张量流索引是如何工作的

how does tensorflow indexing work

我无法理解 tensorflow 的基本概念。张量 read/write 操作的索引如何工作?为了具体说明,如何将以下 numpy 示例转换为 tensorflow(对数组、索引和分配的值使用张量):

x = np.zeros((3, 4))
row_indices = np.array([1, 1, 2])
col_indices = np.array([0, 2, 3])
x[row_indices, col_indices] = 2
x

输出:

array([[ 0.,  0.,  0.,  0.],
       [ 2.,  0.,  2.,  0.],
       [ 0.,  0.,  0.,  2.]])

...和...

x[row_indices, col_indices] = np.array([5, 4, 3])
x

输出:

array([[ 0.,  0.,  0.,  0.],
       [ 5.,  0.,  4.,  0.],
       [ 0.,  0.,  0.,  3.]])

...最后...

y = x[row_indices, col_indices]
y

输出:

array([ 5.,  4.,  3.])

有 github 个问题 #206 可以很好地支持这一点,同时你必须求助于冗长的解决方法

第一个例子可以用tf.select来完成,它通过从一个或另一个中选择每个元素来组合两个相同形状的张量

tf.reset_default_graph()
row_indices = tf.constant([1, 1, 2])
col_indices = tf.constant([0, 2, 3])
x = tf.zeros((3, 4))
sess = tf.InteractiveSession()

# get list of ((row1, col1), (row2, col2), ..)
coords = tf.transpose(tf.pack([row_indices, col_indices]))

# get tensor with 1's at positions (row1, col1),...
binary_mask = tf.sparse_to_dense(coords, x.get_shape(), 1)

# convert 1/0 to True/False
binary_mask = tf.cast(binary_mask, tf.bool)

twos = 2*tf.ones(x.get_shape())

# make new x out of old values or 2, depending on mask 
x = tf.select(binary_mask, twos, x)

print x.eval()

给予

[[ 0.  0.  0.  0.]
 [ 2.  0.  2.  0.]
 [ 0.  0.  0.  2.]]

第二个可以用 scatter_update 完成,除了 scatter_update 只支持线性索引并且适用于变量。所以你可以创建一个临时变量并像这样使用重塑。 (为避免变量,您可以使用 dynamic_stitch,请参阅结尾)

# get linear indices
linear_indices = row_indices*x.get_shape()[1]+col_indices

# turn 'x' into 1d variable since "scatter_update" supports linear indexing only
x_flat = tf.Variable(tf.reshape(x, [-1]))

# no automatic promotion, so make updates float32 to match x
updates = tf.constant([5, 4, 3], dtype=tf.float32)

sess.run(tf.initialize_all_variables())
sess.run(tf.scatter_update(x_flat, linear_indices,  updates))

# convert back into original shape
x = tf.reshape(x_flat, x.get_shape())

print x.eval()

给予

[[ 0.  0.  0.  0.]
 [ 5.  0.  4.  0.]
 [ 0.  0.  0.  3.]]

最后第三个例子已经支持gather_nd,你写

print tf.gather_nd(x, coords).eval()

得到

[ 5.  4.  3.]

编辑,5 月 6 日

更新 x[cols,rows]=newvals 可以在不使用变量(在会话 运行 调用之间占用内存)的情况下通过使用 selectsparse_to_dense 来完成,它采用稀疏值向量, 或依靠 dynamic_stitch

sess = tf.InteractiveSession()
x = tf.zeros((3, 4))
row_indices = tf.constant([1, 1, 2])
col_indices = tf.constant([0, 2, 3])

# no automatic promotion, so specify float type
replacement_vals = tf.constant([5, 4, 3], dtype=tf.float32)

# convert to linear indexing in row-major form
linear_indices = row_indices*x.get_shape()[1]+col_indices
x_flat = tf.reshape(x, [-1])

# use dynamic stitch, it merges the array by taking value either
# from array1[index1] or array2[index2], if indices conflict,
# the later one is used 
unchanged_indices = tf.range(tf.size(x_flat))
changed_indices = linear_indices
x_flat = tf.dynamic_stitch([unchanged_indices, changed_indices],
                           [x_flat, replacement_vals])
x = tf.reshape(x_flat, x.get_shape())
print x.eval()