good first issuetf
倉庫指標
- 星標
- (1,728 顆星)
- PR 合併指標
- (30 天內沒有已合併 PR)
描述
The current GaussianMLPModel actually represents several architecture variants, which makes it difficult to use and to test. We should split it into several variants based on architecture (and possibly parameterization)
| description | mean | std_param |
|---|---|---|
| fixed variance | MLP1 | parameter (trainable or not) |
| split network | MLP1 | MLP2 |
| shared network/multi-headed | MLP1/head1 | MLP1/head2 |