6 - Support new command line interface
9 - CPU backend supports 7 more operations
10 - CPU backend supports 9 more quant8 operations
14 ### New command line interface for user interface consistancy
16 - `one-import-bcq` : import BCQ(Binary coding quantized) TensorFlow model
17 - Commands now support `--version` option to show version number
21 - Experimental support for TensorFlow 2.x has updated to 2.3.0 (TensorFlow 1.3.2 is our official support version)
22 - Support more operators in luci-interpreter
23 - Enhancing one-quantizer
29 - Rename `nnfw_dev.h` to `nnfw_experimental.h`
33 - Remove copies for model input/outputs whenever possible
35 ### Support CPU backend operation
37 - BatchToSpaceND, L2Normalization, ReLU6, ResizeBilinear, SpaceToDepth, SplitV, StatelessRandomUniform
39 ### Support CPU backend quant8 operation
41 - BatchToSpaceND, L2Normalization, Pad, PadV2, ResizeBilinear, Slice, Quantize, SpaceToDepth, Sum