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

997 Commits

Author SHA1 Message Date
xiaying c2a2a24e8e [IOS:Bugfix] Fix compile bug for IOS Demo 2021-04-21 15:01:56 +08:00
jxt1234 3dada34c16
Merge pull request #1454 from alibaba/feature/sync 
Feature/sync
 2021-04-16 15:43:14 +08:00
xiaying 3c4ba7c595 [MNN:Sync] Sync internal gitlab 2021-04-16 14:50:43 +08:00
Hui Shu 0753ea0d60 [PATCH 34/36] Disable bitcode 2021-04-16 14:29:39 +08:00
xiaying e0d8221739 [PATCH 31/36] [Train:Bugfix] Fix compile bug for gcc4.8 2021-04-16 14:29:38 +08:00
xiaying 5947b90a03 [PATCH 30/36] [MNN:Refractor] Move NN to train folder 2021-04-16 14:29:38 +08:00
Hui Shu 7c46523979 [PATCH 28/36] Fix error message 2021-04-16 14:29:38 +08:00
tianbu 9f693b108e [PATCH 27/36] [CUDA Feature] bugfix for multi-input depthwiseconv 2021-04-16 14:29:38 +08:00
tianbu.xsw 0c3cb3c689 [PATCH 26/36] [OpenCL Feature] bugfix for resizeSession 2021-04-16 14:29:38 +08:00
弗人 4cd958d1d1 [PATCH 25/36] add save code 2021-04-16 14:29:38 +08:00
弗人 18ba3f558f [PATCH 24/36] move ConvertToFullQuant out of Expr.cpp 2021-04-16 14:29:38 +08:00
xiaying 3e06cabf38 [PATCH 22/36] Fix bug for CPUScatterNd crash for invalid input 2021-04-16 14:29:37 +08:00
tianbu.xsw 089253a9a0 [PATCH 21/36] delete deconv_2d_buf kernel 2021-04-16 14:29:37 +08:00
tianbu.xsw 1c003f8af8 [PATCH 20/36] merge image and buffer kernel 2021-04-16 14:29:37 +08:00
弗人 18e6a7fb1f [PATCH 19/36] [Python:Bugfix] fix bug for python train quant 2021-04-16 14:29:37 +08:00
tianbu.xsw 64ab57c5f4 [PATCH 18/36] delete unused log 2021-04-16 14:29:37 +08:00
tianbu.xsw 7422afe0ff [PATCH 17/36] add MNN_OPENCL_BUFFER_CLOSED macro 2021-04-16 14:29:37 +08:00
tianbu.xsw 7a314796e3 [PATCH 16/36] reback some revises 2021-04-16 14:29:37 +08:00
tianbu.xsw d9786e5351 [PATCH 15/36] [OpenCL Feature] support deconvolution for OpenCL Buffer 2021-04-16 14:29:36 +08:00
弗人 9621a1f8ad [PATCH 14/36] bug fix for old type 4 models 2021-04-16 14:29:36 +08:00
弗人 2fdfdcb9c3 [PATCH 13/36] revert flatbuffers::NumToString 2021-04-16 14:29:36 +08:00
弗人 a3bbcd01b9 [PATCH 12/36] [Train:Featue] support full quant for train quant, encode when save 2021-04-16 14:29:36 +08:00
弗人 5aae654351 [PATCH 09/36] remove useless code 2021-04-16 14:29:36 +08:00
弗人 95bcb842a0 [PATCH 08/36] [Train:Feature:Bugfix] train quant support full quant 2021-04-16 14:29:36 +08:00
xiaying 0b84532a52 Support TF's FusedBatchNormV3 for is_training = true 2021-04-16 14:19:27 +08:00
xiaying 083725513d Fix bug for crash when the command will change size 2021-04-15 19:37:07 +08:00
xiaying 2442e57b64 Support fuse for HardSwish 2021-04-15 13:59:13 +08:00
jxt1234 e5dcf6c930
Merge pull request #1415 from jokerz0624/master 
fix(HiAI): unload model before setting dynameic inputs
