tensorflow theano.tensor.set_subtensor等价物

Question

我正在keras中实现一个操作,这样它就可以同时处理theano和tensorflow后端.假设操作的输入是:

array([[ 0,  1,  2],
       [ 3,  4,  5],
       [ 6,  7,  8],
       [ 9, 10, 11]], dtype=int64)

那么它的输出应该是:

array([[ 0,  1,  2,  3,  4,  5],
       [ 3,  4,  5,  0,  1,  2],
       [ 6,  7,  8,  9,  10, 11],
       [ 9, 10, 11,  6,   7, 8]], dtype=int64)

我的代码如下:

from keras import backend as K
def pairreshape(x,target_dim,input_shape):
    x1, x2 = x[0::2,], x[1::2,]
    x1_concate = K.concatenate((x1,x2), axis=target_dim)
    x2_concate = K.concatenate((x2,x1), axis=target_dim)
    if K.image_dim_ordering() == 'th':
        import theano.tensor as T
        x_new = T.repeat(x,2,axis=target_dim)
        x_new = T.set_subtensor(x_new[0::2], x1_concate)
        x_new = T.set_subtensor(x_new[1::2], x2_concate)
    elif K.image_dim_ordering() == 'tf':
        import tensorflow as tf
        repeats = [1] * len(input_shape)
        repeats[target_dim] = 2
        x_new = tf.tile(x, repeats)
        x_new[0::2] = x1_concate #TypeError: 'Tensor' object does not support item assignment
        x_new[1::2] = x2_concate #TypeError: 'Tensor' object does not support item assignment

我已经成功实现了theano,但我无法弄清楚如何通过tensorflow分配张量.tensorflow中最后两行张量分配将报告错误.张量流中是否有T.set_subtensor等价？或者你能否推荐一个更好的操作实施？谢谢.

Answer 1

TensorFlow 张量是只读的。为了修改你需要使用变量和.assign（=不能在Python中被覆盖）

tensor = tf.Variable(tf.ones((3,3)))
sess.run(tf.initialize_all_variables())
sess.run(tensor[1:, 1:].assign(2*tensor[1:,1:]))
print(tensor.eval())

输出

[[ 1.  1.  1.]
 [ 1.  2.  2.]
 [ 1.  2.  2.]]