1
$\begingroup$

Why my model shows metrics like this? While my model was training recall and precision was equal to zero? I trying to do binary classification of mushrooms [edible, poisonous]. I have CNN model with some dropout and batch normalization. Dataset have ~7000 img, ration is equal to both class.

Python version is 3.10 Tensorflow version is 2.12

enter image description here

$\endgroup$
1
  • $\begingroup$ Are you sure your validation data is normalized in the same way of the training one? Also check the labels. $\endgroup$ Jun 3, 2023 at 12:20

1 Answer 1

0
$\begingroup$

It seems like your model is not generalizing properly. During training its performance on the traning set increases as it should but it fails to capture general properties in your data that would make it able to predict data in your validation dataset. It also seems to somewhat classify everything in your validation dataset into either of the classes, eg "everything is edible".
This can have various reasons, the most obvious are that your model is not suited for this task or that you don't have enough data. See Wikipedia for a more in-depth explanation:
https://en.wikipedia.org/wiki/Overfitting

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.