Advertisements When running this code, I want to show the image in matplotlib but am I getting an error in some_digit_image = some_digit.reshape(28, 28) where I get the ValueError: cannot reshape array of size 1 into shape (28, 28). Is there any way to fix this issue and get the image in the matplotlib. Thanks… Read More Issue reshaping an array into (28, 28) for an MNIST image

Advertisements Refer to this Complete guide on How to use Autoencoders in Python Notice the author add: x_train = x_train.astype(‘float32’) / 255. x_test = x_test.astype(‘float32’) / 255. x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:]))) x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:]))) after they loaded the MNIST data. Why do they divide the image data by 255? And why 255? After that… Read More Why do we need to pre-process image datasets?