Difference between different tensorflow fully connected layers

Question

What is the difference between the different fully connected layers available in tensorflow. I understand that there could 2 versions: Object oriented and functional, but I was able to find 4 different layers in tensorflow:

1. tf.keras.layers.Dense
2. tf.layers.dense
3. tf.layers.Dense
4. tf.contrib.layers.fully_connected

The documentation contains examples using all of them. I'd also like to know when to use each layer.

Answer 1

1. Keras is a deep learning library which functions as a wrapper over 'lower level' languges such as Tensorflow and Theano. It has recently been integrated as a Tensorflow project and is part of the code-base. If you are using 'raw' Tensorflow, you should not use this layer.

2. Tensorflow defines a functional interface. Layers and operations that are lowercase are typically part of this. These functions are used as building blocks when defining a custom layer or a loss function.

3. This is the layer you should be using.

4. This comes from the contrib library - features that are typically more experimental and volatile. Once a feature is deemed stable, you should use its other implementation (3). (4) will still be present in the library to maintain backwards compatability.

Answer 2

1. Is a Keras wrapper function. Its functionality is same as 3. Checkout Keras .
2. Its a functional interface for tensorflow.
3. Commonly used.
4. Function under development.

Technically speaking first 3 have same functionality (same inputs and outputs).