Load specific trained model

Question

Currently I am loading a previously trained model using

with tf.Session() as sess:
    saver.restore(sess, tf.train.latest_checkpoint('./'))

which loads the file recorded in the file "checkpoint" that was created when saving the model. However, the file "checkpoint" always refers to the last trained model, so if I want to load another model I have to manually edit the "checkpoint" file to change the model name.

My question is, how can I restore a trained model different from the last one I created, without manually editing the "checkpoint" file?

score 2 · Accepted Answer · answered Aug 04 '19 at 07:16

2

You can use jsonpickle to save variables and models and later load them. For example:

sklearn_model = RandomForestClassifier()
sklearn_model.fit(x,y)
model_object = jsonpickle.pickler.Pickler.flatten(sklearn_model)
model = jsonpickle.unpickler.Unpickler.restore(model_object)
model.predict(new_x)

All you need now is to save the model whenever you want, and load it as needed. the model_object is a JSON code that can be saved to a file. You can read more about the package here

answered Aug 04 '19 at 07:16

Roee Anuar

3,071
1
19
33

Hi @Roee, can you tell how to save this model_object to use later for prediction? – Amarpreet Singh May 24 '20 at 05:38
1

@AmarpreetSingh see here https://stackoverflow.com/questions/2398078/saving-and-loading-objects-from-file-using-jsonpickle – Roee Anuar May 25 '20 at 06:12

Load specific trained model

1 Answers1