Programmer Guide (for Korean): TensorFlow Eager Execution
APACHE-2.0 License
(Eager execution) (NumPy ) .
, .
Session.run()
.
, :
x = tf.placeholder(tf.float32, shape=[1, 1])
m = tf.matmul(x, x)
with tf.Session() as sess:
print(sess.run(m, feed_dict={x: [[2.]]}))
# Will print [[4.]]
(Eager execution) :
x = [[2.]]
m = tf.matmul(x, x)
print(m)
, GPU .
(eager execution) . :