Onnx2tf

- Support for `MatMulInteger`

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.10...1.1.11

- Added `PReLU` optimization option
- Converting a model with this option will decompose the PReLU into primitive layers.
- This is effective when hardware accelerators are optimized for primitive layers.

-rpr, --replace_prelu_to_pseudo_prelu
Replace PReLU with a pseudo PReLU.

 

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.9...1.1.10

- Support for `QLinearConcat`
- `QLinearConv`
- Bug fixes
- https://github.com/PINTO0309/onnx2tf/releases/download/1.1.9/license_plate_detection_lpd_yunet_2022may-int8-quantized.onnx

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.8...1.1.9

- Support for `QLinearLeakyRelu`, `QLinearSigmoid`, `QLinearSoftmax`

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.7...1.1.8

- [10 [Query][tflite]The tool or cmdline to support NCHW between NHWC](https://github.com/PINTO0309/onnx2tf/issues/10)
- Support for `QLinearConv`, `QLinearMul`, `QLinearAdd`
- `Flatten`
- bug fixes
- `QLinearMatMul`
- bug fixes

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.6...1.1.7

- `Flatten`
- Added `Flatten` transposition process, transposition behavior similar to `Reshape`.
- Just before the `Flatten` process, a forced inversion to NCHW format is applied.
- Improved `replace.json` to be unnecessary only in some situations.

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.5...1.1.6