The shape of the output layer is different from the result of the tensorflow2onnx transformation.

[ichigosyakure]

Issue Type

Bug

OS

Ubuntu

OS architecture

x86_64

Programming Language

Python

Framework

ONNX

Download URL for tflite file

VertexAI Auto ML classification TFlite Format model

Convert Script

●tflite2tensorflow

docker run -it --rm --gpus all -v pwd:/home/user/workdir ghcr.io/pinto0309/tflite2tensorflow:latest

tflite2tensorflow \ --model_path model.tflite \ --flatc_path ../flatc \ --schema_path ../schema.fbs \ --output_pb \ --optimizing_for_openvino_and_myriad \ --rigorous_optimization_for_myriad

tflite2tensorflow \ --model_path model.tflite \ --flatc_path ../flatc \ --schema_path ../schema.fbs \ --output_onnx \ --onnx_opset 13 \ --output_openvino_and_myriad

●tensorflow2onnx pip install git+https://github.com/onnx/tensorflow-onnx

python -m tf2onnx.convert --opset 13 --tflite model.tflite --output model.onnx --dequantize

Description

I'm trying to convert the attached file from tflite to onnx. (Eventually I want to run it in myriad). In the conversion source tflite, the input to sortmax is [1×8], but in tflite2tensorflow, it is [7×7×8]. If you try tensorflow2tflite, the input to sortmax becomes [1×8] as in tflite. I think [1×8] is correct because it is an 8-class classification model.

[tflite]

[tflite2tensorflow(savedmodel and onnx)]

[tensorflow2onnx]

Relevant Log Output

None.

Source code for simple inference testing code

No response

[PINTO0309]

Please attach the tflite. I know that the structure of the tflite model generated by Auto ML is special.

[ichigosyakure]

Sorry. I forgot to attach the file. I will attach it later.

[ichigosyakure]

file.zip Sorry.　I've re-uploaded it.

[PINTO0309]

commit: 18b3e8880ddf3be5a9e9b70e3fe581bc981ab7a6

[PINTO0309]

[PINTO0309]

Release: https://github.com/PINTO0309/tflite2tensorflow/releases/tag/v1.18.1

[PINTO0309]

Please upgrade the package to v1.18.1 and try again.

[ichigosyakure]

I've confirmed the fix. Thank you.