Home > Mobile >  How to convert a string to a tensorflow model?
How to convert a string to a tensorflow model?

Time:11-03

So, I have created this model model1 and I am trying to create a function which takes in different models like model1 model2 etc and evaluates them. In the process, I have a string called "model1" which I would like to convert to model1 so I can pass the .evaluate() method to it. Would this be possible?

CodePudding user response:

Assuming that your previously trained models are saved to disk, you may just want to load them back into memory and evaluate as:

model_names = ["model1", "model2", "model3", ..., "model10"]
for model_name in model_names:
    model = tf.keras.models.load_model("path/to/location/"   model_name)
    score = model.evaluate(X_test, y_test, ...)

Also, if you plan to have lots of models with sequential names, like model1, model2, ..., model_n, you can use list comprehension instead of hard coding the model names like:

model_names = ["model"   str(x) for x in range(1, n)]

Please note that these are pseudo-codes and you need to complete ... according to your needs.

  • Related