Using SparseTensor as a trainable variable?

Question

I\'m trying to use SparseTensor to represent weight variables in a fully-connected layer.
However, it seems that TensorFlow 0.8 doesn\'t allow to use Sp

Answer 1

As a workaround to your problem, you can provide a tf.Variable (until Tensorflow v0.8) for the values of a sparse tensor. The sparsity structure has to be pre-defined in that case, the weights however remain trainable.

weights = tf.Variable()
sparse_var = tf.SparseTensor(, weights, )  # v0.8
sparse_var = tf.SparseTensor(, tf.identity(weights), )  # v0.9