I'm trying to understand what's possible with TensorFlow's output layer. Specifically, are outputs always a flat array?

Since a neuron (or 'unit', in TF) has just one number, and there is only one set of outputs, it seems that output must have a single dimension. With one-hot probabilities, this is easy to understand. But what about an image?

If my output is going to be a picture, can I have TF output a multi-dimensional array of pixels, e.g. [[r0, g0, b0], [r1, g1, b1], ...]? If so, how would that network be constructed? How would I define the output layer's dimensionality/shape?

The only param I know of that defines output shape is this, from tf.layers.dense, which seems inherently one-dimensional:

  • units (number) Positive integer, dimensionality of the output space.

Any help you can provide is greatly appreciated!

Reference: https://js.tensorflow.org/api/latest/#layers.dense

1 Answer 1


The output layer does not have to be 1D (excl. batch size) but even if it is, it does not necessary mean you cannot transform it to a n dimensional space. Consider an autoencoder used to reconstruct an image:

  1. In the simplest case we could flatten a image (e.g. 24 x 24 pixels) and learn a network to predict the 24 x 24 pixels (output a 1D image). These pixels can then be transformed back to an 2D image (https://www.tensorflow.org/tutorials/generative/autoencoder). So in other words, even if your network outputs a 1D shape, nothing prevent you from reconstructing it to a higher space.

  2. We can achieve similar results as stated in the point above, by using an encoding network (convolutional + pooling layers) followed by a decoding layer (transposed convolutional + up sampling layers). In this case you can effectively generate a 2D image directly (https://www.tensorflow.org/tutorials/generative/cvae).

You can also look at image segmentation networks for inspiration of how higher dimensions outputs can be generated.

  • $\begingroup$ Thanks very much for the info! $\endgroup$
    – Stewii
    Nov 22, 2020 at 0:14
  • $\begingroup$ Just to clarify - is the output made up of multiple layers with hierarchical structure? Or is the output flat, but TensorFlow is 'packaging' that flat array into nested arrays (or a tensor)? I'm confused in trying to visualize this setup, mainly because every graph I've ever seen has just one output layer. I suppose it could be arbitrarily broken up, e.g. 10 nodes that are treated as 2 sets of 5, by the predict() call, for example. - thanks again! I will research the material you suggest. $\endgroup$
    – Stewii
    Nov 22, 2020 at 0:18

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.