我想进行Gram-Schmidt正交化以修复较大的矩阵,这些矩阵开始与纯Tensorflow中的正交性略有不同(要在更大的计算量内在图形上进行而不破坏它)。我见过的like the one there解决方案是“外部”使用的(在内部执行多个sess.run
)。
因此,我自己编写了一个简单但效率很低的实现:
def tf_gram_schmidt(vectors):
# add batch dimension for matmul
basis = tf.expand_dims(vectors[0,:]/tf.norm(vectors[0,:]),0)
for i in range(1,vectors.get_shape()[0].value):
v = vectors[i,:]
# add batch dimension for matmul
v = tf.expand_dims(v,0)
w = v - tf.matmul(tf.matmul(v, tf.transpose(basis)), basis)
# I assume that my matrix is close to orthogonal
basis = tf.concat([basis, w/tf.norm(w)],axis=0)
return basis
但是,当我将其与相同的迭代外部代码进行比较时,它的速度要慢3倍(在GPU上!!!)(尽管精度更高):
how much source differs from orthogonal matrix:
44.7176
tensorflow version:
0.034667
Time elapsed: 23365.9820557ms
numpy version with tensorflow and variable re-assign to the result of numpy code:
0.057589
Time elapsed: 8540.5600071ms
(UPD 4:在我的示例中,我犯了一个小错误,但是它完全没有改变计时,因为
ort_discrepancy()
是一个轻量级的函数):最小示例:
import tensorflow as tf
import numpy as np
import time
# found this code somewhere on stackoverflow
def np_gram_schmidt(vectors):
basis = []
for v in vectors:
w = v - np.sum( np.dot(v,b)*b for b in basis )
if (w > 1e-10).any():
basis.append(w/np.linalg.norm(w))
else:
basis.append(np.zeros(w.shape))
return np.array(basis)
def tf_gram_schmidt(vectors):
# add batch dimension for matmul
basis = tf.expand_dims(vectors[0,:]/tf.norm(vectors[0,:]),0)
for i in range(1,vectors.get_shape()[0].value):
v = vectors[i,:]
# add batch dimension for matmul
v = tf.expand_dims(v,0)
w = v - tf.matmul(tf.matmul(v, tf.transpose(basis)), basis)
# I assume that my matrix is close to orthogonal
basis = tf.concat([basis, w/tf.norm(w)],axis=0)
return basis
# how much matrix differs from orthogonal
# computes ||W*W^T - I||2
def ort_discrepancy(matrix):
wwt = tf.matmul(matrix, matrix, transpose_a=True)
rows = tf.shape(wwt)[0]
cols = tf.shape(wwt)[1]
return tf.norm((wwt - tf.eye(rows,cols)),ord='euclidean')
np.random.seed(0)
# white noise matrix
np_nearly_orthogonal = np.random.normal(size=(2000,2000))
# centered rows
np_nearly_orthogonal = np.array([row/np.linalg.norm(row) for row in np_nearly_orthogonal])
tf_nearly_orthogonal = tf.Variable(np_nearly_orthogonal,dtype=tf.float32)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
print("how much source differs from orthogonal matrix:")
print(ort_discrepancy(tf_nearly_orthogonal).eval())
print("tensorflow version:")
start = time.time()
print(ort_discrepancy(tf_gram_schmidt(tf_nearly_orthogonal)).eval())
end = time.time()
print("Time elapsed: %sms"%(1000*(end-start)))
print("numpy version with tensorflow and variable re-assign to the result of numpy code:")
start = time.time()
tf_nearly_orthogonal = tf.Variable(np_gram_schmidt(tf_nearly_orthogonal.eval()),dtype=tf.float32)
sess.run(tf.variables_initializer([tf_nearly_orthogonal]))
# check that variable was updated
print(ort_discrepancy(tf_nearly_orthogonal).eval())
end = time.time()
print("Time elapsed: %sms"%(1000*(end-start)))
有没有办法加快速度?我不知道如何为G-S做到这一点,这需要附加到基础上(因此
tf.map_fn
并行化无济于事)。UPD:我通过优化
tf.matmul
实现了2倍的差异:def tf_gram_schmidt(vectors):
# add batch dimension for matmul
basis = tf.expand_dims(vectors[0,:]/tf.norm(vectors[0,:]),0)
for i in range(1,vectors.get_shape()[0].value):
v = vectors[i,:]
# add batch dimension for matmul
v = tf.expand_dims(v,0)
w = v - tf.matmul(tf.matmul(v, basis, transpose_b=True), basis)
# I assume that my matrix is close to orthogonal
basis = tf.concat([basis, w/tf.norm(w)],axis=0)
return basis
how much source differs from orthogonal matrix:
44.7176
tensorflow version:
0.0335421
Time elapsed: 17004.458189ms
numpy version with tensorflow and variable re-assign to the result of numpy code:
0.057589
Time elapsed: 8082.20791817ms
编辑2:
只是为了好玩,尝试完全模仿numpy解决方案,并获得了非常长的工作代码:
def tf_gram_schmidt(vectors):
