root
/
MNN
mirror of https://github.com/alibaba/MNN.git
1
0
Fork 0
Code Issues Actions 1 Packages Projects Releases Wiki Activity
936 Commits 20 Branches 109 Tags 396 MiB
Commit Graph

444 Commits

Author SHA1 Message Date
xiaying 6a6ae6d181 Fix sync bug for Im2Col of vulkan 2021-02-24 15:54:38 +08:00
gaoruidong 9e886ba123 improvement(arm82): optimize relu op without slope in arm82 backend 2021-02-23 10:38:49 +08:00
xiaying 5e127496fc Sync Internal Github 2021-02-07 10:47:03 +08:00
jokerz0624 bfc91d2b87
fix(SSE): fix one bug of PRelu in function _SSE_MNNReluWithSlopeChannel (#1371) 2021-02-07 10:35:47 +08:00
jxt1234 b429750b14
Merge pull request #1364 from Wang-Zichen/patch-1 
Update OpenCLRunningUtils.cpp
 2021-02-03 10:03:58 +08:00
jxt1234 df360d01d5
Merge pull request #1365 from WillTao-RD/master 
fix compile error for win MSVC
 2021-02-03 10:03:31 +08:00
Joker 3a121b71ff improvement(arm82): accelerate data format converting between NC8HW8 and NCHW in armv82 2021-01-30 16:06:59 +08:00
taowei 602f6015af fix compile error for win MSVC 2021-01-29 11:35:13 +08:00
Wang-Zichen 4a1c7e51d3
Update OpenCLRunningUtils.cpp 2021-01-27 16:25:30 +08:00
xiaying d766c6d7c0 Fix bug for compute MatMul E=1 for multi-thread 2021-01-11 14:04:25 +08:00
xiaying aad7b7aed1 [MNN:Sync] Sync internal Gitlab 2021-01-08 14:36:59 +08:00
xiaying 5ce5b17c8d [PATCH 17/19] [MNN:Bugfix] Fix bug for unuseful copy of Arm82Backend 2021-01-08 14:16:25 +08:00
xiaying bf5fde426b [PATCH 15/19] [MNN:Refractor] Remove unuseful code for Tensor 2021-01-08 14:16:25 +08:00
xiaying 4b1a11d9dc [PATCH 14/19] [Arm82:Feature] Support All Binary of float for arm82 2021-01-08 14:16:25 +08:00
xiaying 1b7f7ece82 [PATCH 13/19] [Arm82:Feature] Support Prelu with slope count = 1 2021-01-08 14:16:25 +08:00
xiaying 2b69f05d87 [PATCH 12/19] [Arm82:Feature] Support Mul, min, max, sqd for Arm82Binary 2021-01-08 14:16:25 +08:00
xiaying 79eca24544 [PATCH 11/19] [Arm82:Bugfix] Fix bug for Arm82Eltwise for multi input 2021-01-08 14:16:24 +08:00
xiaying 7f94e02410 [PATCH 04/19] [Converter:Bugfix] Support group convolution for PB 2021-01-08 14:16:24 +08:00
xiaying 184fc75738 [PATCH 03/19] [MNN:Bugfix] Fix convert assert and crash for RNN model 2021-01-08 14:16:24 +08:00
xiaying 04530e55ba Fix bug for Arm82Backend's onCopyBuffer 2021-01-07 14:11:48 +08:00
xiaying 07b9a895ce Merge remote-tracking branch 'origin/master' into feature/sync 2021-01-06 16:44:01 +08:00
xiaying 2d1b129121 [MNN:Sync] Sync internal git 2021-01-06 16:29:37 +08:00
xiaying 8dfb7bd21e [PATCH 349/350] [MNN:Bugfix] Fix compile bug for ios Playground of arm82 2021-01-06 15:57:23 +08:00
