In most deep learning frameworks, it is to store the architecture and the trained weights. However, because this can be extremely important, we will demonstrate how to store your model with TensorFlow in the following recipe.
- We start by importing the libraries:
import tensorflow as tf from tensorflow.examples.tutorials.mnist import input_data
- Next, we load the MNIST data:
mnist = input_data.read_data_sets('Data/mnist', one_hot=True)
- We define the placeholders as follows:
n_classes = 10 input_size = 784 x = tf.placeholder(tf.float32, shape=[None, input_size]) y = tf.placeholder(tf.float32, shape=[None, n_classes]) keep_prob = tf.placeholder(tf.float32)
- For convenience, we create functions to build our deep learning network:
def weight_variable(shape): initial = tf.truncated_normal(shape, stddev=0.1) return tf.Variable(initial) def bias_variable(shape): initial = tf.constant(0.1, shape=shape) return tf.Variable...