root
/
MNN
mirror of https://github.com/alibaba/MNN.git
1
0
Fork 0
Code Issues Actions 1 Packages Projects Releases Wiki Activity
948 Commits 19 Branches 107 Tags 393 MiB
Commit Graph

13 Commits

Author SHA1 Message Date
Hui Shu d6795ad031 Github release 1.1.0 2020-11-05 16:49:17 +08:00
tianbu.xsw 1efa0d469f add tuned LWS save 2020-07-23 10:26:24 +08:00
xiaying 255db932eb [MNN:Sync] Sync Internal Github 2020-07-04 01:21:30 +08:00
tianbu.xsw cf97427595 set queue_count to zero for every forward 2020-07-04 01:06:26 +08:00
tianbu.xsw b87ced740b revise cl_flush count 2020-07-04 01:06:26 +08:00
tianbu.xsw 2f93946c79 disable CL_QUEUE_PROFILING_ENABLE onExecute 2020-07-04 01:06:25 +08:00
Zhang 002ac367e4
Update 2019-12-27 22:16:57 +08:00
liqing e93e8dcbe8 0.2.1.5 
# integration
- add travis CI
- fix building parameters for python

# converter
- add half storage option for MNN converter
- fix op name lost in converter
- fix converter bug for print input output, identity remove output

# ops
- add quantized Convolution & Deconvolution support on OpenCL
- add more expression supports
- add DetectionPostProcess Op for TensorFlow Lite (ssd is supported directly now)
- add supports for LSTM & ELU for ONNX
- add support for Convolution that weights is not constant for ONNX
- fix Unary Op compile error on Linux
- fix Metal backend buffer reuse after resize
- fix Metal raw memory access after model releasing
- fix redundant transpose in Winograd generater
 2019-11-15 14:22:45 +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 487a0fbd0a beta 0.2.0.9 
- fix quantization tool compiling on Windows
- fix converter compiling on Windows
- fix eltwise optimization on Windows
- separate sse & avx for Windows
- add LeakyReLU support for TensorFlow
- fix reshape, const for TensorFlow
- fix dimension format error for ONNX ops
- optimize winograd, ReLU for OpenCL
- add fp16 availability & dimensions size check-up for OpenCL
- optimize GEMM for arm32
- fix ExpandDims shape calculation when inputs size == 1
 2019-09-01 19:25:26 +08:00
liqing db155b4d1d beta 0.2.0.2 
- CPU
  - add padding support
  - fix bug in permute when channel % 4 != 0
  - fix bug in exp with extreme value
- OpenCL
  - add protecting logics
- OpenGL
  - add protecting logics
  - support NCHW format in Squeeze and Reshape
- Converter
  - add ShuffleChannel support for Caffe
  - add Clip/Transpose/Unary/Pad supports for ONNX
 2019-07-02 18:01:08 +08:00
liqing 28a6f1a614 beta 0.1.1.2 
- fix register typo
- add input count in conv model
- add 5x5 winograd convolution for OpenCL
- edit condition to use half in OpenCL
- upgrade build.gradle
 2019-05-14 19:54:21 +08:00
liqing 5551108af8 beta 0.1.0 2019-04-19 20:50:09 +08:00