search

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

GroupConvolutionBackpropData implementation #97

Open PINTO0309 opened 2 years ago

PINTO0309 commented 2 years ago

Issue Type

Feature Request

OS

Other

OS architecture

Other

Programming Language

Python

Framework

OpenVINO, ONNX, TensorFlow, TensorFlowLite

Download URL for ONNX / OpenVINO IR

https://github.com/ZZiyin/UIE-WD_Code

Convert Script

docker run --gpus all -it --rm \
-v `pwd`:/home/user/workdir \
ghcr.io/pinto0309/openvino2tensorflow:latest

MODEL=uie_wd
H=192
W=320
$INTEL_OPENVINO_DIR/deployment_tools/model_optimizer/mo.py \
--input_model ${MODEL}_${H}x${W}.onnx \
--data_type FP32 \
--output_dir ${MODEL}_${H}x${W}/openvino/FP32 \
--model_name ${MODEL}_${H}x${W}
$INTEL_OPENVINO_DIR/deployment_tools/model_optimizer/mo.py \
--input_model ${MODEL}_${H}x${W}.onnx \
--data_type FP16 \
--output_dir ${MODEL}_${H}x${W}/openvino/FP16 \
--model_name ${MODEL}_${H}x${W}
mkdir -p ${MODEL}_${H}x${W}/openvino/myriad
${INTEL_OPENVINO_DIR}/deployment_tools/inference_engine/lib/intel64/myriad_compile \
-m ${MODEL}_${H}x${W}/openvino/FP16/${MODEL}_${H}x${W}.xml \
-ip U8 \
-VPU_NUMBER_OF_SHAVES 4 \
-VPU_NUMBER_OF_CMX_SLICES 4 \
-o ${MODEL}_${H}x${W}/openvino/myriad/${MODEL}_${H}x${W}.blob

openvino2tensorflow \
--model_path ${MODEL}_${H}x${W}/openvino/FP32/${MODEL}_${H}x${W}.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 \
--output_integer_quant_type 'uint8' \
--string_formulas_for_normalization 'data / 255' \
--output_tfjs \
--output_coreml \
--non_verbose

Description

GroupConvolutionBackpropData implementation.

Relevant Log Output

The GroupConvolutionBackpropData layer is not yet implemented.

Source code for simple inference testing code

_No response_