:00
danishnxt e3c75646eb changes to GatherV2 kernel for int64 support 2020-12-04 14:27:53 -05:00
zhuyuxiao 77a68b9d2b add adagrad for gpu kernel 2020-12-04 17:15:14 +08:00
zhouyuanshen 3eec6a8d7b fix bug in pack and unpack 2020-12-04 16:17:08 +08:00
mindspore-ci-bot 9466429fdd !9417 Mod test_dense in ut 
From: @wanyiming
Reviewed-by: @zh_qh,@kingxian
Signed-off-by: @kingxian
 2020-12-04 11:38:47 +08:00
mindspore-ci-bot 215f0a7b46 !9037 Updating inputs for ScatterAdd and ScatterUpdate, fix dynamic issue 
From: @TFbunny
Reviewed-by: @robingrosman,@robingrosman
Signed-off-by:
 2020-12-04 02:07:00 +08:00
mindspore-ci-bot b5269d6bd4 !9402 [GPU] Unique op int64 support 
From: @tom__chen
Reviewed-by: @robingrosman,@mikef
Signed-off-by: @robingrosman
 2020-12-03 21:09:53 +08:00
wanyiming 5ab8007475 mod dense 2020-12-03 11:32:03 +08:00
mindspore-ci-bot b15504f6a5 !9327 Cast half to int by rounding down 
From: @jonwe
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2020-12-03 05:25:01 +08:00
mindspore-ci-bot 6945c4dd5f !9338 [MS][DynamicShape] Bug in InferImpl for UnsortedSegmentOps (incorrect identification of dynamic mode) 
From: @danishnxt
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2020-12-03 04:19:44 +08:00
danishnxt bf5ceaae57 updated to test files + DynamicOpCheckFix 
lintfix

Adding Dynamic_shape_depends
 2020-12-02 13:44:46 -05:00
TFbunny 27a602f067 update input for ScatterUpdate/Add, fix doc text and fix dynamic shape 2020-12-02 12:53:03 -05:00
tom__chen c454101d7c unique op int64 support 2020-12-02 12:08:07 -05:00
tom__chen ee8a060f55 Fix unique dynamic shape 2020-12-02 07:49:56 -05:00
mindspore-ci-bot eb7cbd49ac !8595 Add Cholesky op at GPU back-end 
From: @peixu_ren
Reviewed-by: @zichun_ye,@wilfchen
Signed-off-by:
 2020-12-02 10:10:24 +08:00
jonwe e2e6bf59b2 Cast half to int by rounding down 2020-12-01 11:48:30 -05:00
mindspore-ci-bot 01df2341ff !9245 Fixes some typos and formatting errors in docstring. 
From: @peilin-wang
Reviewed-by: @robingrosman,@robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2020-12-01 20:08:18 +08:00
peixu_ren af6ded28e3 Add Cholesky op at GPU back-end 2020-11-30 20:27:22 -05:00
Peilin Wang e4444a1c12 initial commit 
fix testcases

fix ci
 2020-11-30 17:52:07 -05:00
mindspore-ci-bot ccf637f64a !9241 SequenceMask gpu kernel 
From: @peilin-wang
Reviewed-by: @tom__chen
Signed-off-by:
 2020-12-01 06:49:47 +08:00
Peilin Wang f7dc2432a0 initial commit 
fix ci

fix ci

remove old sequence mask api

fix ci

fix ci

remove old seuqence mask tests
 2020-11-30 14:44:22 -05:00
mindspore-ci-bot 5835095e07 !9134 Equal op dynamic shape 
From: @jonwe
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2020-12-01 00:55:27 +08:00
danishnxt 450f1ee886 First Commit - UnsortedSegMin Kernel + DynamicSupport 
lint fix + SegMAX st fix

