tf.concat  |  TensorFlow v2.0.0 (original) (raw)

tf.concat

Stay organized with collections Save and categorize content based on your preferences.

Concatenates tensors along one dimension.

View aliases

Compat aliases for migration

SeeMigration guide for more details.

tf.compat.v1.concat

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

Concatenates the list of tensors values along dimension axis. Ifvalues[i].shape = [D0, D1, ... Daxis(i), ...Dn], the concatenated result has shape

[D0, D1, ... Raxis, ...Dn]

where

Raxis = sum(Daxis(i))

That is, the data from the input tensors is joined along the axisdimension.

The number of dimensions of the input tensors must match, and all dimensions except axis must be equal.

For example:

t1 = [[1, 2, 3], [4, 5, 6]]
t2 = [[7, 8, 9], [10, 11, 12]]
tf.concat([t1, t2], 0)  # [[1, 2, 3], [4, 5, 6], [7, 8, 9], [10, 11, 12]]
tf.concat([t1, t2], 1)  # [[1, 2, 3, 7, 8, 9], [4, 5, 6, 10, 11, 12]]

# tensor t3 with shape [2, 3]
# tensor t4 with shape [2, 3]
tf.shape(tf.concat([t3, t4], 0))  # [4, 3]
tf.shape(tf.concat([t3, t4], 1))  # [2, 6]

As in Python, the axis could also be negative numbers. Negative axisare interpreted as counting from the end of the rank, i.e.,axis + rank(values)-th dimension.

For example:

t1 = [[[1, 2], [2, 3]], [[4, 4], [5, 3]]]
t2 = [[[7, 4], [8, 4]], [[2, 10], [15, 11]]]
tf.concat([t1, t2], -1)

would produce:

[[[ 1,  2,  7,  4],
  [ 2,  3,  8,  4]],

 [[ 4,  4,  2, 10],
  [ 5,  3, 15, 11]]]

tf.concat([tf.expand_dims(t, axis) for t in tensors], axis)

can be rewritten as

tf.stack(tensors, axis=axis)