New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Problem in try to use GraphRunner for FaceNet #9

Open

DreamInSun opened this issue Mar 18, 2019 · 0 comments

DreamInSun commented Mar 18, 2019 •

edited

Loading

I came to have the same problem maybe you've solved.

I use the pre-trained FaceNet Model. the same as you are:

/===== Input Map =====/
Map<String, INDArray> feedMap = Maps.newHashMap();
feedMap.put("input:0", imgArr);
/===== Set Phase Input =====/
INDArray phaseInput = ???;
feedMap.put("phase_train:0", phaseInput);
/===== Run Graph =====/
Map<String, INDArray> resultMap = this.m_faceNetGraphRunner.run(feedMap);
/===== Output Map =====/
INDArray embeddings = resultMap.get("embeddings:0");

the GraphRunner cannot accept Boolean feed.

Have you solved it or found some walkaround ?

My appreciate

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment