[英]How to concat two tensor with dynamic shape in tensorflow?
I have two tensor I want to contact in tensorflow.我有两个张量我想在 tensorflow 中联系。
So the shape of these tensor are: (Bs,dynamics,n_features)
所以这些张量的形状是:
(Bs,dynamics,n_features)
The batch_size
and n_features
are guarantee to be same, so I think this operation is possible. batch_size
和n_features
保证是相同的,所以我认为这个操作是可能的。
However, I think tensorflow will run a pre-check?但是,我认为 tensorflow 会进行预检查吗? (sorry I am new to tensorflow), tensorflow will check if two tensor with shape
(None,None,n_features)
could be concatenated in axis 1, which is not possible, because it doesn't know what is the result of None+None
(对不起,我是 tensorflow 的新手),tensorflow 将检查两个形状为
(None,None,n_features)
的张量是否可以在轴 1 上连接,这是不可能的,因为它不知道None+None
的结果是什么
Anybody has any idea to this?有人对此有任何想法吗?
Concatenating should not be a problem in your case:在您的情况下,连接应该不是问题:
import tensorflow as tf
x1 = tf.random.normal((5, 10, 20))
x2 = tf.random.normal((5, 33, 20))
@tf.function
def concatenate(x1, x2):
return tf.concat([x1, x2], axis=1)
concatenate(x1, x2).shape
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.