Skip to content

Instantly share code, notes, and snippets.

@yuhanz

yuhanz/keras-model-to-tensorflow-model.py

Created September 17, 2018 05:53
Show Gist options

  • Select an option

    Learn more about clone URLs
  • Save yuhanz/a5d783af813f66c566bd31387f719120 to your computer and use it in GitHub Desktop.

Select an option

Learn more about clone URLs
Save yuhanz/a5d783af813f66c566bd31387f719120 to your computer and use it in GitHub Desktop.
Download ZIP
Convert a trained keras model .h5 file into tensorflow saved model
Raw
keras-model-to-tensorflow-model.py
from keras.models import load_model
import numpy as np
model = load_model('trained_keras_model.h5')
from keras import backend as K
import tensorflow as tf
signature = tf.saved_model.signature_def_utils.predict_signature_def(
inputs={'image': model.input}, outputs={'scores': model.output})
builder = tf.saved_model.builder.SavedModelBuilder('/tmp/my_saved_model')
builder.add_meta_graph_and_variables(
sess=K.get_session(),
tags=[tf.saved_model.tag_constants.SERVING],
signature_def_map={
tf.saved_model.signature_constants.DEFAULT_SERVING_SIGNATURE_DEF_KEY:
signature
})
builder.save()
@PatrickNa
Copy link

PatrickNa commented May 19, 2020 •
edited
Loading

TensorFlow 2.x

import tensorflow as tf

model = tf.keras.models.load_model('trained_keras_model.h5')
tf.saved_model.save(model, '/tmp/my_saved_model')

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