LeNet for MNIST data

Note

You can follow along with the code in the Jupyter notebook ch-09a_CNN_MNIST_TF_and_Keras.

Prepare the MNIST data into test and train sets:

from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets(os.path.join('.','mnist'), one_hot=True)
X_train = mnist.train.images
X_test = mnist.test.images
Y_train = mnist.train.labels
Y_test = mnist.test.labels

LeNet CNN for MNIST with TensorFlow

In TensorFlow, apply the following steps to build the LeNet based CNN models for MNIST data:

1. Define the hyper-parameters, and the placeholders for x and y (input images and output labels):

n_classes = 10 # 0-9 digits
n_width = 28
n_height = 28
n_depth = 1
n_inputs = n_height * n_width * n_depth # total pixels
learning_rate = 0.001
n_epochs = 10
batch_size = 100
n_batches = int(mnist.train.num_examples/batch_size)

# input images shape: (n_samples,n_pixels)
x = tf.placeholder(dtype=tf.float32, name="x", shape=[None, n_inputs]) 
# output labels
y = tf.placeholder...