# add batch dimension for matmul
basis = tf.expand_dims(vectors[0,:]/tf.norm(vectors[0,:]),0)
for i in range(1,vectors.get_shape()[0].value):
v = vectors[i,:]
# like in numpy example
multiplied = tf.reduce_sum(tf.map_fn(lambda b: tf.scalar_mul(tf.tensordot(v,b,axes=[[0],[0]]),b), basis), axis=0)
w = v - multiplied
## add batch dimension for matmul
##v = tf.expand_dims(v,0)
##w = v - tf.matmul(tf.matmul(v, basis, transpose_b=True), basis)
# I assume that my matrix is close to orthogonal
basis = tf.concat([basis, tf.expand_dims(w/tf.norm(w),0)],axis=0)
return basis
(这似乎也填满了GPU内存):
how much source differs from orthogonal matrix:
44.7176
tensorflow version:
2018-01-05 22:12:09.854505: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 14005 get requests, put_count=5105 evicted_count=1000 eviction_rate=0.195886 and unsatisfied allocation rate=0.714031
2018-01-05 22:12:09.854530: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:259] Raising pool_size_limit_ from 100 to 110
2018-01-05 22:12:13.090296: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 308520 get requests, put_count=314261 evicted_count=6000 eviction_rate=0.0190924 and unsatisfied allocation rate=0.00088487
2018-01-05 22:12:22.270822: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 1485113 get requests, put_count=1500399 evicted_count=16000 eviction_rate=0.0106638 and unsatisfied allocation rate=0.000490198
2018-01-05 22:12:37.833056: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 3484575 get requests, put_count=3509407 evicted_count=26000 eviction_rate=0.00740866 and unsatisfied allocation rate=0.000339209
2018-01-05 22:12:59.995184: I tensorflow/core/common_runtime/gpu/pool_allocator.cc:247] PoolAllocator: After 6315546 get requests, put_count=6349923 evicted_count=36000 eviction_rate=0.00566936 and unsatisfied allocation rate=0.000259202
0.0290728
Time elapsed: 136108.97398ms
numpy version with tensorflow and variable re-assign to the result of numpy code:
0.057589
Time elapsed: 10618.8428402ms
UPD3:我的GPU是GTX1050,与我的CPU相比,它通常可以提高5-7倍的速度。所以结果对我来说很奇怪。
UPD5:好的,我发现该代码几乎不使用GPU,而通过人工编写的反向传播训练神经网络时,该反向传播使用了大量的
tf.matmul
和其他矩阵算法来充分利用它。为什么会这样呢?UPD 6:
根据给出的建议,我以新的方式衡量了时间:
# Akshay's suggestion to measure performance correclty
orthogonalized = ort_discrepancy(tf_gram_schmidt(tf_nearly_orthogonal))
with tf.Session() as sess:
sess.run(init)
print("how much source differs from orthogonal matrix:")
print(ort_discrepancy(tf_nearly_orthogonal).eval())
print("tensorflow version:")
start = time.time()
tf_result = sess.run(orthogonalized)
end = time.time()
print(tf_result)
print("Time elapsed: %sms"%(1000*(end-start)))
print("numpy version with tensorflow and variable re-assign to the result of numpy code:")
start = time.time()
tf_nearly_orthogonal = tf.Variable(np_gram_schmidt(tf_nearly_orthogonal.eval()),dtype=tf.float32)
sess.run(tf.variables_initializer([tf_nearly_orthogonal]))
# check that variable was updated
print(ort_discrepancy(tf_nearly_orthogonal).eval())
end = time.time()
print("Time elapsed: %sms"%(1000*(end-start)))
现在我可以看到4倍加速:
how much source differs from orthogonal matrix:
44.7176
tensorflow version:
0.018951
Time elapsed: 2594.85888481ms
numpy version with tensorflow and variable re-assign to the result of numpy code:
0.057589
Time elapsed: 8851.86600685ms
最佳答案
TensorFlow的显示速度很慢,因为您的基准测试同时测量了它构造图形的时间和执行它所花费的时间。 TensorFlow和NumPy之间进行更公平的比较会从基准中排除图形构造。特别是,您的基准应该看起来像这样:
print("tensorflow version:")
# This line constructs the graph but does not execute it.
orthogonalized = ort_discrepancy(tf_gram_schmidt(tf_nearly_orthogonal))
start = time.time()
tf_result = sess.run(orthogonalized)
end = time.time()
关于python - 纯Tensorflow中的Gram-Schmidt正交化:迭代解的性能比numpy慢得多,我们在Stack Overflow上找到一个类似的问题:https://stackoverflow.com/questions/48119473/