Reshape the original dataset and the noised dataset to shape 60000*28*28*1. This is important since the 2D convolutions expect to receive images of shape 28*28*1.
# Reshaping the training data
X_train = X_train.reshape(X_train.shape[0], X_train.shape[1], X_train.shape[2], 1)
print('Size/Shape of the original training set: ', X_train.shape)
# Reshaping the nosied training data
noised_train_data = noised_train_data.reshape(noised_train_data.shape[0],
noised_train_data.shape[1],
noised_train_data.shape[2], 1)
print('Size/Shape of the noised training set: ', noised_train_data.shape)
# Reshaping the testing data
X_test = X_test.reshape(X_test.shape[0], X_test.shape[1], X_test.shape[2], 1)
print('Size/Shape of the original test set: ', X_test.shape)
# Reshaping the noised testing data
noised_test_data = noised_test_data.reshape(noised_test_data.shape[0],
noised_test_data.shape[1],
noised_test_data.shape[2], 1)
print('Size/Shape of the noised test set: ', noised_test_data.shape)
If you are doing multiple training runs on the GPU, it is always a good idea to clear space on the GPU after each run so that your next run executes efficiently without errors related to 'resource exhaustion' which is pretty common with GPU's. This can be done with...
from keras import backend as k
k.clear_session()