Onnx2tf

- API changed
- The input and output quantization types can now be specified with separate, different parameters for input and output.
- Abolition
- `input_output_quant_dtype`
- Addition
- `input_quant_dtype`
- `output_quant_dtype`
- `Conv`
- Supports parameter substitution for post-processing of `Conv`.
- replace_conv.json
json
{
"format_version": 1,
"operations": [
{
"op_name": "wa/conv/Conv",
"param_target": "outputs",
"param_name": "output",
"post_process_transpose_perm": [0,3,1,2]
}
]
}

- test

onnx2tf -i model_conv.onnx -kat input -prf replace_conv.json

- `Mul`
- Improved conversion stability of `Mul`.

- [Error by broadcasting in tf.math.Multiply Operation 698](https://github.com/PINTO0309/onnx2tf/issues/698)
- [Add transposition to the tflite model 700](https://github.com/PINTO0309/onnx2tf/issues/700)
- [README corrections due to API changes (I'll get serious from tomorrow) 702](https://github.com/PINTO0309/onnx2tf/issues/702)

What's Changed
* Input and output quantization chosen separately by marcoschepis in https://github.com/PINTO0309/onnx2tf/pull/701
* Updated README.md by marcoschepis in https://github.com/PINTO0309/onnx2tf/pull/703
* Supports parameter substitution for post-processing of `Conv` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/704
* Improved conversion stability of `Mul` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/705

New Contributors
* marcoschepis made their first contribution in https://github.com/PINTO0309/onnx2tf/pull/701

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.25.15...1.26.0

- `Mul`, `Add`
- Fixed to force switch between `X` and `Y` when X: `np.ndarray`, Y: `Tensor`

onnx2tf -i 1005_s0_nonar_text_decoder.onnx -cotof

- [Error by broadcasting in tf.math.Multiply Operation 698](https://github.com/PINTO0309/onnx2tf/issues/698)

What's Changed
* Fixed to force switch between `X` and `Y` when X: `np.ndarray`, Y: `Tensor` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/699


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.25.14...1.25.15

- `ArgMin`
- Dealing with garbage-like broken structures in ONNX (`ArgMin`) 695
- [[YOLOv7] None in graph_node_input.shape 694](https://github.com/PINTO0309/onnx2tf/issues/694)

What's Changed
* Dealing with garbage-like broken structures in ONNX (ArgMin) 695 by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/696


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.25.13...1.25.14

- `ArgMax`, `Faltten`
- Dealing with garbage-like broken structures in ONNX.
- [[YOLOv7] None in graph_node_input.shape 694](https://github.com/PINTO0309/onnx2tf/issues/694)

What's Changed
* Dealing with garbage-like broken structures in ONNX by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/695


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.25.12...1.25.13

- `Flatten`
- Improved handling when `axis` attribute is not defined and the batch size of the first dimension is undefined.
- ONNX
bash
wget https://github.com/PINTO0309/onnx2tf/releases/download/0.0.2/resnet18-v1-7.onnx
onnx2tf -i resnet18-v1-7.onnx

ls -lh saved_model/

assets
fingerprint.pb
resnet18-v1-7_float16.tflite
resnet18-v1-7_float32.tflite
saved_model.pb
variables

TF_CPP_MIN_LOG_LEVEL=3 \
saved_model_cli show \
--dir saved_model \
--signature_def serving_default \
--tag_set serve

The given SavedModel SignatureDef contains the following input(s):
inputs['data'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 224, 224, 3)
name: serving_default_data:0
The given SavedModel SignatureDef contains the following output(s):
outputs['output_0'] tensor_info:
dtype: DT_FLOAT
shape: (-1, 1000)
name: PartitionedCall:0
Method name is: tensorflow/serving/predict

- TFLite

What's Changed
* Improved handling when `axis` attribute is not defined and the batch size of the first dimension is undefined. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/692


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.25.11...1.25.12

- `BatchNormalization`
- Improved the conversion stability of `BatchNormalization`.

What's Changed
* Improved the conversion stability of `BatchNormalization`. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/690


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.25.10...1.25.11