Onnx2tf

Latest version: v1.27.1

Safety actively analyzes 723200 Python packages for vulnerabilities to keep your Python projects secure.

Scan your dependencies

Page 70 of 86

1.1.17

- Support for `--replace_abs_to_pseudo_abs`

-rabs, --replace_abs_to_pseudo_abs
Replace Abs with a pseudo Abs.


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.16...1.1.17

1.1.16

- Supports model splitting.
- Interrupts model transformation at the specified output name and outputs the model partitioned into subgraphs.
- Support for `--output_names_to_interrupt_model_conversion` option.

-onimc OUTPUT_NAMES [OUTPUT_NAMES ...], \
--output_names_to_interrupt_model_conversion OUTPUT_NAMES [OUTPUT_NAMES ...]

Output names that interrupt model conversion.
Interrupts model transformation at the specified output name and outputs the
model partitioned into subgraphs.
e.g. --output_names_to_interrupt_model_conversion "output0" "output1" "output2"


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.15...1.1.16

1.1.15

- `InstanceNormalization`
- Improved handling of `GroupNormalization` (`InstanceNormalization`)
- For StableDiffusion [Hugging Face]
- vae_encoder.onnx

onnx2tf -i vae_encoder.onnx -prf replace.json


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.14...1.1.15

1.1.14

- Support for `--keep_nwc_or_nhwc_or_ndhwc_input_names` option
- If the input OP of ONNX before conversion is NHWC, use the -kt option.
- https://github.com/gmalivenko/onnx2keras/issues/151
- face_liveness.onnx - NHWC Input OP
![image](https://user-images.githubusercontent.com/33194443/200362419-9d9ab447-0ae0-4559-adb6-e30ade57ae1c.png)

-kt KEEP_NWC_OR_NHWC_OR_NDHWC_INPUT_NAMES [KEEP_NWC_OR_NHWC_OR_NDHWC_INPUT_NAMES ...], \
--keep_nwc_or_nhwc_or_ndhwc_input_names KEEP_NWC_OR_NHWC_OR_NDHWC_INPUT_NAMES \
[KEEP_NWC_OR_NHWC_OR_NDHWC_INPUT_NAMES ...]

Holds the NWC or NHWC or NDHWC of the input shape for the specified INPUT OP names.
If a nonexistent INPUT OP name is specified, it is ignored.
If the input OP name is the same as the input OP name specified
in the keep_ncw_or_nchw_or_ncdhw_input_names option, it is ignored.
Valid only for 3D, 4D and 5D input tensors.
e.g. --keep_nwc_or_nhwc_or_ndhwc_input_names "input0" "input1" "input2"

- sample

onnx2tf -i face_liveness.onnx -kt input -b 1


**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.13...1.1.14

1.1.13

- `BatchNormalization`
- Bug fixes
- https://github.com/PINTO0309/onnx2tf/issues/10

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.12...1.1.13

1.1.12

- Improved conversion efficiency of models not optimized with onnxsim
- human_segmentation_pphumanseg_2021oct.onnx
- https://github.com/opencv/opencv_zoo/tree/master/models/human_segmentation_pphumanseg
- [12 Conversion error in human_segmentation_pphumanseg_2021oct.onnx](https://github.com/PINTO0309/onnx2tf/issues/12)

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.11...1.1.12

Page 70 of 86

Links

Releases

Has known vulnerabilities

© 2025 Safety CLI Cybersecurity Inc. All Rights Reserved.