I got the following error when I tried to call the create model function
It says input depth must be evenly divisible by filter depth: 1 vs 3
Please click my name and message your notebook as an attachment.
Each image has shape (28, 28, 1). Your model input dimension is (150, 150, 3). Hence the problem.
>>> print(train_generator.x.shape)
(27455, 28, 28, 1)
The previous error is different from the error above.
In this case, the number of units in the output layer is lesser than the number of labels. Here’s a hint from the notebook:
You will be using the Sign Language MNIST dataset, which contains 28x28 images of hands depicting the 26 letters of the english alphabet.
