Export tensorflow weights to hdf5 file and model to keras model.json

Question

I recently found this Project which runs inference of keras model in a browser with GPU support using webgl. I have a few tensorflow project that I would like to run inference on a browser, is there a way to export tensorflow models into hdf5 file so it can be run using keras-js

You can check my answer on this issue in another thread. https://stackoverflow.com/questions/44466066/how-can-i-convert-a-trained-tensorflow-model-to-keras/46210187#46210187 — Prasad, Sep 14 '17 at 03:48

score 0 · Answer 1 · answered Apr 14 '17 at 06:07

0

If you are using Keras, you can do something like this.

model.save_weights('my_model.hdf5')

answered Apr 14 '17 at 06:07

Wasi Ahmad

35,739
32
114
161

No I am using tensorflow – anandaravindan Apr 14 '17 at 13:56

score 0 · Answer 2 · answered Apr 14 '17 at 20:18

The only way I can see this working is if you use a Keras model as an interface to your TensorFlow workflow. If you do that, you can do this to save the model and its weights:

# save model
with open(model_save_filename, "w") as model_save_file:
    model_json = model.to_json()
    model_save_file.write(model_json)

# save model weights
model.save_weights(model_weights_save_filename)

More information on using Keras as an interface to Tensorflow workflows here: https://blog.keras.io/keras-as-a-simplified-interface-to-tensorflow-tutorial.html#using-keras-models-with-tensorflow

Export tensorflow weights to hdf5 file and model to keras model.json

2 Answers2

Linked