Why Trained and Loaded Model is giving different evaluate result? 82% vs 5%


I implemented my seq-Keras model and it was successfully trained.

>>Result:  Successfully completed: TrainAcc=99%, ValAcc=88%

NOW I run this code:

model.evaluate(X_test, y_test)
   Result >> accuracy: 0.8216

but when I load the saved model(Model88) and evaluate that:

model = keras.models.load_model('Model88.h5')
model.evaluate(X_test, y_test)
    Result >>  accuracy: 0.0214 !!!

The test data is the same, the saved model and the loaded model are the same!

Why does this happen? accuracy: 82% -> 5% !!!!


I had same problem before and i found out that test accuracy was calculated wrongly during training. I had changed test batch size to 1 to fix it.

Answered By – Uur Kn

Answer Checked By – David Goodson (AngularFixing Volunteer)

Leave a Reply

Your email address will not be published.