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
Help convert person-detection-0302 from openvino to onnx #123
I want to convert person-detection-0302 from openvino model to onnx, but I get error message and I truely do not know how to fit these error by reading 6-7 part in the README.
I have read 6-7 part in the README several times. But I'm still confused about how to do fix then. There are many error type information. For example , "dims must represent a vector, got shape [160,1] [Op:Fill]", "ValueError: Dimensions must be equal, but are 80 and 3", etc.
Can you elaborate on how you can fininsh replace.json file step by step for a new model?
It is better to teach a man to fish than to give him a fish
Issue Type
Feature Request
OS
Ubuntu
OS architecture
x86_64
Programming Language
Python
Framework
OpenVINO, ONNX
Download URL for ONNX / OpenVINO IR
https://storage.openvinotoolkit.org/repositories/open_model_zoo/2022.1/models_bin/3/person-detection-0302/FP32/person-detection-0302.xml
https://storage.openvinotoolkit.org/repositories/open_model_zoo/2022.1/models_bin/3/person-detection-0302/FP32/person-detection-0302.bin
Convert Script
H=544 W=920 MODEL=person-detection-0302
sudo openvino2tensorflow --model_path ${MODEL}.xml --output_saved_model --output_pb --output_no_quant_float32_tflite --output_dynamic_range_quant_tflite --output_weight_quant_tflite --output_float16_quant_tflite --output_integer_quant_tflite --string_formulas_for_normalization 'data / 255.0' --output_tfjs --output_coreml
Description
I want to convert person-detection-0302 from openvino model to onnx, but I get error message and I truely do not know how to fit these error by reading 6-7 part in the README.
I have read 6-7 part in the README several times. But I'm still confused about how to do fix then. There are many error type information. For example , "dims must represent a vector, got shape [160,1] [Op:Fill]", "ValueError: Dimensions must be equal, but are 80 and 3", etc.
Can you elaborate on how you can fininsh replace.json file step by step for a new model?
It is better to teach a man to fish than to give him a fish
Thank you
Relevant Log Output
Source code for simple inference testing code
No response