removing unreq whitspace

lint fix

lint fix2
 2020-11-27 18:29:30 -05:00
mindspore-ci-bot 3e2eb70fc0 !8669 Split op extending PrimitiveWithCheck 
From: @tom__chen
Reviewed-by: 
Signed-off-by:
 2020-11-28 06:50:40 +08:00
mindspore-ci-bot 442217314d !8861 [MS][GPU][DynamicShapeUpdate] Converting UnsortedSegmentMax from normal to dynamic shape op 
From: @danishnxt
Reviewed-by: 
Signed-off-by:
 2020-11-28 06:49:39 +08:00
mindspore-ci-bot 28772d4fb7 !9132 Fix bug for SparseGatherV2 GPU and add dynamic shape testcase 
From: @TFbunny
Reviewed-by: 
Signed-off-by:
 2020-11-28 06:04:20 +08:00
mindspore-ci-bot 9b0ec824c4 !9096 DynamicShapeOp int64 support and bug fix 
From: @peilin-wang
Reviewed-by: @robingrosman,@tom__chen
Signed-off-by: @robingrosman
 2020-11-28 06:01:12 +08:00
mindspore-ci-bot 2e31899101 !9095 [MS][DynamicShape][API] Fixes for UnsortedSegementSum DynamicShape support API + InferImpl func 
From: @danishnxt
Reviewed-by: 
Signed-off-by:
 2020-11-28 05:58:07 +08:00
mindspore-ci-bot b76c7cc7bf !9025 ReLU gpu op supports int32 and int64 
From: @jonwe
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @tom__chen
 2020-11-28 05:54:11 +08:00
tom__chen 4fa6238dde change Split op to extend PrimitiveWithCheck 2020-11-27 15:33:20 -05:00
jonwe 6ae8573803 Equal op dynamic shape 2020-11-27 14:59:53 -05:00
TFbunny 419f8bf72a fix dynamic shape and add testcase for SparseGatherV2 GPU 2020-11-27 12:45:29 -05:00
mindspore-ci-bot f28b73f231 !9040 ExpandDims dynamic shape 
From: @jonwe
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2020-11-27 23:41:20 +08:00
mindspore-ci-bot 28e6c7f29e !9034 [MS][DynamicShape] - Converting P.Square to DynamicShape op 
From: @danishnxt
Reviewed-by: @robingrosman
Signed-off-by:
 2020-11-27 23:25:45 +08:00
mindspore-ci-bot b0496aaa10 !8673 Add min/max_shape to ScatterAdd/Update and Transpose and add new dynamic shape testcases 
From: @TFbunny
Reviewed-by: @robingrosman
Signed-off-by:
 2020-11-27 22:13:32 +08:00
Jonathan Yan 9f70ebac64 Cast/ReLU dynamic shapelsgpu op supports int32 and int64 2020-11-27 07:03:50 -05:00
jonwe 36ea519009 ExpandDims dynamic shape 2020-11-27 06:24:04 -05:00
mindspore-ci-bot 40222f59a7 !9043 Add support to op L2Loss on gpu 
From: @yuan_shen_zhou
Reviewed-by: @liangchenghui,@liangchenghui
Signed-off-by: @liangchenghui,@liangchenghui
 2020-11-27 17:05:42 +08:00
danishnxt cfc3542261 First Commit SegMax changes + typo in SegSum InferImpl 
UnsortedSegmentMax update + new STs

switch to lambda function

SegmentSum - InferImpl min/max shape pushback fix

lint fix

revert segSum due to sep pr + addressing comments:
 2020-11-26 22:06:52 -05:00
Peilin Wang 1dd302ae93 int64 support and typo fix 
fixed typo

fix pylint
 2020-11-26 20:47:20 -05:00
zhouyuanshen f6e87143c6 add support to op L2Loss on gpu 2020-11-27 09:34:47 +08:00
danishnxt 6f64fffdb4 Adding API fix for handling dynamic_shape correctly plus STs for SegSum dyn_shape 
Updating InferImpl function

adding check to inferImpl function

lint

lint2
 2020-11-26 18:50:36 -05:00
TFbunny 5e19a642f9 fix and add testcase for dynamic shape scatteradd/update transpose 2020-11-26 17:33:49 -05:00
mindspore-ci-bot e6ebb310eb !8928 [MS][GPU][CUDA] - New GPU kernel -> LinSpace 
From: @danishnxt
Reviewed-by: 
Signed-off-by:
 2020-11-27 05:26:59 +08:00
danishnxt 64a6769d3f Update Square Op to support Dynamic Shape 2020-11-26 12:49:15 -05:00
mindspore-ci-bot c3b057bd69 !8825 [MS][GPU] GatherV2_Dynamic_BugFix 
From: @danishnxt
Reviewed-by: 
Signed-off-by:
 2020-11-27 01:07:32 +08:00
danishnxt a17f76dd1d Initial Commit - GPU LinSpace 
comment fix

docString fix

added asserts in test file atop np checks

lint

lint-2

lint3
 2020-11-26 02:33:55 -05:00
danishnxt 241c8f3d96 GatherUpdate 
test file finishing pending