 2021-04-14 11:43:36 +08:00
jxt1234 8065733681
Merge pull request #1446 from MambaWong/master 
Remove unnecessary '+'
 2021-04-14 11:36:11 +08:00
jason_w 29a7128bdb
Remove unnecessary '+' 
Remove unnecessary '+'
 2021-04-13 08:12:38 +08:00
xiaying 3a21e5d7da [Converter:Feature] Add Onnx::Not and Onnx::GatherElement 2021-04-11 09:46:20 +08:00
xiaying c797dca85c [Converter:Bugfix] Fix bug for OnnxEinsum for dim size not correct 2021-04-11 09:43:52 +08:00
jxt1234 2e17ca8669
Merge pull request #1437 from alibaba/feature/sync 
[MNN:Sync] Sync internal Gitlab ，CPU FP16 / BF16 Opt , TensorArray bugfix, Full-Quantization
 2021-04-08 18:48:43 +08:00
xiaying d91fc63976 [MNN:Sync] Sync internal Gitlab 2021-04-08 15:34:23 +08:00
xiaying 7af23d29f4 [MNN:Bugfix] Fix compile bug 2021-04-01 13:57:02 +08:00
jxt1234 48192633d1
Merge pull request #1423 from ysh329/patch-1 
[BugFix] Fix typo in code comment for opencl
 2021-03-31 12:52:23 +08:00
xiaying 1181033ca4 Fix onnx scatternd convert bug 2021-03-31 11:53:41 +08:00
ysh329 588515c6f3
[BugFix] Fix typo in code comment 
Fix typo in code comment
 2021-03-28 17:32:33 +08:00
Joker 00aca57dff fix(HiAI): unload model before setting dynameic inputs 2021-03-22 11:24:52 +08:00
xiaying 5ed9ee8f8d [OpenCL:Bugfix] Sync Interpreter.hpp 2021-03-15 15:52:16 +08:00
xiaying 4cacb72e0e [OpenCL:Bugfix] Add Eltwise-Sub for opencl 2021-03-14 19:16:39 +08:00
jxt1234 fa5b3cc4de
Merge pull request #1406 from alibaba/feature/syncopencl 
[MNN:Sync] Sync opencl from Internal Gitlab, support Buffer and more auto-turning mode
 2021-03-13 11:54:32 +08:00
jxt1234 99bc944cd3
Merge pull request #1403 from jokerz0624/fix_npu_cmake 
improvement(HiAI): update cmake of HiAI backend to support it when MNN_SEP_BUILD=true
 2021-03-13 11:04:05 +08:00
jxt1234 8877e74e82
Merge pull request #1402 from jokerz0624/fix_hiai_upsample 
improvement(HiAI): use ResizeBilinearV2 to support halfPixelCenter in Interp of HiAI backend
 2021-03-13 11:01:23 +08:00
xiaying 787a34aec5 [MNN:Sync] Sync opencl from Internal Gitlab, support Buffer and more 
auto-turning mode
 2021-03-12 18:43:38 +08:00
Joker 0461946e97 improvement(HiAI): Interp of HiAI backend support more halfPixelCenters 2021-03-12 12:25:22 +08:00
Joker 21127cb907 improvement(HiAI): update cmake of HiAI backend to support it when MNN_SEP_BUILD=true 2021-03-11 16:36:22 +08:00
Joker ad90923c72 fix(HiAI): replace ResizeBilinear with ResizeBilinearV2 to support halfPixelCenter in Interp of HiAI backend 2021-03-09 17:08:48 +08:00
jokerz0624 0dd397a228
Merge pull request #5 from alibaba/master 
merge MNN
 2021-03-09 16:59:18 +08:00
xiaying 1c4eded014 [MNN:Bugfix] Fix bug for CPUPool for w, h < kernelSize and pad 2021-03-04 22:46:06 +08:00