View source: R/attention-layers.R
Simplified Self attention layer Expecting shape(x) == (batch, maxtime, units)
1 2 3 4 5 6 7 8 | layer_self_attention_simple(
x,
filter_depth = 32L,
output_depth = 64L,
num_parts = 3L,
dropout = 0,
share_kv = TRUE
)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.