Update to GatherV2_Bug_Fix

lint fix

lint fix - 2

lint fix

Update to GatherV2 - fixed default inferImpl func + CudeStreamSync

lint fix

SyncDevice

added dynamic shape init_size input

lint
 2020-11-25 17:49:27 -05:00
jonwe 9a6ced3cc7 DinNoNan gpu kernel supports int8/uint8 2020-11-24 11:38:03 -05:00
mindspore-ci-bot 0793198891 !8917 Add grad definition for sigmoidGrad. 
From: @david-he91
Reviewed-by: @liangchenghui,@linqingke
Signed-off-by: @liangchenghui
 2020-11-24 10:39:36 +08:00
mindspore-ci-bot 6a04c21456 !8875 Fix some bug about GatherD and GatherDGrad op on gpu 
From: @yuan_shen_zhou
Reviewed-by: 
Signed-off-by:
 2020-11-24 09:46:50 +08:00
mindspore-ci-bot d915fd9b96 !8592 change repeat_elements to a composite op 
From: @tom__chen
Reviewed-by: 
Signed-off-by:
 2020-11-23 23:15:23 +08:00
hedongodng 0279323b99 add grad definition for sigmoidGrad operation 2020-11-23 20:08:46 +08:00
zhouyuanshen e1026961f7 fix some bug in gather and gathergrad op 2020-11-23 16:24:45 +08:00
mindspore-ci-bot 82456e3f2b !8749 batchnorm2d test case for use_batch_statistics is false 
From: @jonwe
Reviewed-by: @robingrosman
Signed-off-by:
 2020-11-21 00:54:57 +08:00
mindspore-ci-bot 044c7d183c !8803 Validate SampledSoftmaxLoss Args 
From: @jonwe
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2020-11-20 10:58:39 +08:00
jonwe 036e28bb96 batchnorm2d use_batch_statistics false test case 2020-11-19 16:23:23 -05:00
tom__chen a52cd685fc change repeat_element op to a composite op 2020-11-19 15:42:22 -05:00
Jonathan Yan 22cb2814e8 validate SampledSoftmaxLoss args 2020-11-19 12:43:58 -05:00
Peilin Wang 3d4d5ec77f initial commit for gpu dynamic shape testing op 
fix ci

