我需要遍历长度可变的第一维,我该如何设法做到这一点?如果不可能有任何解决方法?
答案 0 :(得分:3)
demo 不支持:
如果
value.shape[axis]
未知,则引发ValueError。
但您可以尝试使用tf.unstack
迭代张量切片。这是一个计算总和的例子:
# Input tensor: trying to iterate along axis=0
x = tf.placeholder(dtype=tf.float32, shape=[None, 3])
batch_size = tf.shape(x)[0]
def cond(x, i, _):
return i < batch_size
def body(x, i, x_prev):
# Do some operation with `x_prev` and `x[i]`. Here we just add the slices
sum = x_prev + x[i]
return x, i + 1, sum
# This means: starting from 0, apply the body, while the `cond` is true
_, _, c = tf.while_loop(cond, body, (x, 0, tf.zeros([3])))
# Test it
with tf.Session() as sess:
data = np.arange(12).reshape([4, 3])
print(data)
result = sess.run(c, feed_dict={x: data})
print(result)
输出:
[[ 0 1 2]
[ 3 4 5]
[ 6 7 8]
[ 9 10 11]]
[ 18. 22. 26.]