root
/
MNN
mirror of https://github.com/alibaba/MNN.git
1
0
Fork 0
Code Issues Actions 6 Packages Projects Releases Wiki Activity
1,048 Commits 20 Branches 107 Tags 393 MiB
Commit Graph

16 Commits

Author SHA1 Message Date
hush-alibaba 58545d6ca1
Synchronize internal github for version 1.2.0 (#1518) 2021-06-11 17:17:13 +08:00
xiaying d91fc63976 [MNN:Sync] Sync internal Gitlab 2021-04-08 15:34:23 +08:00
xiaying 7f94e02410 [PATCH 04/19] [Converter:Bugfix] Support group convolution for PB 2021-01-08 14:16:24 +08:00
xiaying 2d1b129121 [MNN:Sync] Sync internal git 2021-01-06 16:29:37 +08:00
xiaying 0fe2b0dfee [PATCH 278/350] [MNN:Speed] Support OneDNN for MNN Convolution 2021-01-06 15:57:17 +08:00
houjiang d7d7ece8f4 [PATCH 214/350] [MNN::Refine] Rearrange weights for 1x1 and generic convolution. 2021-01-06 15:57:12 +08:00
houjiang 5cb6071469 [PATCH 203/350] [MNN::Feature] Rearrange weights. 2021-01-06 15:57:11 +08:00
xiaying 255db932eb [MNN:Sync] Sync Internal Github 2020-07-04 01:21:30 +08:00
xiaying 49ca95571d Revert "[MNN:Speed] Optmize winograd convolution" 
This reverts commit 9e34b9a856ccf9d2a81bc9387a1c7dfbc6a12e5d.
 2020-07-04 01:06:21 +08:00
xiaying e708cff674 Optmize winograd convolution 2020-07-04 01:06:20 +08:00
xiaying c7051d367c Temply forbid not im2col case for 1x1 conv 2020-07-04 01:06:19 +08:00
xiaying 010913aaaa [PATCH 070/160] [MNN:Refract] Seperate the load of quan and half to ConvolutionCommon 2020-03-22 19:02:06 +08:00
Zhang 002ac367e4
Update 2019-12-27 22:16:57 +08:00
liqing 73ad3413cc - dynamic computation graph (beta) 
- add supports (/express)
	- add tests
	- add benchmarks with it (/benchmark/exprModels)
- Python
	- MNN engine and tools were submitted to pip
	- available on Windows/macOS/Linux
- Engine/Converter
	- add supports for each op benchmarking
	- refactor optimizer by separating steps
- CPU
	- add supports for Conv3D, Pool3D, ELU, ReverseSequence
	- fix ArgMax, Permute, Scale, BinaryOp, Slice, SliceTf
- OpenCL
	- add half transform in CPU
	- add broadcast supports for binary
	- optimize Conv2D, Reshape, Eltwise, Gemm, etc.
- OpenGL
	- add sub, real div supports for binary
	- add supports for unary
	- optimize Conv2D, Reshape
- Vulkan
	- add max supports for eltwise
- Metal
	- fix metallib missing problem
- Train/Quantization
	- use express to refactor training codes
 2019-09-26 21:02:07 +08:00
liqing 6a4213f7dc beta 0.2.0.0 
- replace FreeImage with stb_image
- warn unicode error in Windows compiling
- separate clang/gcc build script for android
- add default values in fbs
- optimize CPU conv / conv depthwise / deconv / deconv depthwise / lstm / sigmoid
- add sub support in eltwise
- add reciprocal / log1p / log in unary
- add zero like / select / set diff 1d
- add batch support for permute
- add training codes
- fix metal error in dynamic separate storage type handling
 2019-06-17 20:10:35 +08:00
liqing 5551108af8 beta 0.1.0 2019-04-19 20:50:09 +08:00