Onnx2tf

- `Split`
- Enhanced FlexSplitV generation suppression
- [model.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/11042500/model.onnx.zip)
- Before
- After
- [Load converted tensorflow model error 261](https://github.com/PINTO0309/onnx2tf/issues/261)

What's Changed
* Enhanced FlexSplitV generation suppression by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/262


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.7.34...1.7.35

- `Div`
- Fixed a type conversion bug in the OP optimization process for
1. `Div` -> `Mul`
2. `Mul` -> `Div`
3. `Div` -> `Div`
- CenterFusion
- [cf_fus.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/11037276/cf_fus.onnx.zip)



TypeError: Exception encountered when calling layer "tf.math.divide" (type TFOpLambda).

`x` and `y` must have the same dtype, got tf.float64 != tf.float32.

Call arguments received by layer "tf.math.divide" (type TFOpLambda):
• x=tf.Tensor(shape=(), dtype=float64)
• y=tf.Tensor(shape=(1, 112, 200, 1), dtype=float32)
• name='Div_33'


- Revert: [Merge two consecutive identical OPs into one 231](https://github.com/PINTO0309/onnx2tf/pull/231)

What's Changed
* Fix minor typo by kozistr in https://github.com/PINTO0309/onnx2tf/pull/259
* Fixed a type conversion bug in the OP optimization process for `Div` -> `Mul` and `Mul` -> `Div` and `Div` -> `Div` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/260

New Contributors
* kozistr made their first contribution in https://github.com/PINTO0309/onnx2tf/pull/259

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.7.33...1.7.34

- `Reshape`, `Expand`, `Unsqueeze`, `Squeeze`
- Elimination of unnecessary OP sequential processing
From:

[1,81,52,52] -> Reshape [81,52,52] -> Expand [1,81,52,52]
[1,81,52,52] -> Reshape [81,52,52] -> Unsqueeze [1,81,52,52]
[81,52,52] -> Reshape [1,81,52,52] -> Squeeze [81,52,52]

To:

[1,81,52,52]
[1,81,52,52]
[81,52,52]

- `Cast`
- Suppression of `FlexCast` generation

What's Changed
* 1.Elimination of unnecessary OP sequential processing 2.Suppression of FlexCast generation by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/257


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.7.32...1.7.33

- Fix onnxsim calls using `--no_large_tensor`

onnxsim xxx.onnx yyy.onnx --no_large_tensor 10MB


What's Changed
* Fix onnxsim calls using `--no_large_tensor` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/256


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.7.31...1.7.32

- `RandomNormalLike`, `RandomUniformLike`
- Improved stability of `RandomNormalLike` and `RandomUniformLike`
- `Split`
- Suppression of `FlexSplitV` generation
- https://github.com/isletennos/MMVC_Trainer
- `D_180000.onnx`
- `G_180000.onnx`


onnx2tf -i D_180000.onnx -ois specs:1,257,100 -cotof -cotoa 1e-1


- [Incorrect tensor shape when converting a model with "torch.randn_like" 253](https://github.com/PINTO0309/onnx2tf/issues/253)

What's Changed
* 1.Improved stability of `RandomNormalLike` and `RandomUniformLike`. 2.Suppression of `FlexSplitV` generation by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/255


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.7.30...1.7.31

- Significantly reduced RAM consumption during model conversion when the `-cotof` option is not specifie
- https://github.com/PINTO0309/PINTO_model_zoo/tree/main/352_MAXIM

What's Changed
* Significantly reduced RAM consumption during model conversion when the `-cotof` option is not specifie by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/254


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.7.29...1.7.30