Aleph7 - 2 years ago 2286

Python Question

I'm porting my Caffe network over to TensorFlow but it doesn't seem to have xavier initialization. I'm using

`truncated_normal`

Recommended for you: Get network issues from **WhatsUp Gold**. **Not end users.**

Answer Source

A nice wrapper around `tensorflow`

called `prettytensor`

gives an implementation in the source code (copied directly from here):

```
def xavier_init(n_inputs, n_outputs, uniform=True):
"""Set the parameter initialization using the method described.
This method is designed to keep the scale of the gradients roughly the same
in all layers.
Xavier Glorot and Yoshua Bengio (2010):
Understanding the difficulty of training deep feedforward neural
networks. International conference on artificial intelligence and
statistics.
Args:
n_inputs: The number of input nodes into each output.
n_outputs: The number of output nodes for each input.
uniform: If true use a uniform distribution, otherwise use a normal.
Returns:
An initializer.
"""
if uniform:
# 6 was used in the paper.
init_range = math.sqrt(6.0 / (n_inputs + n_outputs))
return tf.random_uniform_initializer(-init_range, init_range)
else:
# 3 gives us approximately the same limits as above since this repicks
# values greater than 2 standard deviations from the mean.
stddev = math.sqrt(3.0 / (n_inputs + n_outputs))
return tf.truncated_normal_initializer(stddev=stddev)
```

Recommended from our users: **Dynamic Network Monitoring from WhatsUp Gold from IPSwitch**. ** Free Download**