fix ci
 2020-11-19 11:22:39 -05:00
mindspore-ci-bot 99fc0a4e64 !8526 Add 'in_channel' and 'out_channel' to cell_attr_register 
From: @wanyiming
Reviewed-by: @kingxian
Signed-off-by: @kingxian
 2020-11-19 15:41:53 +08:00
TFbunny fb1a65c469 add int8 and uint8 support to scatteradd and fix doc example 2020-11-17 14:41:50 -05:00
mindspore-ci-bot 3fdd75dd5e !8450 add supports to op randomcategorical on gpu 
From: @yuan_shen_zhou
Reviewed-by: @c_34,@liangchenghui
Signed-off-by: @c_34,@liangchenghui
 2020-11-13 09:28:28 +08:00
mindspore-ci-bot 71af3bf1ac !8283 Minimum Op and Mul Op support dynamic shape 
From: @jonwe
Reviewed-by: 
Signed-off-by:
 2020-11-13 05:24:00 +08:00
Jonathan Yan 5a8238a09c mul v1 2020-11-12 13:45:10 -05:00
wanyiming 237bcfd36b add_channel_to_attr 2020-11-12 20:18:26 +08:00
mindspore-ci-bot 7d6039d384 !7858 [MS][GPU] Add Unique Op 
From: @tom__chen
Reviewed-by: 
Signed-off-by:
 2020-11-12 04:08:07 +08:00
mindspore-ci-bot a511e32cf8 !8386 [MS] Changing TensorDot from P Operations op to Composite op 
From: @danishnxt
Reviewed-by: @tom__chen,@robingrosman
Signed-off-by: @robingrosman
 2020-11-12 02:12:25 +08:00
zhouyuanshen 048fc49aed add support to op RandomCategorical 2020-11-11 19:13:13 +08:00
tom__chen 9263145990 gpu unique op kernel and st test 2020-11-10 13:45:25 -05:00
TFbunny 7f769568a6 Register SparseGatherV2 and add dynamic shape support 2020-11-10 10:49:49 -05:00
danishnxt 9dba65c424 TensorDot Conv: P -> C 2020-11-09 17:25:10 -05:00
mindspore-ci-bot 35dd47711d !7798 ROIAlign GPU kernel height/width plus1 
From: @jonwe
Reviewed-by: @robingrosman,@robingrosman,@tom__chen
Signed-off-by: @tom__chen
 2020-11-09 21:14:03 +08:00
mindspore-ci-bot 7622b44c21 !8170 Support Nd*2d for nn.Dense 
From: @wanyiming
Reviewed-by: 
Signed-off-by:
 2020-11-09 21:01:51 +08:00
HuangBingjian 265a6d61b6 reverse fix shape=0 2020-11-09 15:06:37 +08:00
mindspore-ci-bot c76e7107a5 !8220 Add supports to op unpack on gpu 
From: @yuan_shen_zhou
Reviewed-by: @liangchenghui
Signed-off-by: @liangchenghui
 2020-11-09 09:50:52 +08:00
mindspore-ci-bot 370e7ab95f !8204 add supports to op pack on gpu 
From: @yuan_shen_zhou
Reviewed-by: @liangchenghui
Signed-off-by:
 2020-11-09 09:32:09 +08:00
wanyiming 3c7a3b6693 modify_dense 2020-11-06 15:45:43 +08:00
zhouyuanshen 5c4885821f add supports to op unpack on gpu 2020-11-06 14:23:54 +08:00
zhouyuanshen 00f1c0c7f3 add supports to op pack on gpu 2020-11-06 14:19:30 +08:00
HuangBingjian 4477fcfe19 fix shape bug. 2020-11-06 12:59:03 +08:00
jonwe 575280bb61 roi end mode 2020-11-04 13:21:10 -05:00
mindspore-ci-bot 4b4ca1a188 !8146 Improve performance for GPU-ScatterUpdate, add int32 support 
Merge pull request !8146 from 34bunny/GPU-ScatterUpdateFix
 2020-11-04 22:05:52 +08:00
mindspore-ci-bot 04142b74f6 !8144 Rename GPU-UniformSampler to GPU-UniformCandidateSampler 
Merge pull request !8144 from 34bunny/GPU-UniformCandidateSampler
 2020-11-04 21:08:46 +08:00
mindspore-ci-bot 4c2344ed35 !8141 Improve performance for GPU-ScatterAdd, add use_locking and add int32 support 
Merge pull request !8141 from 34bunny/GPU-ScatterAdd
 2020-11-04 21:07:57 +08:00
TFbunny cd7329082e refine GPU-Scatteradd 2020-11-03 16:24:16 -05:00
mindspore-ci-bot 769bd24c63 !8002 Add expm1 op at GPU back-end 
Merge pull request !8002 from peixu_ren/custom_gpu
 2020-11-03 09:16:04 +08:00
TFbunny 356844da46 refine GPU-ScatterUpdate 2020-11-02 19:01:33 -05:00
TFbunny ee4e2db77e rename UniformSampler to UniformCandidateSampler 2020-11-02 16:31:44 -05:00
mindspore-ci-bot cfe226fc97 !7950 new add softplus and softplus grad gpu ops. 
Merge pull request !7950 from linqingke/gpu_ops
 2020-11-02 09:17:58 +08:00
mindspore-ci-bot ccbc6df79c !8068 add supports to op gathergrad on gpu 
Merge pull request !8068 from zhouyuanshen/gathergrad
 2020-10-31 15:58:33 +08:00
zhouyuanshen 21c96b3c31 add supports to op gathergrad on gpu 2020-10-31 14:43:37 +08:00
mindspore-ci-bot b64de9c1dc !8000 Add supports to op Gather on gpu 
Merge pull request !8000 from zhouyuanshen/gather
 2020-10-31 13:12:44 +08:00
mindspore-ci-bot 497f2f0cff !8054 Add gpu support for ScatterUpdate 
Merge pull request !8054 from 34bunny/GPU-ScatterUpdate
 2020-10-31 07:17:33 +08:00
mindspore-ci-bot de20d3e488 !8006 [MS][GPU][CUDA][API] Adding new Ops - UnsortedSegmentMax GPU 
Merge pull request !8006 from danishnxt/SegMax
 2020-10-31 05:48:50 +08:00
TFbunny cd9d0bf79a add GPU-ScatterUpdate 2020-10-30 16:54:54 -04:00
mindspore-ci-bot 93c11d1dcc !8008 Add gpu support to ScatterAdd 
Merge pull request !8008 from 34bunny/GPU-ScatterAdd
 2020-10-31 03:13:42 +08:00
mindspore-ci-bot 4f4eadda8f !8003 Repeat Elements Grad GPU Kernel 
Merge pull request !8003 from JonathanY/repeat_grad
 2020-10-31 03:11:53 +08:00
peixu_ren b8abcf858a Add expm1 op at GPU back-end 2020-10-30 10:06:57 -04:00
zhouyuanshen f0f67b8aa8 add gather op on gpu 2020-10-30 15:05:36 +08:00
TFbunny dc2144ee0d add GPU-ScatterAdd 2020-10-29 17:51:26 -04:00
danishnxt 34cc178bd0 New New UnsortedSegmentMax for GPU [API][CUDA_KERNEL] 
PyLintFix

