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
332
stars
40
forks
source link
Inconsistent model output after converting to tensorflow #109
Issue Type
Bug
OS
Ubuntu
OS architecture
x86_64
Programming Language
Python
Framework
TensorFlow
Download URL for ONNX / OpenVINO IR
https://drive.google.com/file/d/1RufrET4Tz20FQNlFaCXCVwwiChOCS7ef/view?usp=sharing
Convert Script
python3 openvino2tensorflow/openvino2tensorflow2.py --model_path ../../test_data/iresnet50_relu/model.xml --model_output_path ../../test_data/iresnet50_relu/ --output_saved_model --output_no_quant_float32_tflite
Description
The onnx to openvino works ok and I verified output. But tensorflow output not expected
Relevant Log Output
Source code for simple inference testing code