Commit f6d81b94 authored by lucas_miranda's avatar lucas_miranda
Browse files

Modified LSTMs to work with cuDNN implementation

parent dbf138d8
......@@ -203,7 +203,7 @@ class SEQ_2_SEQ_GMVAE:
loc=tf.random.uniform(
shape=[self.ENCODING], minval=0, maxval=15
),
scale=10,
scale=1,
),
reinterpreted_batch_ndims=1,
)
......
Supports Markdown
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