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 b…

Reshaped input shape

german.mesa November 3, 2021, 1:50pm 2

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

Hope it helps

1 Like

Topic		Replies	Views
Excercise-3-Question -Why do we need to change input shape Introduction to TF for Artificial Intelligence ... week-module-3	1	572	February 14, 2022
Graph execution error Convolutional Neural Networks in TensorFlow week-module-4	1	506	November 4, 2022
C2_W1_Lab01_Shape_2D Advanced Learning Algorithms week-module-1	1	515	July 12, 2022
C2W4 (None,1) and (None, 26) Error Convolutional Neural Networks in TensorFlow week-module-4	1	427	August 8, 2023
Week 4 Programming Convolutional Neural Networks in TensorFlow week-module-4	1	629	November 8, 2021