TensorFlow: How to freeze a model and serve it with a python API

Thanks for the article!

I’ve been following the TensorFlow for Poets 2 codelab on a model I’ve trained, and I only get a single output_graph.pb file generated from the retrain script.How can I freeze the model?

AttributeError: module ‘bottleneck’ has no attribute ‘__version__’

Like what you read? Give Ronald Miranda a round of applause.

From a quick cheer to a standing ovation, clap to show how much you enjoyed this story.