Add the ability to extrapolate Transpose and Replace to weights_replacement_config

PINTO0309 / openvino2tensorflow

This script converts the ONNX/OpenVINO IR model to Tensorflow's saved_model, tflite, h5, tfjs, tftrt(TensorRT), CoreML, EdgeTPU, ONNX and pb. PyTorch (NCHW) -> ONNX (NCHW) -> OpenVINO (NCHW) -> openvino2tensorflow -> Tensorflow/Keras (NHWC/NCHW) -> TFLite (NHWC/NCHW). And the conversion from .pb to saved_model and from saved_model to .pb and from .pb to .tflite and saved_model to .tflite and saved_model to onnx. Support for building environments with Docker. It is possible to directly access the host PC GUI and the camera to verify the operation. NVIDIA GPU (dGPU) support. Intel iHD GPU (iGPU) support.

MIT License

334 stars 40 forks source link

1. OS you are using e.g. Ubuntu 20.04, WIndows10, etc: Ubuntu 20.04

2. OS Architecture e.g. x86_64, armv7l, aarch64, etc: any

3. Version of OpenVINO e.g. 2021.2.185, etc: 2021.4

4. Version of TensorFlow e.g. v2.4.1, tf-nightly==2.5.0.dev20210128, etc: v2.6.0

5. Version of TensorRT e.g. TensorRT6.0 GA, etc: 8.0

13. Issue Details

Add the ability to extrapolate Transpose and Replace to weights_replacement_config.

Specify the layer id and port number of the previous and next connection target.
Transposition and shape specification
Make it selectable whether to insert in front of or behind the layer

PINTO0309 / openvino2tensorflow