Clever Geek Handbook

How to concatenate two tensors horizontally in TensorFlow?

I have 2 shape tensors (100, 4)

and (100, 2)

. I would like to perform a concatenation operation in TensorFlow, similar to np.hstack

that in NumPy, so that the output is shaped (100, 6)

. Is there a TensorFlow feature for this?

+3


source to share


1 answer


You can use tf.concat

for this purpose as follows:

sess=tf.Session()
t1 = [[1, 2], [4, 5]]
t2 = [[7, 8, 9], [10, 11, 12]]
res=tf.concat(concat_dim=1,values=[t1, t2])
print(res.eval(session=sess))


Will print

[[ 1  2  7  8  9]
 [ 4  5 10 11 12]]
+3


source






More articles:


All Articles