PINTO0309 / onnx2tf

Self-Created Tools to convert ONNX files (NCHW) to TensorFlow/TFLite/Keras format (NHWC). The purpose of this tool is to solve the massive Transpose extrapolation problem in onnx-tensorflow (onnx-tf). I don't need a Star, but give me a pull request.

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

onnx2tf conversion error for gpt2 transformers model #591 follow up

flores-o opened this issue · comments

Issue Type

Others

OS

Linux

onnx2tf version number

1.19.11

onnx version number

1.15.0

onnxruntime version number

1.16.3

onnxsim (onnx_simplifier) version number

0.4.33

tensorflow version number

2.16.1

Download URL for ONNX

https://huggingface.co/openai-community/gpt2/resolve/main/onnx/decoder_model.onnx?download=true

Parameter Replacement JSON

Not required as per https://github.com/PINTO0309/onnx2tf/issues/591

Description

This is a the same error described in #591

To reproduce the error, can run the following notebook
https://colab.research.google.com/drive/1pBnJpC4613cUoNl-k_rdHeGm3pnFCuds?usp=sharing

I tried running the suggested command in #591 and I am getting the same error
!onnx2tf -i /content/model.onnx -b 1 -osd

Can you share library versions you used when running the command successfully or do you have any hints on why it would not work in the linked colab? Thank you in advance!

https://github.com/PINTO0309/onnx2tf?tab=readme-ov-file#environment

image

pip show tensorflow

Name: tensorflow
Version: 2.14.0
Summary: TensorFlow is an open source machine learning framework for everyone.
Home-page: https://www.tensorflow.org/
Author: Google Inc.
Author-email: packages@tensorflow.org
License: Apache 2.0
Location: /home/b920405/.local/lib/python3.10/site-packages
Requires: absl-py, astunparse, flatbuffers, gast, google-pasta, grpcio, h5py, keras, libclang, ml-dtypes, numpy, opt-einsum, packaging, protobuf, setuptools, six, tensorboard, tensorflow-estimator, tensorflow-io-gcs-filesystem, termcolor, typing-extensions, wrapt
Required-by: retina-face, tensorflow-decision-forests, tensorflowjs

Thank you, the command ran without errors with the environment above and tf 2.14.0