A brief discussion on the use of tensorflow

concat() is to connect the tensors along the specified dimension. Among them, tensorflow version 1.3 is defined as follows:

concat(values,axis,name='concat')

1. For 2 dimensions, 0 represents rows and 1 represents columns

t1 = [[1, 2, 3], [4, 5, 6]]
t2 = [[7, 8, 9], [10, 11, 12]]
 
with () as sess:
 print((([t1, t2], 0) ))

The results are: [[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]

t1 = [[1, 2, 3], [4, 5, 6]]
t2 = [[7, 8, 9], [10, 11, 12]]
 
with () as sess:
 print((([t1, t2], 1) ))

The result is: [[1, 2, 3, 7, 8, 9], [4, 5, 6, 10, 11, 12]]

2. For 3 dimensions, 0 means vertical, 1 means row, and 2 means column

t1 = [[[1, 1, 1],[2, 2, 2]],[[3, 3, 3],[4, 4, 4]]]
 
t2 = [[[5, 5, 5],[6, 6, 6]],[[7, 7, 7],[8, 8, 8]]]
 
with () as sess:
 print((([t1, t2], 0) ))

Results: [[[1 1 1],[2 2 2]] , [[3 3 3],[4 4 4]] , [[5 5 5],[6 6 6]] , [[7 7 7],[8 8 8]]]
Tensor("concat_30:0", shape=(4, 2, 3), dtype=int32)

The result of axis=1 is as follows:

Tensor("concat_31:0", shape=(2, 4, 3), dtype=int32)
[[[1 1 1]， [2 2 2]，[5 5 5]，[6 6 6]]， [[3 3 3]， [4 4 4]，[7 7 7]， [8 8 8]]]

The result of axis=2 is as follows:

Tensor("concat_32:0", shape=(2, 2, 6), dtype=int32)
[[[1 1 1 5 5 5]，[2 2 2 6 6 6]]， [[3 3 3 7 7 7]， [4 4 4 8 8 8]]]

The above brief discussion on the use of () in tensorflow is all the content I share with you. I hope you can give you a reference and I hope you can support me more.