header fix
 2020-10-29 16:33:03 -04:00
jonwe e896d38c34 repeat grad 2020-10-29 16:29:01 -04:00
mindspore-ci-bot 542a52fbf8 !7873 [MS][GPU] Add GPU SparseApplyFtrl op 
Merge pull request !7873 from tom_chen/sparse_ftrl
 2020-10-30 04:20:20 +08:00
mindspore-ci-bot 851ee9c3d5 !7875 Add support to GPU SparseApplyProximalAdagrad 
Merge pull request !7875 from 34bunny/GPU-SparseApplyProximalAdagrad
 2020-10-30 04:11:27 +08:00
linqingke 6dc3618758 new add softplus and softplus grad gpu ops. 2020-10-29 15:13:55 +08:00
mindspore-ci-bot 9c2704030f !7872 Add log1p operator at GPU back-end and move erf and erf to the unary_op list 
Merge pull request !7872 from peixu_ren/custom_pp_ops
 2020-10-29 10:50:15 +08:00
mindspore-ci-bot 5ef3d02ce3 !7696 Add calculation of triangle matrix determinant op at GPU back-end 
Merge pull request !7696 from peixu_ren/custom_gpu
 2020-10-29 10:49:34 +08:00
TFbunny a638973378 add GPU SparseApplyProximalAdagrad 2020-10-28 14:43:08 -04:00
tom__chen 71b235c302 sparse apply ftrl gpu kernel 2020-10-28 11:56:04 -04:00
mindspore-ci-bot 4ebc55b29e !7841 Add supports to ACosGrad and AsinGrad on gpu 
Merge pull request !7841 from zhouyuanshen/ACosGrad_and_AsinGrad
 2020-10-28 21:09:48 +08:00
mindspore-ci-bot f3e8798b40 !7879 fix bug that asin/acos not support fp16 on gpu 
Merge pull request !7879 from zhouyuanshen/asin_acos_fp16
 2020-10-28 19:19:40 +08:00
mindspore-ci-bot ea4df3c3c2 !7826 new add l2normalize_grad gpu ops. 
Merge pull request !7826 from linqingke/gpu_ops
 2020-10-28 10:36:34 +08:00
zhouyuanshen 1804c042ec fix bug that asin/acos not support fp16 on gpu 2020-10-28 09:37:24 +08:00
zhouyuanshen 8481fd59d8 Add supports to ACosGrad and AsinGrad 2020-10-28 09:23:20 +08:00
peixu_ren dfe5a951eb Add log1p operator at GPU back-end and move erf and erf to the unary_op list 2020-10-27 16:22:10 -04:00
peixu_ren 99f2927c21 Add calculation of triangle matrix determinant op at GPU back-end 2020-10-27 15:20:23 -04:00
linqingke 3465c9c400 new add l2normalize_grad gpu ops. 2020-10-27 17:18:45 +08:00
mindspore-ci-bot 5b28016b4d !7735 fix gpu multinomial seed issue and GRAPH_MODE 
Merge pull request !7735 from baihuawei/fixmultinomial
 2020-10-27 15:37:07 +08:00
mindspore-ci-bot d479b91093 !7767 GPU update resnet50 readme and add cast type 
Merge pull request !7767 from VectorSL/readme
 2020-10-27 10:51:20 +08:00
mindspore-ci-bot deb17b36c1 !7786 Add SampledSoftmaxLoss GPU Kernel 
Merge pull request !7786 from JonathanY/ops_oct
 2020-10-27 07:37:37 +08:00
mindspore-ci-bot 5ad25494ab !7736 [MS][GPU][CUDA] - Reworked MirrorPad / MirrroPadGrad Op to add support for 3d/4d padding + Updated ST + added support for int32 in all GPu paddings 
Merge pull request !7736 from danishnxt/MirrorPadRework
 2020-10-27 03:13:04 +08:00
jonwe fc81f46053 sampled softmax loss 2020-10-26 09:59:00 -04:00
mindspore-ci-bot a3af89bd48 !7611 [MS][GPU] Adding new Ops - TensorDot and TensorDot Grad 
Merge pull request !7611 from danishnxt/newMaster
 2020-10-26 21:00:11 +08:00
VectorSL 5102482e3a 1readme update resnet 2cast add more type 2020-10-26 18:31:25 +08:00
mindspore-ci-bot b6b254f6e4 !7670 add l2normalize gpu kernel. 
Merge pull request !7670 from linqingke/gpu_ops
 2020-10-26 11:31:20 +08:00
danishnxt 0f69be06b1 Reworked mirrorPad 
lintIssues

