I am running a MNIST example in a Jupyter notebook running in an Anaconda virtual environment. I have tried to run the code below (not yet finished, I was testing it) when it comes up with an error (can be seen below the code).
(X_train, y_train), (X_test, y_test) = mnist.load_data()
#print("X_train shape", X_train.shape)
#print ("y_train shape", y_train.shape)
#print("X_test shape", X_test.shape)
#print ("y_test shape", y_test.shape)
from keras.models import Sequential #imports the sequential model
from keras.layers import Dense, Dropout, Conv2D, MaxPool2D
from keras.utils import np_utils
#flattens the images from the 28x28 pixels to 1D 787 pixels
X_train = X_train.reshape (60000, 784) #flattening the image into 28x28 pixels, so into an array of 784.
X_test = X_test.reshape (10000, 784)
X_train = X_train.astype('float32') #using a 32-bit precision when training the neural network. This is most commonly used.
X_test = X_test.astype('float32')
X_train /=255 #Used for normalisation. Each image has a 'degree' of darkness within the range of 0-255 so you need to reduce that range to 0-1 for your Neural Network
X_test /=255
#one-hot encoding using keras' numpy-related utilities
n_classes=10
print ("Shape before one-hot encoding: ", y_train.shape)
Y_train = np.utils.to_categorical(y_train, n_classes)
Y_test = np.utils.to_categorical(y_test, n_classes)
print ("Shape after one-hot encoding:", Y_train.shape)
Error:
---------------------------------------------------------------------------
NameError Traceback (most recent call last)
<ipython-input-4-0063f366d5bd> in <module>
22 n_classes=10
23 print ("Shape before one-hot encoding: ", y_train.shape)
---> 24 Y_train = np.utils.to_categorical(y_train, n_classes)
25 Y_test = np.utils.to_categorical(y_test, n_classes)
26 print ("Shape after one-hot encoding:", Y_train.shape)
NameError: name 'np' is not defined
I guess I need to define np somewhere, but the practise code on the website I am using doesn't actually define np anywhere. Any suggestions?
Many thanks
