luongminh97 luongminh97 - 5 months ago 24
Python Question

What is the default variable initializer in Tensorflow?

What is the default method of variable initialization used when

is called without any specification for the initializer? The Docs just says 'None'.

Answer Source

From the documentation:

If initializer is None (the default), the default initializer passed in the variable scope will be used. If that one is None too, a glorot_uniform_initializer will be used.

The glorot_uniform_initializer function initializes values from a uniform distribution.

It is an unexported function, documented as:

The Glorot uniform initializer, also called Xavier uniform initializer.

It draws samples from a uniform distribution within [-limit, limit],
where limit is sqrt(6 / (fan_in + fan_out))
where fan_in is the number of input units in the weight tensor
and fan_out is the number of output units in the weight tensor.