Hi, I trained an image classification model using convnet and then froze it.
mohit choudhary

You have to explore which part holds memory and lead to this memory leak.

Be careful, you should not use this code in a production environment, it is meant as a fast way to prototype and testing. Check TensorFlow serving for a more robust way to serve your models.

Like what you read? Give Morgan a round of applause.

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