Concept 06 was about saving variables. This one's about loading what you saved. Start by creating an interactive session:
In [1]:
import tensorflow as tf
sess = tf.InteractiveSession()
Create a boolean vector called spikes of the same dimensions as before:
In [2]:
spikes = tf.Variable([False]*8, name='spikes')
Restored the variable data from disk, serve warm, and enjoy:
In [3]:
saver = tf.train.Saver()
try:
saver.restore(sess, 'spikes.ckpt')
print(spikes.eval())
except:
print('file not found')
Show's over, goodnight:
In [4]:
sess.close()