Main Feature:
1. Add OpenCV API and Numpy API Support
2. Protobuf move into MNN
3. Add more op for torchscript convert
4. Add recompute to speed up geometry compute
5. Add ModuleBasic Test
# 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 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
- 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
xiaying
Hui Shu
Turing311
Zhang
liqing