PINTO0309 / PINTO_model_zoo

A repository for storing models that have been inter-converted between various frameworks. Supported frameworks are TensorFlow, PyTorch, ONNX, OpenVINO, TFJS, TFTRT, TensorFlowLite (Float32/16/INT8), EdgeTPU, CoreML.

Home Page:https://qiita.com/PINTO

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

ONNX version for person-reidentification-retail-0277

hyperf0cus opened this issue · comments

Issue Type

Others

OS

Ubuntu

OS architecture

x86_64

Programming Language

Python

Framework

ONNX

Model name and Weights/Checkpoints URL

https://storage.openvinotoolkit.org/repositories/open_model_zoo/2023.0/models_bin/1/person-reidentification-retail-0277/

Description

Inside 083 directory for person-reidentification-retail-0277 there is model_float32.onnx, but I'm not sure is this onnx model is the same as openvino models for 0277, furthermore model_float32.onnx is nwhc as tensorflow, and can't convert it through model_optimizer to compare with models from openvino model zoo for person-reidentification-retail-0277. Do you have onnx model for example person-reidentification-retail-0277.onnx?

Relevant Log Output

No response

URL or source code for simple inference testing code

No response

Not sure what you are talking about, but it is the same model. ONNX channel positions can be rewritten in miscellaneous ways.

image

person-reidentification-retail-0265.onnx.zip

so model_float_32.onnx inside your repo and person-reidentification-retail-0265.onnx supposed to be the same?

Strictly speaking, there is no documentation of how Intel generated the ONNX files, so there is no way I can answer that question.

Thank you for answers, and last one, how you get your model_float32.onnx, .pb, tflite etc?