microsoft / microsoft/onnxruntime
[Documentation Request]
- Dominant language
- C++
- Stars
- 21.9k
- Forks
- 4.2k
- Avg merge
- 4d 11h
- Merged PRs (30d)
- 184
Description
[Enter feedback here]
There is an issue with the following function:
tf2onnx.convert.from_keras()
The errror details:
"""
An error occurred: 'Sequential' object has no attribute 'output_names'
"""
I have to roll back tensorflow from 2.16.1 to 2.15.0 so that this can be solved
Please add this to the documentation and investigate what cause this incompatibility issue
if you want more details of the code, feel free to reach out to me at expdal3@gmail.com
---
#### Document Details
* Title: Getting Started - TensorFlow
* Page: [https://onnxruntime.ai/docs/tutorials/tf-get-started.html](https://onnxruntime.ai/docs/tutorials/tf-get-started.html)
* Page Source: tf-get-started.md
Contributor guide
Research direction
Start with tf-get-started.md and the documented tf2onnx.convert.from_keras() example. Reproduce the reported 'Sequential' object has no attribute 'output_names' error with TensorFlow 2.16.1 and compare it with 2.15.0; done means documenting the incompatibility and its cause or updating the getting-started guidance.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- tensorflow
- Domain
- documentation, machine-learning
- Issue type
- Documentation
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100