convert long -> int64

correcting int64 -> int64_t

lint
 2020-10-25 20:27:54 -04:00
baihuawei 05dcec0583 fix multinomial 2020-10-25 17:17:07 +08:00
linqingke 99480d26c6 add l2normalize gpu kernel. 2020-10-24 15:53:51 +08:00
danishnxt 06a9b4aa37 Commit1_TensorDot 
linting errors fix

comments cleanup

typo fix in doc

added more tests, fixed some formatting

changed expected dx values for linter

pylint const data fix
 2020-10-22 18:07:58 -04:00
mindspore-ci-bot 0d5e119fa4 !7483 Add GPU-UniformSampler and nn.UniformCandidateSampler 
Merge pull request !7483 from 34bunny/GPU-ucs
 2020-10-22 23:21:30 +08:00
mindspore-ci-bot 2c468a358a !7537 new gpu op for cbg: repeat_elements 
Merge pull request !7537 from Peilin/cbg-new-gpu-ops-repeat_elements
 2020-10-22 23:21:25 +08:00
Peilin Wang bd0b462691 new gpu op for cbg repeat_elements 
fixed ci

fixed ci

addressed comments
 2020-10-21 16:25:56 -04:00
TFbunny e18a78feb9 add GPU UniformSampler 2020-10-21 12:20:48 -04:00
mindspore-ci-bot 6cc37db833 !7482 roialign gpu operator output is zero 
Merge pull request !7482 from JonathanY/roialign_zero
 2020-10-21 23:42:06 +08:00
mindspore-ci-bot e24b50f559 !7548 Support elu and elugrad with dtype float and half on gpu 
Merge pull request !7548 from zhouyuanshen/master
 2020-10-21 19:11:38 +08:00
zhouyuanshen 2ab0b3d67a support ops elu and elugrad on gpu 2020-10-21 15:52:15 +08:00
mindspore-ci-bot fd8ebde400 !7545 GPU reshape add type 
Merge pull request !7545 from VectorSL/int64
 2020-10-21 14:19:11 +08:00
VectorSL 5c0c363c66 gpu reshepe add type 2020-10-21 10:47:57 +08:00
jonwe 4583bc1c57 roialign zero output 2020-10-20 11:08:56 -04:00
zhouyuanshen f49bd92b88 support asin and acos with dtype float on gpu 2020-10-20 11:21:46 +08:00
wanyiming e2b8810413 1D*ND 2020-10-12 17:21:07 +08:00
mindspore-ci-bot 21c5607fca !6971 cudnn inplace optimizer 
Merge pull request !6971 from chenweifeng/tensoradd_inplace
 2020-10-09 10:01:58 +08:00
wilfChen b420b6cda7 cudnn inplace optimizer 2020-09-30 16:18:16 +08:00
baihuawei fea928e976 remove CTCLossV2 2020-09-25 16:09:20 +08:00
wilfChen 13a3a6d117 test case seed 2020-09-23 14:11:20 +08:00
mindspore-ci-bot d60033c8db !6381 Add dtype float16 that erf and erfc should support 
Merge pull request !6381 from peixu_ren/custom_gpu
 2020-09-21 09:40:12 +08:00
wukesong f9a865fd42 add GPU operator 2020-09-19 12:13:06 +08:00
peixu_ren 8132e56417 Add dtype float16 that erf and erfc should support 2020-09-17 09:36:23 -04:00
mindspore-ci-bot 3f0ac45954 !6206 new add gpu ops sqrt_grad and rsqrt_grad. 
Merge pull request !6206 from linqingke/new_ops
 2020-09-17 20:40:26 +08:00
linqingke dda3176fca new add sqrt_grad and rsqrt_grad. 2020-09-17 17:13:25 +08:00
