tensorflow / tensorflow/models
How can I save a frozen inference graph in TF2?
Open
@pkulzc is already working on this.
Since Sep 21, 2020.
models:research:odapi
type:support
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
I have trained a network to be able to use it in tensorflow.js but it works very slow because it has been converted from a saved model instead of a frozen graph as they have done with the pretrained models provided here.
to check that it was not my thing, I have taken the ssdlite_mobilenet_v2 (TF1.x) from this repository and I have tried to convert the graph as indicated here and the saved model and it has the same problem, the saved model is very slow with respect to the graph. so I would like to know how to export the frozen inference graph
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.