Onnx2tf

Latest version: v1.26.3

Safety actively analyzes 688634 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 8 of 85

1.20.8

- `If`
- Improved conversion stability of subgraphs of `If` operations.
- https://github.com/onnx/onnx-tensorflow/issues/1056
- https://github.com/PINTO0309/onnx2tf/releases/download/1.20.7/maskrcnn_resnet50_fpn.onnx


onnx2tf \
-i maskrcnn_resnet50_fpn.onnx \
-onimc boxes.55 onnx::Shape_3316 3315 onnx::Loop_3751

![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/c68e9cfe-154b-43c2-9c32-5741e885783a)

What's Changed
* Improved conversion stability of subgraphs of `If` operations. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/622


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.20.7...1.20.8

1.20.7

- Optimization of `torch.nn.PixelUnshuffle`.
- https://pytorch.org/docs/stable/generated/torch.nn.PixelUnshuffle.html
- https://www.tensorflow.org/api_docs/python/tf/nn/space_to_depth
- This implementation is inspired by the valuable knowledge of [AlexanderLutsenko / nobuco](https://github.com/AlexanderLutsenko/nobuco). Thank you very much.
- https://github.com/AlexanderLutsenko/nobuco?tab=readme-ov-file#implementation-mismatch-pick-your-poison
- Unlike PyTorch's method of replacing internal processing, a similar process is implemented from a frozen ONNX graph with the minimum number of operations required.

|ONNX|Before<br>tflite|After<br>tflite|
|:-:|:-:|:-:|
|![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/f39b4e8b-7fed-4ca5-af6a-e4e48f9e7adc)|![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/a9da56c5-b582-4c7a-aaf5-35f78d0b529c)|![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/b1d16985-614c-42dd-b040-49886b2da9b6)|

![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/36f4aa05-c8f2-47b2-8e0d-6c60ac8a11c6)

- Bug fix. `ReduceL1`, `ReduceL2`, `ReduceLogSum`, `ReduceLogSumExp`, `ReduceMax`, `ReduceMean`, `ReduceMin`, `ReduceProd`, `ReduceSum`, `ReduceSumSquare`

What's Changed
* Optimization of `torch.nn.PixelUnshuffle` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/621


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.20.6...1.20.7

1.20.6

- `MaxPool`, `AveragePool`
- Improved conversion stability when `H`, `W` and `D` of `MaxPool` and `AveragePool` contain undefined dimensions.
- **The accuracy of the converted model is not always accurate.**
- e.g. YOLOvNn dynamic inputs `[N, 3, H, W]`
- YOLOvN has been modified only to avoid a situation where the conversion aborts, although this is undoubtedly not good for the design of the model, as fixed parameters such as the number of classes are embedded in the backward `Split` operation with fixed values.
- Concatenating dimensions that have completely different meanings is also a major problem.
- Unless you replace the PyTorch implementation with `Slice`, you won't be able to do proper inferencing.
- ONNX
![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/cacbec18-2c57-4005-9567-37360ee3699f)
![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/363ff05e-fe56-4a44-a0a2-d712252edad4)
- TFLite
![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/6e337b7d-e709-4895-85fd-72be778c7d04)
![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/a05b5017-90b0-4fb5-9781-b9e6282b889e)

What's Changed
* Improved conversion stability when `H`, `W` and `D` of `MaxPool` and `AveragePool` contain undefined dimensions by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/620


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.20.5...1.20.6

1.20.5

- Distribute test data files to GitHub releases.
- `calibration_image_sample_data_20x128x128x3_float32.npy`
- https://github.com/PINTO0309/onnx2tf/releases/download/1.20.4/calibration_image_sample_data_20x128x128x3_float32.npy
- connection timeout: 1 sec
- read timeout: 5 sec
- The downstream speed of Wasabi Storage is very slow due to the rapid increase in the number of requests per day.
- Porting to Wasabi Storage if the download from GitHub releases times out.

1.20.4

- [experimental, Breaking change] `tf.keras` -> `tf_keras`
- `pip install tf-keras~=2.16`
- Because the API path for `tf.keras` is obsolete.

What's Changed
* [experimental, Breaking change] `tf.keras` -> `tf_keras` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/618


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.20.3...1.20.4

1.20.3

- `ReduceL1`, `ReduceL2`, `ReduceLogSum`, `ReduceLogSumExp`, `ReduceMax`, `ReduceMean`, `ReduceMin`, `ReduceProd`, `ReduceSum`, `ReduceSumSquare`
- Improve stability of `axes` conversion when an unknown dimension order other than NCHW is input to `ReduceXXX`.
- Automatically compensates for mistakes in `axes` dimensional transpositions.
- Error
![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/4d11a255-a417-49e8-841e-c0dde12cab9f)
![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/a26a4edd-bb47-4d0a-a0e6-793b940fb7d8)
- Fixed
![image](https://github.com/PINTO0309/onnx2tf/assets/33194443/593e0431-b8ed-41e7-80f8-2f25a35b1520)
- [Op Error about "Transpose" 616](https://github.com/PINTO0309/onnx2tf/issues/616)

What's Changed
* Improve stability of `axes` conversion when an unknown dimension order other than NCHW is input to `ReduceXXX` by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/617


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.20.2...1.20.3

Page 8 of 85

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.