[New feature] ONNC supports new operators Clip, Max, Min, ReduceMean, and PRelu.
[New feature] ONNC can compile models into C files.
[New feature] ONNC provides a library containing function implementation for 116 neural network operators defined in ONNX rel-1.3.0 specification.
[New feature] The ONNC library can call Intel MKLDNN library for accelerating the computation of convolution and Gemm (matrix multiplication) on Intel CPU.
Supported ONNX Operators
- Clip new
- Max new
- Min new
- PRelu new
- ReduceMean new
- Transpose (use in ShuffleNet)