Many pad ops added to the conv

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

Many pad ops added to the conv #113

Closed liyancas closed 2 years ago

liyancas commented 2 years ago

Issue Type

Performance

OS

Ubuntu

OS architecture

x86_64

Programming Language

Python

Framework

OpenVINO

Download URL for ONNX / OpenVINO IR

refer to https://github.com/PINTO0309/openvino2tensorflow/issues/112

Convert Script

refer to https://github.com/PINTO0309/openvino2tensorflow/issues/112

Description

Relevant Log Output

refer to https://github.com/PINTO0309/openvino2tensorflow/issues/112

Source code for simple inference testing code

No response

PINTO0309 commented 2 years ago

Pad reduction cannot be addressed. There is no exact specification match between OpenVINO and TensorFlow. Have you checked to see if the layers of Padding are really affecting performance?

This is an unfixable condition. If you are dissatisfied with the tool's specifications, use onnx-tf.