Onnx2tf

Latest version: v1.27.1

Safety actively analyzes 723685 Python packages for vulnerabilities to keep your Python projects secure.

Page 72 of 86

1.1.5

- Support for `QLinearMatMul`

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.4...1.1.5

1.1.4

- `Conv`
- Bug fixes
- `QuantizeLinear`
- Bug fixes
- Support for `DequantizeLinear`

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.3...1.1.4

1.1.3

- Improved `FusedArgMax` processing efficiency
![image](https://user-images.githubusercontent.com/33194443/199656687-c3eba15e-9ae3-48e6-8a23-c718d2725c15.png)

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.2...1.1.3

1.1.2

- Improved processing by considering data resizing in the INT8 calibration process

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.1...1.1.2

1.1.1

- Support for `INT8 Quantization with INT16 activation`
- Support for `Full INT8 Quantization with INT16 activation`

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.1.0...1.1.1

1.1.0

- Support for Integer Quantization, Full Integer Quantization, Dynamic Range Quantization
- Add `--output_integer_quantized_tflite` option
- Add `--quant_type {per-channel,per-tensor}` option
- Add `--quant_calib_input_op_name_np_data_path INPUT_NAME NUMPY_FILE_PATH MEAN STD` option
- Add `--input_output_quant_dtype {int8,uint8}` option

**Full Changelog**: https://github.com/PINTO0309/onnx2tf/compare/1.0.49...1.1.0

Page 72 of 86

Releases

Has known vulnerabilities

Previous Next

Onnx2tf

Page 72 of 86

1.1.5

1.1.4

1.1.3

1.1.2

1.1.1

1.1.0

Page 72 of 86

Links

Releases