Commit 4070fa63 authored by Dan O'Shea's avatar Dan O'Shea
Browse files

Adjusting init_linear comment

parent 2c9a1100
...@@ -92,7 +92,7 @@ def init_linear(in_size, out_size, do_bias=True, mat_init_value=None, ...@@ -92,7 +92,7 @@ def init_linear(in_size, out_size, do_bias=True, mat_init_value=None,
in_size: The integer size of the non-batc input dimension. [(x),y] in_size: The integer size of the non-batc input dimension. [(x),y]
out_size: The integer size of non-batch output dimension. [x,(y)] out_size: The integer size of non-batch output dimension. [x,(y)]
do_bias (optional): Add a (learnable) bias vector to the operation, do_bias (optional): Add a (learnable) bias vector to the operation,
if false, b will be an appropriately sized, non-trainable vector if false, b will be None
mat_init_value (optional): numpy constant for matrix initialization, if None mat_init_value (optional): numpy constant for matrix initialization, if None
, do random, with additional parameters. , do random, with additional parameters.
alpha (optional): A multiplicative scaling for the weight initialization alpha (optional): A multiplicative scaling for the weight initialization
......
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment