# 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
- 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
- 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
- add NaN check-up
- add quantification support for ScaleAdd Op
- add binary to eltwise optimization
- add console logs for quantization tool
- better document for quantization tool
- replace redundant dimension flags with dimension format
- optimize performance of TensorFlow Lite Quantized Convolution
- fix axis support for ONNX softmax
- fix get performance compile error on Windows
- fix bugs in quantization
- add evaluating tool for quantization
- add ADMM support in quantization
- fix lock in thread pool
- fix fusing for deconv
- fix reshape converting from ONNX to MNN
- turn off blob size checking by default
- 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
- update resources and docs
- unite tensor's width/height/channel/batch getter
- optimize several ops
- fix compile warnings and errors on Ubantu
- some other bug fixes
Zhang
liqing
如幻