Hacker News
new
|
past
|
comments
|
ask
|
show
|
jobs
|
submit
login
diyer22
80 days ago
|
parent
|
context
|
favorite
| on:
Show HN: I invented a new generative model and got...
In DDN, 1×1 convolutions are used only in the output layers of the Discrete Distribution Layer (DDL). The NN blocks between DDLs, which supply the fundamental computational power and parameter count, adopt standard 3×3 convolutions.
randomNumber7
80 days ago
[–]
Was there a specific reason for this choice?
diyer22
80 days ago
|
parent
[–]
1x1 convolution is the most lightweight operator for transforming features into outputs.
3x3 convolution is the most common operator used to provide basic computational power.
Guidelines
|
FAQ
|
Lists
|
API
|
Security
|
Legal
|
Apply to YC
|
Contact
Search:
