Adding an additional channel to a 3 channel tensor-CodePudding

I would like to combine a tensor of shape [3,1024,1024] and a tensor of shape [1,1024,1024] in order to form a single tensor of shape [4,1024,1024]

This is to combine the channels of an RGB image to a depth image in the format of [r,g,b,d] for each pixel

Im am currently trying to do this like this:

tensor = tf.concat([imageTensor, depthTensor], axis=2)

But I receive the error

InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [3,1024,1024] vs. shape[1] = [1,1024,1024] [Op:ConcatV2]

I was just wondering how this would be done?

CodePudding user response：

You want to concatenate on axis=0:

import tensorflow as tf
t1 = tf.random.uniform((3, 1024, 1024))
t2 = tf.random.uniform((1, 1024, 1024))
final_tensor = tf.concat((t1, t2), axis=0)
print(final_tensor.shape)
(4, 1024, 1024)

CodePudding user response：

Depending on what your tensors look like, try:

import tensorflow as tf

imageTensor = tf.random.normal((3,1024,1024))
depthTensor = tf.random.normal((1,1024,1024))
tensor = tf.concat([imageTensor, depthTensor], axis=0)
print(tensor.shape)
# (4, 1024, 1024)

Or:

imageTensor = tf.random.normal((1024,1024,3))
depthTensor = tf.random.normal((1024,1024, 1))
tensor = tf.concat([imageTensor, depthTensor], axis=-1)
print(tensor.shape)
# (1024, 1024, 4)