Reshaped input shape

To use conv2D, we reshape the data to a single 4D list that is 60,000x28x28x1, and the same for the test images. If you don’t do this, you’ll get an error when training as the Convolutions do not recognize the shape.

However, the input_shape for the first Conv2D layer is (28,28,1). Shouldn’t this be (60,000x28x28x1)?

Hi @JeainnyKim,

I have answer a similar question here. I hope it helps.

Hope it helps

1 Like