mindspore-ci-bot b79240fc3f !6367 fix shape bug 
Merge pull request !6367 from caozhou/fix_shape_bug
 2020-09-17 10:24:42 +08:00
caozhou 5010956773 fix weight_init bug 2020-09-17 09:23:34 +08:00
mindspore-ci-bot 71ab9e300b !6012 Support erf and erfc ant GPU backend 
Merge pull request !6012 from peixu_ren/custom_gpu
 2020-09-16 23:23:02 +08:00
mindspore-ci-bot af5ebcf1a9 !6232 fix gpu heterogeneous bug 
Merge pull request !6232 from baihuawei/embedding
 2020-09-16 16:49:39 +08:00
peixu_ren fdd2d8209f Support erf and erfc ant GPU backend 2020-09-15 22:14:32 -04:00
baihuawei 09a3f2ff5e fix GPU hete 2020-09-15 20:36:23 +08:00
mindspore-ci-bot eedbbb3649 !5958 Modify interface for function and remove duplicated def 
Merge pull request !5958 from lilei/modify_bug
 2020-09-10 21:22:32 +08:00
lilei 71adabd944 modify_bug 2020-09-09 18:20:32 +08:00
Peilin Wang f020e19636 add int32 support to greater gpu kernel 
fix ci
 2020-09-08 18:32:44 -04:00
mindspore-ci-bot 6fdb43d22d !5895 gpu maximum minimum absgrad kernel fix 
Merge pull request !5895 from chenweifeng/maximum-fix
 2020-09-08 20:44:43 +08:00
mindspore-ci-bot 98725bc865 !5790 [MS][GPU][CUDA] Dedicated new user facing Pad API kernel 
Merge pull request !5790 from danishnxt/GPU_three
 2020-09-08 20:40:50 +08:00
mindspore-ci-bot b717a686cf !5690 ROIAlign kernel memory leak 
Merge pull request !5690 from JonathanY/rcnn
 2020-09-08 20:32:25 +08:00
wilfChen 3b54e55223 gpu maximum & minimum kernel with fp16 input 2020-09-08 15:03:22 +08:00
wilfChen 6ebe132cd3 broadcast refactor 2020-09-07 16:57:50 +08:00
danish 273fc0071c New User facing Pad Kernel + ST + Allows for channel padding 
style fix

lint fixes

added check in NN layer for > 4 paddings, plus lint fix

fix python lint

lint fix

lint fix

updating to pytest asserts to improve testing

removed unnecc vars from test file fail checks
 2020-09-04 15:13:05 -04:00
mindspore-ci-bot fc79997de5 !5502 Mod SoftmaxCrossEntropyWithlogits 
Merge pull request !5502 from wanyiming/mod_SoftmaxCrossEntropyWithlogits
 2020-09-03 20:24:43 +08:00
wanyiming 0ec70068ae mod_SoftmaxCrossEntropyWithLogits 2020-09-03 17:33:20 +08:00
Jonathan Yan bbd19dbe43 roi align memory leak 2020-09-02 22:17:59 -04:00
mindspore-ci-bot 749979e7c4 !5458 NMS GPU OP Performance improvement 
Merge pull request !5458 from danishnxt/GPU_two
 2020-09-01 23:05:56 +08:00
mindspore-ci-bot 087212441a !5192 Add unit tests for scatternd 
Merge pull request !5192 from Peilin/scatternd-type-support
 2020-09-01 14:26:15 +08:00
danish 7d7fa760a0 reduce based nms final pass - speed improv 
refactored faster nms

refactored faster nms + typo fix

added box flipping choice

set choice to true for testing - yz

switching back

new test file
 2020-08-28 13:41:09 -04:00