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.
File Explorer
Download Latest Version (.zip)- config.yml
- issue_template.yml
- codeql-analysis.yml
- python-publish.yml
- FUNDING.yml
- ir_weight_extractor.py
- openvino2tensorflow.py
- pb_to_saved_model.py
- pb_to_tflite.py
- saved_model_to_pb.py
- saved_model_to_tflite.py
- view_npy.py
- calibration_data_img_sample.npy
- ir_weight_extractor
- openvino2tensorflow
- pb_to_saved_model
- pb_to_tflite
- saved_model_to_pb
- saved_model_to_tflite
- view_npy
- 1125.npy
- .dockerignore
- .gitignore
- bashrc
- Dockerfile
- Dockerfile.base
- LICENSE
- README.md
- setup.py
- tf_to_openvino_reverse_check.sh
- weight_replacement_config_sample.json
# Installation Guide
git clone https://github.com/PINTO0309/openvino2tensorflow
Downloads the entire project code from GitHub to your computer.
cd openvino2tensorflow
Moves into the project folder you just downloaded.
2. Docker
Easy Recommended- Git Needed to download the project code from GitHub.
- Docker Desktop Needed to build and run containers. Install it and keep it running in the background.
$ docker pull ghcr.io/pinto0309/openvino2tensorflow:latest
Type this command into your terminal and run it.
$ docker build --no-cache -t ghcr.io/pinto0309/openvino2tensorflow:latest .
Builds a runnable image based on the Dockerfile.
$ docker run -it --rm \
Runs the built image as an actual container.
docker run -it --rm \
Runs the built image as an actual container.
docker run --gpus all -it --rm \
Runs the built image as an actual container.
Pulled directly from this repo's README.
3. Python
Easy$ pip3 install --user --upgrade openvino2tensorflow
Installs the Python libraries listed in requirements.txt (or similar).
$ pip3 install --user --upgrade git+https://github.com/PINTO0309/openvino2tensorflow
Installs the Python libraries listed in requirements.txt (or similar).
Pulled directly from this repo's README.