-1
$\begingroup$

Let's say I have implemented a model to predict whether the image is dog, cat, bird, elephant. my model predicts the input dog image as a cat how to interpret the model how/why it goes high prediction on the particular label?

PS:- I'm using TensorFlow and Resnet50 pre-trained model.

$\endgroup$

1 Answer 1

0
$\begingroup$

The thing about neural networks is that they are uninterpretable. I bet there might be some techniques that tackle this issue. You can try google scholar for that. But yeah, neural networks are basically black boxes. You can extract the convolutional filters and see the results of each layer on the image, but you will just come up with ,,When this shape is present and this shape is present next to it the probability of input being a cat raises by 30%".

$\endgroup$

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.