Why does my CIFAR 100 CNN model mainly predict two classes?

Question

I am currently trying to get a decent score (> 40% accuracy) with Keras on CIFAR 100. However, I\'m experiencing a weird behaviour of a CNN model: It tends to predict some c

Answer 1

One important part of the problem was that my ~/.keras/keras.json was

{
    "image_dim_ordering": "th",
    "epsilon": 1e-07,
    "floatx": "float32",
    "backend": "tensorflow"
}

Hence I had to change image_dim_ordering to tf. This leads to

and an accuracy of 12.73%. Obviously, there is still a problem as the validation history gave 45.1% accuracy.