I am trying to create model architecture for classification of animals, but facing error while implementing it. Please help me to solve the error.
Here is the error that I am facing -
ValueError: Input 0 of layer sequential_3 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [None, 100, 100].
Kindly find the link to colab.
You have used loss=“binary_crossentropy” but this is not a binary classification problem. It has more than 2 classes in Target variable. So use categorical_crossentropy
Thanks for correcting me.
Could you please help me with notebook submission of Assignment 1? I can’t see any upload option there.
Hi @nisrin_dhoondia. Now I am facing these issue -
ValueError: Input 0 of layer sequential is incompatible with the layer: expected axis -1 of input shape to have value 100 but received input with shape [None, 100, 100, 3]
This is the updated colab.
It seems like you are providing the input shape to CNN as (3,100,100) but shaping the actual inputs(in train datagen) differently. That’s what is causing the error.