使用张量流执行简单的最小化任务(为硬S形逼近拟合最佳参数)后,我决定将其从图模式转换为热切模式。我感到惊讶的是,在急切模式下运行需要更长的时间。
这里是密码。
图形模式代码:
import tensorflow as tf
from time import time
beg = time()
a = tf.Variable(-10, name='a', dtype=tf.float32)
b = tf.Variable(10, name='b', dtype=tf.float32)
def g(x):
return tf.clip_by_value( (x-a)/(b-a), 0, 1)
X = tf.lin_space(-20., 20., 2000)
loss = tf.reduce_sum( tf.square( tf.math.sigmoid(X) - g(X)))
opt = tf.train.AdamOptimizer(learning_rate=1e-3)
train_op = opt.minimize( loss)
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init_op)
for _ in range( int(1e4)):
sess.run( train_op)
print( 'Non-eager run in %.1f seconds' %(time()-beg))
打印Non-eager run in 3.5 seconds
急切模式代码:
import tensorflow as tf
from time import time
tf.enable_eager_execution()
beg = time()
a = tf.Variable(-10, name='a', dtype=tf.float32)
b = tf.Variable(10, name='b', dtype=tf.float32)
def g(x):
return tf.clip_by_value( (x-a)/(b-a), 0, 1)
X = tf.lin_space(-20., 20., 2000)
opt = tf.train.AdamOptimizer(learning_rate=1e-3)
for _ in range( int(1e4)):
with tf.GradientTape() as tape:
loss = tf.reduce_sum( tf.square( tf.math.sigmoid(X) - g(X)))
grads = tape.gradient(loss, [a,b])
opt.apply_gradients(zip(grads, [a,b]), global_step=tf.train.get_or_create_global_step())
print( 'Eager run in %.1f seconds' %(time()-beg))
打印Eager run in 20.9 seconds
我敢打赌,我急切的代码是次优的,并且tensorflow
在下一个重要版本中似乎正转向急切执行,我想知道如何优化此代码以使其性能至少与第一版。
答案 0 :(得分:2)
您的代码在tensorflow 2.0中看起来像(请注意,您已经可以尝试每晚构建tensorflow 2.0(https://pypi.org/project/tf-nightly-2.0-preview/))
import tensorflow as tf
from time import time
tf.enable_eager_execution()
beg = time()
@tf.function
def train():
a = tf.Variable(-10, name='a', dtype=tf.float32)
b = tf.Variable(10, name='b', dtype=tf.float32)
def g(x):
return tf.clip_by_value((x - a) / (b - a), 0, 1)
X = tf.lin_space(-20., 20., 2000)
opt = tf.train.AdamOptimizer(learning_rate=1e-3)
for _ in range(int(1e4)):
with tf.GradientTape() as tape:
loss = tf.reduce_sum(tf.square(tf.math.sigmoid(X) - g(X)))
grads = tape.gradient(loss, [a, b])
opt.apply_gradients(
zip(grads, [a, b]),
global_step=tf.train.get_or_create_global_step())
train()
print('Eager run in %.1f seconds' % (time() - beg))
请注意,@tf.session
的基础tf.contrib.eager.defun
和Autograph
(在1.12及更高版本中可用)仍在积极开发中,并且实验性 ,因此目前的实现有点麻烦。因此,如果它无法运行或运行速度较慢,可能值得在Github上发布一个问题。
在2.0版本中,@tf.session
将合并defun
和autograd
的优点