View source: R/attention-layers.R
Uses .compute_attention_component function vie T2T framework
1 2 3 4 5 6 7 8 9 10 11 | layer_compute_qkv(
query,
memory = NULL,
key_depth = 64L,
value_depth = 64L,
q_filter_width = 1L,
kv_filter_width = 1L,
q_padding = "SAME",
kv_padding = "SAME",
vars_3d_num_heads = 0L
)
|
Add the following code to your website.
For more information on customizing the embed code, read Embedding Snippets.