xiaying aedc8f6a68 [PATCH 341/350] Add avx512 patch 2021-01-06 15:57:22 +08:00
xiaying 9213e99bbd [PATCH 339/350] fix cuda matmul/batchmatmul 2021-01-06 15:57:22 +08:00
xiaying 83f577fbfb [PATCH 335/350] [MNN:Bugfix] Fix bug for int8 sse not align 2021-01-06 15:57:22 +08:00
雁行 c83db435bc [PATCH 334/350] [MNNConverter:Bugfix] fix upsample scale dim bug 2021-01-06 15:57:22 +08:00
xiaying 2735396cb3 [PATCH 324/350] [Vulkan:Bugfix] Fix bug for mali sync error 2021-01-06 15:57:21 +08:00
xiaying 7800f8245e [PATCH 323/350] [Vulkan:Bugfix] Support width * heigh > image2d 2021-01-06 15:57:21 +08:00
Hui Shu 24322f4221 [PATCH 322/350] Fix opencl log messages 2021-01-06 15:57:21 +08:00
xiaying ca538cef7d [PATCH 320/350] use MNN_PRINT 2021-01-06 15:57:20 +08:00
xiaying 4cdd10401b [PATCH 319/350] close gather currently 2021-01-06 15:57:20 +08:00
xiaying ead1743c98 [PATCH 317/350] revert 2021-01-06 15:57:20 +08:00
xiaying 1b6744b00c [PATCH 316/350] bugfix 2021-01-06 15:57:20 +08:00
xiaying ed21d51e5a [PATCH 315/350] support trt gather & interp-bilinear plugin 2021-01-06 15:57:20 +08:00
xiaying 49b0544719 [PATCH 314/350] [MNN:Bugfix] Fix memory usage bug for OneDNNConvolution 2021-01-06 15:57:20 +08:00
gaoruidong 3ea7d98680 [PATCH 300/350] improvement(arm82): optimize arm82 raster op use multi-threads 2021-01-06 15:57:19 +08:00
雁行 23305bc8e0 [PATCH 291/350] [MNN::Bugfix] fix bug of not full dst copy fuse 2021-01-06 15:57:18 +08:00
xiaying 9517edf085 [PATCH 283/350] [MNN:Bugfix] Fix memory leak for Express and Vulkan 2021-01-06 15:57:17 +08:00
xiaying f258d6bd92 [PATCH 279/350] [MNN:Bugfix] Fix comiple bug for cross-compile of ARM 2021-01-06 15:57:17 +08:00
xiaying 0fe2b0dfee [PATCH 278/350] [MNN:Speed] Support OneDNN for MNN Convolution 2021-01-06 15:57:17 +08:00
弗人 e6697960f0 [PATCH 276/350] bugfix for topk neon compile 2021-01-06 15:57:17 +08:00
弗人 d3d34f16f1 [PATCH 275/350] [MNN:Bugfix] bugfix for topk neon compile 2021-01-06 15:57:16 +08:00
雁行 e8fff0b1b4 [PATCH 272/350] [MNN:Bugfix] fix zero stride expand 2021-01-06 15:57:16 +08:00
和彬 c328e8ff15 [PATCH 270/350] fix conv depthwise overflow bug 2021-01-06 15:57:16 +08:00
雁行 63acf0e8a9 [PATCH 269/350] [MNN:Bugfix] fix bug of Pool pads 2021-01-06 15:57:16 +08:00
houjiang ef942629ec [PATCH 257/350] [MNN::Bugfix] Fix avx load statments. 2021-01-06 15:57:15 +08:00
xiaying 155fc9d849 [PATCH 249/350] cuda interp bugfix 2021-01-06 15:57:14 +08:00
xiaying a29158d0d9 [PATCH 248/350] [TRT:Bugfix] Fix bug for TRTMatMul for 3 inputs 2021-01-06 15:57:14 +08:00
houjiang e3262eac4c [PATCH 243/350] [MNN::Refine] Refine code style. 2021-01-06 15:57:14 +08:00