Simpler MWE for "Computer freeze when feeding a large numpy"

from tensorflow.examples.tutorials.mnist import input_data
import tensorflow as tf

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(initial)

def conv2d(x, W):
  return tf.nn.conv2d(x, W, strides=[1, 1, 1, 1], padding='SAME')

def max_pool_2x2(x):
  return tf.nn.max_pool(x, ksize=[1, 2, 2, 1],
                        strides=[1, 2, 2, 1], padding='SAME')

mnist = input_data.read_data_sets('MNIST_data', one_hot=True)
sess = tf.InteractiveSession()

x = tf.placeholder(tf.float32, shape=[None, 784])
y_ = tf.placeholder(tf.float32, shape=[None, 10])

x_image = tf.reshape(x, [-1,28,28,1])

filters=4
W_conv = weight_variable([5, 5, 1, filters])
b_conv = bias_variable([filters])

h_conv = (conv2d(x_image, W_conv) + b_conv)
h_pool = max_pool_2x2(h_conv)

s=14*14*filters
h=16
h_pool_flat = tf.reshape(h_pool, [-1, s])
classes=10
W_fc = weight_variable([s, classes])
b_fc = bias_variable([classes])
y_conv = tf.matmul(h_pool_flat, W_fc) + b_fc
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(y_conv, y_))

sess.run(tf.initialize_all_variables())

n=55000
train_accuracy = cross_entropy.eval(feed_dict={ x:mnist.train.images[:n,:], y_: mnist.train.labels[:n,:]})