Onnx2tf

- `GridSample`
- The inference speed was approximately 2.5 times faster.
- [1] use "broadcast" attribute and batched tf.gather_nd to generate bilinear interpolate items, to reduce intermediate tf ops.
- [2] use tf.clip_by_value to avoid conversion errors when H or W is 1

input size: N=32, C=16, H_in=32, W_in=64, H_out=48, W_out=54
4.0K grid_sample_reproduction.onnx
660K grid_sample_reproduction_float32.tflite

CPU inference elapsed runtime
pytorch: 0.0082 sec
onnx: 0.0255 sec
tflite: 0.0865 sec

- [Batched GridSample results in surprisingly large TFLite models 426](https://github.com/PINTO0309/onnx2tf/issues/426)
- `Reshape`
- Workaround to special patterns with wrong transposition when all axes except batch size have the same value.
- Examine which combination of axis configurations reduces the error in output values the most, and apply the transposition with the best performance.
- Input: [1, 20, 20, 20], Output: [1, 800, 10]
- [subgraph_model.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12520958/subgraph_model.onnx.zip)
- [Reshape Unmatched max abs error when doing ONNX and TF output value validation 478](https://github.com/PINTO0309/onnx2tf/issues/478)
- `ConvInteger`
- Miscellaneous implementation. Accuracy is likely to deteriorate.

What's Changed
* [experimental] `ConvInteger` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/477
* Reduction of transposition errors when all axis values except batch size are the same by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/479
* Feature/babiking/grid sampler by babiking in https://github.com/PINTO0309/onnx2tf/pull/480

New Contributors
* babiking made their first contribution in https://github.com/PINTO0309/onnx2tf/pull/480

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.7...1.16.8

- `LSTM`, `GRU`, `RNN`, `MatMul`
- Fixed a malfunction in the processing of RNNs in general, affected by a significant improvement in the tool's overall axis correction functionality.
- Bug fixes
- [crnn_lite_lstm.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506398/crnn_lite_lstm.onnx.zip)
- [LSTM.tanh.bidirectional_b10.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506400/LSTM.tanh.bidirectional_b10.onnx.zip)
- [torch_lstm.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506403/torch_lstm.onnx.zip)
- [RNN.bidirectional.one_layer.relu.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506407/RNN.bidirectional.one_layer.relu.onnx.zip)
- [RNN.bidirectional.one_layer.relu_b10.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506404/RNN.bidirectional.one_layer.relu_b10.onnx.zip)
- [GRU.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506417/GRU.onnx.zip)
- [gru_14_b1.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506418/gru_14_b1.onnx.zip)
- [gru_14_b2.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506419/gru_14_b2.onnx.zip)
- [lstm_undefined_dim.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12506423/lstm_undefined_dim.onnx.zip)
- [TypeError: Failed to convert object of type <class 'list'> to Tensor. 688](https://github.com/onnx/onnx-tensorflow/issues/688)

What's Changed
* Bug fixes in `LSTM`, `GRU`, `RNN`, and `MatMul` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/476


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.6...1.16.7

- `Concat`
- Attempts to force axis correction when the number of axes in the combined tensor do not exactly match.
- However, if more than 2 patterns of correct answers exist, give up the correction.
- This workaround is useful when automatic axis correction is practically difficult, such as when all tensors to be combined originate from `Transpose` or `Reshape`.
- Under very limited conditions, it is no longer necessary to correct the axis in JSON.
- [[D3Net] Clarification regarding a specific input dimension type 473](https://github.com/PINTO0309/onnx2tf/issues/473)

What's Changed
* Attempts to force axis correction when the number of axes in the combined tensor do not exactly match by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/475


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.5...1.16.6

- `Pad`
- Negative padding supported.
- Force substitution to `StridedSlice` since the TensorFlow runtime does not support padding of negative numbers.
- [d3net_dnn_double_44.onnx.zip](https://github.com/PINTO0309/onnx2tf/files/12505175/d3net_dnn_double_44.onnx.zip)
- onnx
- tflite
- results
- [[D3Net] Clarification regarding a specific input dimension type 473](https://github.com/PINTO0309/onnx2tf/issues/473)

What's Changed
* Negative padding supported by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/474


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.4...1.16.5

- `onnx2tf.py`, `common_functions.py`
- Significantly improved conversion stability by reducing the frequency of SWAPs due to lack of RAM for large models.
- Change the maximum number of recursions in Python to the maximum number of recursions. For Python to abort when the model structure is too large.
python
sys.setrecursionlimit(2147483647) C int maximum

- `InstanceNormalization`
- Workaround for inconsistent `C` position.
- Improved processing stability of `InstanceNormalization`.
- `Stable Diffusion v1.5`
- https://s3.ap-northeast-2.wasabisys.com/temp-models/onnx2tf_430/stable_diffusion_v1.5.tar.gz
- [[Stable Diffusion] Conversion error with stable diffusion model. 424](https://github.com/PINTO0309/onnx2tf/issues/424)
- [[TODO] Switch to a mode that performs inference in slow delay shape estimation mode during very large size transformations such as diffusion models 430](https://github.com/PINTO0309/onnx2tf/issues/430)

What's Changed
* Significantly improved conversion stability by reducing the frequency of SWAPs due to lack of RAM for large models, and improved processing stability of `InstanceNormalization`. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/472


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.3...1.16.4

- `Mul`, `Div`
- Prevents `Mul` -> `Div` patterns from creating redundant `Mul` -> `Mul` operation sets.
- This optimization improves the overall computational efficiency of the model just a little bit.
|onnx|tflite|
|:-:|:-:|
|||
- [[Demucs] Issue while converting demucs model from onnx to tflite in conv2d_transpose 470](https://github.com/PINTO0309/onnx2tf/issues/470)

What's Changed
* [experimental] Prevents `Mul` -> `Div` patterns from creating redundant `Mul` -> `Mul` operation sets. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/471


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.16.2...1.16.3