Onnx2tf

Latest version: v1.22.3

Safety actively analyzes 633398 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 1 of 80

2.16.1

- Keras 3.0 will be the default Keras version. You may need to update your script to use Keras 3.0.
- Please refer to the new Keras documentation for Keras 3.0 (https://keras.io/keras_3).
- This pull request is to experimentally verify the upgrade to `TensorFlow==2.16.1`.

What's Changed
* [experimental] tensorflow==2.16.1, Keras 3.0 by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/609


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.19.16...1.20.0

2.13.0rc0

- [[TODO] Verification of operation when upgrading to TensorFlow v1.13.0 348](https://github.com/PINTO0309/onnx2tf/issues/348)

What's Changed
* TF v2.12.0 -> TF v2.13.0-rc0 by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/363


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.11.11...1.12.0

2.12.0rc0

-okv3, --output_keras_v3: Optional[bool]
Output model in Keras (keras_v3) format.

![image](https://user-images.githubusercontent.com/33194443/218926250-5f3b6ecc-c05d-462f-8ceb-8b53c2feb335.png)
![image](https://user-images.githubusercontent.com/33194443/218926343-e750ef5b-61ba-40ca-86c9-a17f9d3561be.png)

What's Changed
* [Experimental / WIP] Generate a miniscule model for each OP only, retain the results of test inference, and propagate to all OPs. STEP.1,2 by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/184
* TF v2.12.0rc0 - 1. `Transpose` now supports 6D tensors. 2. Support for `Atan2`. by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/189
* Support for `keras_v3` format by PINTO0309 in https://github.com/PINTO0309/onnx2tf/pull/190


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.6.7...1.7.0

1.22.3

What's Changed
* Fix multi-platform image push by ysohma in https://github.com/PINTO0309/onnx2tf/pull/639


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.22.0...1.22.3

1.22.0

- `Docker Image` (arm64, Apple Silicon Mac)
Distributed docker image is not compatible with ARM environments such as Apple Silicon Mac.
Although Docker offers emulation for x86/amd64 environments, onnx2tf within this emulation mode results in an error, as shown below:

bash
$ root39d07181ce27:/ onnx2tf -h
> Illegal instruction

This issue is suspected to be caused by the dependency of PyPI TensorFlow on x86-specific instruction sets.

To address this,
I've augmented the release process with GitHub Actions to include building and pushing Docker images for Arm64 architecture. This make it possible to execute onnx2tf with docker on Arm64 hosts.

- Update Dockerfile
- Extra dependencies (pkg-config and libhdf5-dev) are required to install h5py for arm64 docker build.
- Add Arm64 build and push in GitHub Actions
- Referenced the following URL for guidance: https://docs.docker.com/build/ci/github-actions/multi-platform/

What's Changed
* Add arm64 docker image by ysohma in https://github.com/PINTO0309/onnx2tf/pull/636


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.21.6...1.22.0

1.21.6

- `MatMulInteger`
Currently, MatMulInteger is implemented as tf matmul with int32 inputs/outputs, which leads to generation of Flex(Batch)MatMul ops.

When `-rtpo MatMulInteger` is specified, inputs of MatMulInteger are casted to float32 instead, allowing the node to be converted to the builtin FullyConnected or BatchMatMul ops.

ONNX input:
![image](https://github.com/PINTO0309/onnx2tf/assets/25856103/25c91c62-1b3e-4ca4-b541-1cd59db7f39b)

Before:
![Screenshot_20240517_202911](https://github.com/PINTO0309/onnx2tf/assets/25856103/dbb7386f-f650-4803-873e-d1517bde445e)

After:
![image](https://github.com/PINTO0309/onnx2tf/assets/25856103/caaf48b0-8385-47c0-a134-5e21d0644df0)

What's Changed
* support suppressing flex ops for MatMulInteger by DDoSolitary in https://github.com/PINTO0309/onnx2tf/pull/635


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.21.5...1.21.6

Page 1 of 80

Links

Releases

Has known vulnerabilities

© 2024 Safety CLI Cybersecurity Inc. All Rights Reserved.