Onnx2tf

- `Unsqueeze`
- Revised the method of determining the position of the axis of the Unsqueeze target.
- [alike_t_opset11_192x320.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12548247/alike_t_opset11_192x320.onnx.zip)

What's Changed
* [experimental] Revised the method of determining the position of the axis of the Unsqueeze target. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/487


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.13...1.16.14

- `Softmax`
- Official `tf.nn.softmax` doesn't support input logits with dimension > 5. This limit would fail onnx2tf correction_process_for_accuracy_errors() check, when tf subgraph contains softmax op with input dimension > 5.
- Before `tf.nn.softmax`, reshape the input logits to `[reduce_prod(shape[:axis]), shape[axis]`, `reduce_prod(shape[axis + 1:])]`.
after `tf.nn.softmax`, reshape back to original logits shape.
- Test code: https://github.com/PINTO0309/onnx2tf/blob/main/make_test_op/test_softmax_convert.py
- https://github.com/princeton-vl/RAFT-Stereo
- parameter replacement: [raftstereo-middlebury.zip](https://github.com/PINTO0309/onnx2tf/files/12546289/raftstereo-middlebury.zip)

What's Changed
* tf.nn.softmax doesn't support Dim(logits) > 5 by babiking in https://github.com/PINTO0309/onnx2tf/pull/486


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.12...1.16.13

- Improved overall model transformation processing stability.
- `ScatterND`
- Fixed to determine if the trailing index needs to be transposed and force transposition and retry if necessary.
- `Where`
- Improved NHWC information to be passed on to subsequent tensors.
- [yolox_nano_ti_lite_26p1_41p8.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12543304/yolox_nano_ti_lite_26p1_41p8.onnx.zip)

What's Changed
* Improved stability of `ScatterND` and `Where` conversions by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/485


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.11...1.16.12

- `Concat`
- Reduces post-concat accuracy degradation when all axes except batch size have the same value.
- Only supported when there are two input tensors, as the process is redundant.
- [vttrack.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12537164/vttrack.onnx.zip)

What's Changed
* Correction of missing judgment conditions for parameter replacement by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/484
* Reduces post-concat accuracy degradation when all axes except batch size have the same value by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/483


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.10...1.16.11

- `Concat`
- Reduce error frequency of `Concat` of two tensors containing constants.
- It is a simple correction and does not cover all patterns.
- `common_functions.py`
- Disable tensor swapping during `Sub`, `Div` and `Mod`.

What's Changed
* Reduce error frequency of `Concat` of two tensors containing constants and disable tensor swapping during `Sub`, `Div` and `Mod`. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/482


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.9...1.16.10

- `MatMul`
- Eliminates unnecessary narrowing of the search for the correct answer axis.
- Reduction of accuracy degradation due to transposition errors and overall time required for model conversion.
- [parseq_tiny.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12525877/parseq_tiny.onnx.zip)

What's Changed
* Eliminates unnecessary narrowing of the search for the correct answer axis by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/481


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.8...1.16.9