Keras accuracy calculation and meaning

Asked Apr 15 '18 at 12:06

Active Jun 08 '19 at 10:37

Viewed 366 times

I am detecting objects using CNN and keras

When i test/train model it outputs acc and loss.

I am using MSE loss functions so i understand what loss mean, however what is accuracy and how is it calculated? I have 4000 loss and accuracy 80% which is stupid. It does not detect object 80% correctly. What does it mean and how is it calcualted then?

Thanks for help.

edited Jun 08 '19 at 10:37

desertnaut

57,590
26
140
166

asked Apr 15 '18 at 12:06

jejjejd

are you using categorical accuracy or binary accuracy – Primusa Apr 15 '18 at 17:30
I am using the default one model.compile(loss="mse", optimizer=keras.optimizers.Adam(),metrics=['accuracy']) – jejjejd Apr 19 '18 at 13:21
1

mse loss is for regression not classification. – Primusa Apr 19 '18 at 15:52
yes but the acc is still there so how is it calcualated? – jejjejd Apr 20 '18 at 14:53
1

Thats the point. It's not calculated correctly – Primusa Apr 20 '18 at 15:04
Possible duplicate of [What function defines accuracy in Keras when the loss is mean squared error (MSE)?](https://stackoverflow.com/questions/48775305/what-function-defines-accuracy-in-keras-when-the-loss-is-mean-squared-error-mse) – desertnaut Jun 08 '19 at 10:38

Keras accuracy calculation and meaning

0 Answers0